In Journal of food biochemistry

Heydarnia Elaheh, Taghian Farzaneh, Jalali Dehkordi Khosro, Moghadasi Mehrzad

2022-Jul-02

antioxidant supplement, apoptosis markers, combined exercise, streptozotocin-induced diabetic rats

In Integrative biology : quantitative biosciences from nano to macro

Gayan Sukanya, Joshi Gargee, Dey Tuli

2022-Jul-02

cancer biomarker, circulatory tumor cell, mitochondria, mtDNA, single-cell omics

In Schizophrenia research ; h5-index 61.0

Bracher-Smith Matthew, Rees Elliott, Menzies Georgina, Walters James T R, O’Donovan Michael C, Owen Michael J, Kirov George, Escott-Price Valentina

2022-Jun-29

Machine learning, Polygenic risk scores, Precision psychiatry, Schizophrenia

In Alzheimer's & dementia : the journal of the Alzheimer's Association

BACKGROUND : High blood pressure (BP) is a risk factor for late-life brain health; however, the association of elevated BP with brain health in mid-life is unclear.

METHODS : We identified 661 participants from the Coronary Artery Risk Development in Young Adults Study (age 18-30 at baseline) with 30 years of follow-up and brain magnetic resonance imaging at year 30. Cumulative exposure of BP was estimated by time-weighted averages (TWA). Ideal cardiovascular health was defined as systolic BP < 120 mm Hg, diastolic BP < 80 mm Hg. Brain age was calculated using previously validated high dimensional machine learning pattern analyses.

RESULTS : Every 5 mmHg increment in TWA systolic BP was associated with approximately 1-year greater brain age (95% confidence interval [CI]: 0.50-1.36) Participants with TWA systolic or diastolic BP over the recommended guidelines for ideal cardiovascular health, had on average 3-year greater brain age (95% CI: 1.00-4.67; 95% CI: 1.45-5.13, respectively).

CONCLUSION : Elevated BP from early to mid adulthood, even below clinical cut-offs, is associated with advanced brain aging in mid-life.

Dintica Christina S, Habes Mohamad, Erus Guray, Vittinghoff Eric, Davatzikos Christos, Nasrallah Ilya M, Launer Lenore J, Sidney Stephen, Yaffe Kristine

2022-Jul-02

blood pressure, brain age, brain imaging, cognition, longitudinal, magnetic resonance imaging, mid-life, risk factors

In Hepatology international

INTRODUCTION : Immunotherapy is a new promising treatment for patients with advanced hepatocellular carcinoma (HCC), but is costly and potentially associated with considerable side effects. This study aimed to evaluate the role of machine learning (ML) models in predicting the 1-year cancer-related mortality in advanced HCC patients treated with immunotherapy.

METHOD : 395 HCC patients who had received immunotherapy (including nivolumab, pembrolizumab or ipilimumab) between 2014 and 2019 in Hong Kong were included. The whole data sets were randomly divided into training (n = 316) and internal validation (n = 79) set. The data set, including 47 clinical variables, was used to construct six different ML models in predicting the risk of 1-year mortality. The performances of ML models were measured by the area under receiver operating characteristic curve (AUC) and their performances were compared with C-Reactive protein and Alpha Fetoprotein in ImmunoTherapY score (CRAFITY) and albumin-bilirubin (ALBI) score. The ML models were further validated with an external cohort between 2020 and 2021.

RESULTS : The 1-year cancer-related mortality was 51.1%. Of the six ML models, the random forest (RF) has the highest AUC of 0.92 (95% CI 0.87-0.98), which was better than logistic regression (0.82, p = 0.01) as well as the CRAFITY (0.68, p < 0.01) and ALBI score (0.84, p = 0.04). RF had the lowest false positive (2.0%) and false negative rate (5.2%), and performed better than CRAFITY score in the external validation cohort (0.91 vs 0.66, p < 0.01). High baseline AFP, bilirubin and alkaline phosphatase were three common risk factors identified by all ML models.

CONCLUSION : ML models could predict 1-year cancer-related mortality in HCC patients treated with immunotherapy, which may help to select patients who would benefit from this treatment.

Lui Thomas Ka Luen, Cheung Ka Shing, Leung Wai Keung

2022-Jul-02

Artificial intelligence, Gradient boosting, Hepatocellular carcinoma, Immunotherapy, Ipilimumab, Machine learning, Mortality, Nivolumab, Pembrolizumab, Random forest

In European radiology ; h5-index 62.0

OBJECTIVES : While chest radiograph (CXR) is the first-line imaging investigation in patients with respiratory symptoms, differentiating COVID-19 from other respiratory infections on CXR remains challenging. We developed and validated an AI system for COVID-19 detection on presenting CXR.

METHODS : A deep learning model (RadGenX), trained on 168,850 CXRs, was validated on a large international test set of presenting CXRs of symptomatic patients from 9 study sites (US, Italy, and Hong Kong SAR) and 2 public datasets from the US and Europe. Performance was measured by area under the receiver operator characteristic curve (AUC). Bootstrapped simulations were performed to assess performance across a range of potential COVID-19 disease prevalence values (3.33 to 33.3%). Comparison against international radiologists was performed on an independent test set of 852 cases.

RESULTS : RadGenX achieved an AUC of 0.89 on 4-fold cross-validation and an AUC of 0.79 (95%CI 0.78-0.80) on an independent test cohort of 5,894 patients. Delong's test showed statistical differences in model performance across patients from different regions (p < 0.01), disease severity (p < 0.001), gender (p < 0.001), and age (p = 0.03). Prevalence simulations showed the negative predictive value increases from 86.1% at 33.3% prevalence, to greater than 98.5% at any prevalence below 4.5%. Compared with radiologists, McNemar's test showed the model has higher sensitivity (p < 0.001) but lower specificity (p < 0.001).

CONCLUSION : An AI model that predicts COVID-19 infection on CXR in symptomatic patients was validated on a large international cohort providing valuable context on testing and performance expectations for AI systems that perform COVID-19 prediction on CXR.

KEY POINTS : • An AI model developed using CXRs to detect COVID-19 was validated in a large multi-center cohort of 5,894 patients from 9 prospectively recruited sites and 2 public datasets. • Differences in AI model performance were seen across region, disease severity, gender, and age. • Prevalence simulations on the international test set demonstrate the model's NPV is greater than 98.5% at any prevalence below 4.5%.

Kuo Michael D, Chiu Keith W H, Wang David S, Larici Anna Rita, Poplavskiy Dmytro, Valentini Adele, Napoli Alessandro, Borghesi Andrea, Ligabue Guido, Fang Xin Hao B, Wong Hing Ki C, Zhang Sailong, Hunter John R, Mousa Abeer, Infante Amato, Elia Lorenzo, Golemi Salvatore, Yu Leung Ho P, Hui Christopher K M, Erickson Bradley J

2022-Jul-02

Artificial intelligence, COVID-19, Public health, Radiology, Thoracic

In European radiology ; h5-index 62.0

OBJECTIVES : Content-based image retrieval systems (CBIRS) are a new and potentially impactful tool for radiological reporting, but their clinical evaluation is largely missing. This study aimed at assessing the effect of CBIRS on the interpretation of chest CT scans from patients with suspected diffuse parenchymal lung disease (DPLD).

MATERIALS AND METHODS : A total of 108 retrospectively included chest CT scans with 22 unique, clinically and/or histopathologically verified diagnoses were read by eight radiologists (four residents, four attending, median years reading chest CT scans 2.1± 0.7 and 12 ± 1.8, respectively). The radiologists read and provided the suspected diagnosis at a certified radiological workstation to simulate clinical routine. Half of the readings were done without CBIRS and half with the additional support of the CBIRS. The CBIRS retrieved the most likely of 19 lung-specific patterns from a large database of 6542 thin-section CT scans and provided relevant information (e.g., a list of potential differential diagnoses).

RESULTS : Reading time decreased by 31.3% (p < 0.001) despite the radiologists searching for additional information more frequently when the CBIRS was available (154 [72%] vs. 95 [43%], p < 0.001). There was a trend towards higher overall diagnostic accuracy (42.2% vs 34.7%, p = 0.083) when the CBIRS was available.

CONCLUSION : The use of the CBIRS had a beneficial impact on the reading time of chest CT scans in cases with DPLD. In addition, both resident and attending radiologists were more likely to consult informational resources if they had access to the CBIRS. Further studies are needed to confirm the observed trend towards increased diagnostic accuracy with the use of a CBIRS in practice.

KEY POINTS : • A content-based image retrieval system for supporting the diagnostic process of reading chest CT scans can decrease reading time by 31.3% (p < 0.001). • The decrease in reading time was present despite frequent usage of the content-based image retrieval system. • Additionally, a trend towards higher diagnostic accuracy was observed when using the content-based image retrieval system (42.2% vs 34.7%, p = 0.083).

Röhrich Sebastian, Heidinger Benedikt H, Prayer Florian, Weber Michael, Krenn Markus, Zhang Rui, Sufana Julie, Scheithe Jakob, Kanbur Incifer, Korajac Aida, Pötsch Nina, Raudner Marcus, Al-Mukhtar Ali, Fueger Barbara J, Milos Ruxandra-Iulia, Scharitzer Martina, Langs Georg, Prosch Helmut

2022-Jul-02

Artificial intelligence, Diagnosis, Computer assisted, Lung diseases, Interstitial, Tomography, X-ray computed

In Current opinion in allergy and clinical immunology

PURPOSE OF REVIEW : Severe asthma requires intensive pharmacological treatment to achieve disease control. Oral corticosteroids are effective, but their use is burdened with important side effects. Biologics targeting the specific inflammatory pathways underpinning the disease have been shown to be effective but not all patients respond equally well. As we treat more patients than those who can respond, our inability to predict responders has important healthcare costs considering that biologics are expensive drugs. Thus, a more precise choice of the 'right patients' to be prescribed with the 'right biologics' would be desirable.

RECENT FINDINGS : Machine learning techniques showed that it is possible to increase our ability to predict outcomes in patients treated with biologics. Recently, we identified by cluster analysis four different clusters within the T2 high phenotype with differential benralizumab response. Two of these clusters, characterized by higher levels of inflammatory markers, showed the highest response rate (80-90%).

SUMMARY : Machine learning holds promise for asthma research enabling us to predict which patients will respond to which drug. These techniques can facilitate the diagnostic workflow and increase the chance of selecting the more appropriate treatment option for the individual patient, enhancing patient care and satisfaction.

Di Bona Danilo, Spataro Federico, Carlucci Palma, Paoletti Giovanni, Canonica Giorgio W

2022-Jul-04

In Aging cell ; h5-index 58.0

Johnson Adiv A, English Bradley W, Shokhirev Maxim N, Sinclair David A, Cuellar Trinna L

2022-Jul-02

aging clock, biological age, epigenetic age, healthspan, lifespan, longevity, machine learning, mortality

In Annals of hematology ; h5-index 39.0

Piñana José Luis, Rodríguez-Belenguer Pablo, Caballero Dolores, Martino Rodrigo, Lopez-Corral Lucia, Terol María-José, Vazquez Lourdes, Calabuig Marisa, Sanz-Linares Gabriela, Marin-Jimenez Francisca, Alonso Carmen, Montoro Juan, Ferrer Elena, Facal Ana, Pascual María-Jesús, Rodriguez-Fernandez Alicia, Olave María T, Cascales-Hernandez Almudena, Gago Beatriz, Hernández-Rivas José-Ángel, Villalon Lucia, Corona Magdalena, Roldán-Pérez Alicia, Ribes-Amoros Julia, González-Santillana Clara, Garcia-Sanz Ramon, Navarro David, Serrano-López Antonio J, Cedillo Ángel, Soria-Olivas Emilio, Sureda Anna, Solano Carlos

2022-Jul-02

Allogeneic stem cell transplantation, Autologous stem cell transplantation, Bayesian Networks, CAR-T therapy, COVID-19, Chronic lymphocytic leukemia, Hematological malignancies, Immunocompromised patients, Moderna mRNA-1273, Non-Hodgkin lymphoma, Pfizer-BioNTech BNT162b2, Probabilistic graphical models, Respiratory virus, SARS-CoV-2 vaccines, mRNA vaccine

In Molecular ecology resources

Kronenberger J A, Wilcox T M, Mason D H, Franklin T W, McKelvey K S, Young M K, Schwartz M K

2022-Jul-01

assay, base-pair mismatches, eDNA, environmental DNA, random forest, specificity

In Computers in biology and medicine

Liu Jia, Qi Jing, Chen Wei, Nian Yongjian

2022-Jun-15

Auxiliary learning, Deep learning, Feature fusion, Multi-task learning, Pneumonia

In Environmental science and pollution research international

Kumari Surbhi, Singh Sunil Kumar

2022-Jul-02

Air pollution, CO 2 emissions, Holt-Winters, LSTM, Linear regression, Random forest regressor, Time series forecasting

In Annals of hematology ; h5-index 39.0

Piñana José Luis, Rodríguez-Belenguer Pablo, Caballero Dolores, Martino Rodrigo, Lopez-Corral Lucia, Terol María-José, Vazquez Lourdes, Calabuig Marisa, Sanz-Linares Gabriela, Marin-Jimenez Francisca, Alonso Carmen, Montoro Juan, Ferrer Elena, Facal Ana, Pascual María-Jesús, Rodriguez-Fernandez Alicia, Olave María T, Cascales-Hernandez Almudena, Gago Beatriz, Hernández-Rivas José-Ángel, Villalon Lucia, Corona Magdalena, Roldán-Pérez Alicia, Ribes-Amoros Julia, González-Santillana Clara, Garcia-Sanz Ramon, Navarro David, Serrano-López Antonio J, Cedillo Ángel, Soria-Olivas Emilio, Sureda Anna, Solano Carlos

2022-Jul-02

Allogeneic stem cell transplantation, Autologous stem cell transplantation, Bayesian Networks, CAR-T therapy, COVID-19, Chronic lymphocytic leukemia, Hematological malignancies, Immunocompromised patients, Moderna mRNA-1273, Non-Hodgkin lymphoma, Pfizer-BioNTech BNT162b2, Probabilistic graphical models, Respiratory virus, SARS-CoV-2 vaccines, mRNA vaccine

In Scientific reports ; h5-index 158.0

Kang Jieun, Hwang Sangwon, Lee Tae Sic, Cho Jooyoung, Seo Dong Min, Choi Seong Jin, Uh Young

2022-Jul-02

In Nature communications ; h5-index 260.0

Green Anna G, Yoon Chang Ho, Chen Michael L, Ektefaie Yasha, Fina Mack, Freschi Luca, Gröschel Matthias I, Kohane Isaac, Beam Andrew, Farhat Maha

2022-Jul-02

In Communications biology

Zhao Nan, Zhuo Maji, Tian Kun, Gong Xinqi

2022-Jul-02

In BMC medical research methodology

BACKGROUND : Discharge medical notes written by physicians contain important information about the health condition of patients. Many deep learning algorithms have been successfully applied to extract important information from unstructured medical notes data that can entail subsequent actionable results in the medical domain. This study aims to explore the model performance of various deep learning algorithms in text classification tasks on medical notes with respect to different disease class imbalance scenarios.

METHODS : In this study, we employed seven artificial intelligence models, a CNN (Convolutional Neural Network), a Transformer encoder, a pretrained BERT (Bidirectional Encoder Representations from Transformers), and four typical sequence neural networks models, namely, RNN (Recurrent Neural Network), GRU (Gated Recurrent Unit), LSTM (Long Short-Term Memory), and Bi-LSTM (Bi-directional Long Short-Term Memory) to classify the presence or absence of 16 disease conditions from patients' discharge summary notes. We analyzed this question as a composition of 16 binary separate classification problems. The model performance of the seven models on each of the 16 datasets with various levels of imbalance between classes were compared in terms of AUC-ROC (Area Under the Curve of the Receiver Operating Characteristic), AUC-PR (Area Under the Curve of Precision and Recall), F1 Score, and Balanced Accuracy as well as the training time. The model performances were also compared in combination with different word embedding approaches (GloVe, BioWordVec, and no pre-trained word embeddings).

RESULTS : The analyses of these 16 binary classification problems showed that the Transformer encoder model performs the best in nearly all scenarios. In addition, when the disease prevalence is close to or greater than 50%, the Convolutional Neural Network model achieved a comparable performance to the Transformer encoder, and its training time was 17.6% shorter than the second fastest model, 91.3% shorter than the Transformer encoder, and 94.7% shorter than the pre-trained BERT-Base model. The BioWordVec embeddings slightly improved the performance of the Bi-LSTM model in most disease prevalence scenarios, while the CNN model performed better without pre-trained word embeddings. In addition, the training time was significantly reduced with the GloVe embeddings for all models.

CONCLUSIONS : For classification tasks on medical notes, Transformer encoders are the best choice if the computation resource is not an issue. Otherwise, when the classes are relatively balanced, CNNs are a leading candidate because of their competitive performance and computational efficiency.

Lu Hongxia, Ehwerhemuepha Louis, Rakovski Cyril

2022-Jul-02

BERT, CNN, Deep learning, Embedding, Medical notes, Text classification, Transformer encoder

In Diagnostic and interventional imaging

PURPOSE : The main objective of this study was to compare radiologists' performance without and with artificial intelligence (AI) assistance for the detection of bone fractures from trauma emergencies.

MATERIALS AND METHODS : Five hundred consecutive patients (232 women, 268 men) with a mean age of 37 ± 28 (SD) years (age range: 0.25-99 years) were retrospectively included. Three radiologists independently interpreted radiographs without then with AI assistance after a 1-month minimum washout period. The ground truth was determined by consensus reading between musculoskeletal radiologists and AI results. Patient-wise sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) for fracture detection and reading time were compared between unassisted and AI-assisted readings of radiologists. Their performances were also assessed by receiver operating characteristic (ROC) curves.

RESULTS : AI improved the patient-wise sensitivity of radiologists for fracture detection by 20% (95% confidence interval [CI]: 14-26), P< 0.001) and their specificity by 0.6% (95% CI: -0.9-1.5; P = 0.47). It increased the PPV by 2.9% (95% CI: 0.4-5.4; P = 0.08) and the NPV by 10% (95% CI: 6.8-13.3; P < 0.001). Thanks to AI, the area under the ROC curve for fracture detection of readers increased respectively by 10.6%, 10.2% and 9.9%. Their mean reading time per patient decreased by respectively 10, 16 and 12 s (P < 0.001).

CONCLUSIONS : AI-assisted radiologists work better and faster compared to unassisted radiologists. AI is of great aid to radiologists in daily trauma emergencies, and could reduce the cost of missed fractures.

Canoni-Meynet Lisa, Verdot Pierre, Danner Alexis, Calame Paul, Aubry Sébastien

2022-Jun-29

Artificial intelligence, Bone fracture, Emergency radiology, Musculoskeletal, Radiography

In Human brain mapping

Zhang Jie, Sun Zhe, Duan Feng, Shi Liang, Zhang Yu, Solé-Casals Jordi, Caiafa Cesar F

2022-Jul-01

cortical layers, diffusion magnetic resonance imaging, in vivo, laminar connections, noninvasive, working memory

In European radiology ; h5-index 62.0

OBJECTIVES : While chest radiograph (CXR) is the first-line imaging investigation in patients with respiratory symptoms, differentiating COVID-19 from other respiratory infections on CXR remains challenging. We developed and validated an AI system for COVID-19 detection on presenting CXR.

METHODS : A deep learning model (RadGenX), trained on 168,850 CXRs, was validated on a large international test set of presenting CXRs of symptomatic patients from 9 study sites (US, Italy, and Hong Kong SAR) and 2 public datasets from the US and Europe. Performance was measured by area under the receiver operator characteristic curve (AUC). Bootstrapped simulations were performed to assess performance across a range of potential COVID-19 disease prevalence values (3.33 to 33.3%). Comparison against international radiologists was performed on an independent test set of 852 cases.

RESULTS : RadGenX achieved an AUC of 0.89 on 4-fold cross-validation and an AUC of 0.79 (95%CI 0.78-0.80) on an independent test cohort of 5,894 patients. Delong's test showed statistical differences in model performance across patients from different regions (p < 0.01), disease severity (p < 0.001), gender (p < 0.001), and age (p = 0.03). Prevalence simulations showed the negative predictive value increases from 86.1% at 33.3% prevalence, to greater than 98.5% at any prevalence below 4.5%. Compared with radiologists, McNemar's test showed the model has higher sensitivity (p < 0.001) but lower specificity (p < 0.001).

CONCLUSION : An AI model that predicts COVID-19 infection on CXR in symptomatic patients was validated on a large international cohort providing valuable context on testing and performance expectations for AI systems that perform COVID-19 prediction on CXR.

KEY POINTS : • An AI model developed using CXRs to detect COVID-19 was validated in a large multi-center cohort of 5,894 patients from 9 prospectively recruited sites and 2 public datasets. • Differences in AI model performance were seen across region, disease severity, gender, and age. • Prevalence simulations on the international test set demonstrate the model's NPV is greater than 98.5% at any prevalence below 4.5%.

Kuo Michael D, Chiu Keith W H, Wang David S, Larici Anna Rita, Poplavskiy Dmytro, Valentini Adele, Napoli Alessandro, Borghesi Andrea, Ligabue Guido, Fang Xin Hao B, Wong Hing Ki C, Zhang Sailong, Hunter John R, Mousa Abeer, Infante Amato, Elia Lorenzo, Golemi Salvatore, Yu Leung Ho P, Hui Christopher K M, Erickson Bradley J

2022-Jul-02

Artificial intelligence, COVID-19, Public health, Radiology, Thoracic

In Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research

Padula William V, Kreif Noemi, Vanness David J, Adamson Blythe, Rueda Juan-David, Felizzi Federico, Jonsson Pall, IJzerman Maarten J, Butte Atul, Crown William

2022-Jul

artificial intelligence, machine learning

In Taiwanese journal of obstetrics & gynecology

OBJECTIVE : To report three families with chromosome 15q11q13 duplications.

CASE REPORT : We report the prenatal diagnosis and genetic counseling of three 15q11q13 duplications.

CONCLUSION : Chromosomal microdeletions and microduplications are difficult to be detected by conventional cytogenetics. With molecular genetic techniques including array-based methods, the number of reported cases has rapidly increased. An integration of prenatal ultrasound, NIPT, karyotype analysis, CMA and genetic counseling is helpful for the prenatal diagnosis of chromosomal microdeletions/microduplications.

Song Jieping, Liu Xu, Zhang Chengcheng, Xu Fei, Wang Bo

2022-Jul

Chromosomal microarray analysis (CMA), Chromosomal microdeletions/microduplications, Chromosome karyotype, Noninvasive prenatal testing (NIPT), Prenatal diagnosis

In Journal of ethnopharmacology ; h5-index 59.0

ETHNOPHARMACOLOGICAL RELEVANCE : Pneumonia is common and frequently-occurred disease caused by pathogens which predisposes to lung parenchymal inflammation leading pulmonary dysfunction. To prevent and alleviate the symptoms of pneumonia, Qinggan Yin formula (QGY) was composed based on clinical experience and four classical traditional Chinese medicine prescriptions which frequently applied to treat infectious diseases.

AIM OF THE STUDY : Traditional Chinese medicine is a complex mixture and it is difficult to distinguish the effective component molecules. The aim of this study is to identify the compounds of QGY with anti-inflammatory effects and investigate the molecular mechanism.

MATERIALS AND METHODS : The high-resolution mass spectrometry and molecular networking were performed for comprehensive chemical profiling of QGY. Network pharmacology was used to generate "herbal-target-pathway" network for target predictions. The anti-inflammation effects of QGY were evaluated in mice model of lipopolysaccharide (LPS) induced acute inflammation. Tail transected zebrafish was also employed to validate macrophage migration reversed effect of QGY. Based on the molecular enrichment analysis, the active substances of QGY with anti-inflammatory effects were further identified in cellular model of macrophage activation. The mechanisms of active substances were investigated by testing their effects on the expression of correlated proteins by Western blot.

RESULTS : In total, 71 compounds are identified as major substances of QGY. According to the results of network pharmacology, QGY shows moderate anti-inflammatory effects and inhibit pulmonary injury. MAPK signaling pathway was predicted as the most related pathway regulated by QGY. Moreover, QGY significantly inhibit LPS-induced pulmonary inflammation in mice, and reversed macrophage migration toward the injury site in zebrafish. We also validate that some major compounds in QGY significantly attenuated the release of IL-1β, IL-6 and TNF-α in LPS-stimulated macrophage. Those active substances including acacetin and arctiin can inhibit the phosphorylation of ERK/JNK and down-regulated the protein expression of BCL-2.

CONCLUSION : Collectively, QGY possessed pronounced anti-inflammation effects. The integration of network pharmacology and experimental results indicated arctiin, iridin, acacetin, liquiritin, and arctigenin are major active substances of QGY with anti-inflammatory effects. The underlying mechanism of QGY involves MAPK signaling pathway and oxidative stress pathway.

Jin Zehua, Sheng Hongda, Wang Shufang, Wang Yi, Cheng Yiyu

2022-Jun-29

Active compounds screening, Inflammation, MAPK signaling Pathway, Mass spectrometry molecular networking, Network pharmacology, Qinggan Yin formula

In Annals of epidemiology ; h5-index 39.0

OBJECTIVE : Children may be exposed to numerous in-home environmental exposures (IHEE) that trigger asthma exacerbations. Spatially linking social and environmental exposures to electronic health records (EHR) can aid exposure assessment, epidemiology, and clinical treatment, but EHR data on exposures are missing for many children with asthma. To address the issue, we predicted presence of indoor asthma trigger allergens, and estimated effects of their key geospatial predictors.

STUDY DESIGN AND SETTING : Our study samples were comprised of children with asthma who provided self-reported IHEE data in EHR at a safety-net hospital in New England during 2004-2015. We used an ensemble machine learning algorithm and 86 multilevel features (e.g., individual, housing, neighborhood) to predict presence of cockroaches, rodents (mice or rats), mold, and bedroom carpeting/rugs in homes. We reduced dimensionality via elastic net regression and estimated effects by the G-computation causal inference method.

RESULTS : Our models reasonably predicted presence of cockroaches (Area under receiver operating curves [AUC]=0.65), rodents (AUC=0.64), and bedroom carpeting/rugs (AUC=0.64), but not mold (AUC=0.54). In models adjusted for confounders, higher average household sizes in census tracts were associated with more reports of pests (cockroaches and rodents). Tax-exempt parcels were associated with more reports of cockroaches in homes. Living in a White-segregated neighborhood was linked with lower reported rodent presence, and mixed residential/commercial housing and newer buildings were associated with more reports of bedroom carpeting/rugs in bedrooms.

CONCLUSION : We innovatively applied a machine learning and causal inference mixture methodology to detail IHEE among children with asthma using EHR and geospatial data, which could have wide applicability and utility.

Bozigar Matthew, Connolly Catherine L, Legler Aaron, Adams William G, Milando Chad W, Reynolds David B, Carnes Fei, Jimenez Raquel B, Peer Komal, Vermeer Kimberly, Levy Jonathan I, Fabian M Patricia

2022-Jun-29

Exposure assessment, asthma triggers, electronic health records, housing, neighborhoods

In Journal of theoretical biology

Chen Fang, Wu Te, Wang Long

2022-Jun-29

Direct reciprocity, Evolutionary game, Repeated multiplayer games, Zero-determinant strategies

In Free radical biology & medicine

Huang Fangfang, Zhang Suzhou, Li Xiaoling, Huang Yuge, He Shasha, Luo Lianxiang

2022-Jun-29

Ferroptosis, Machine learning, STAT3, Salmonella typhimurium, Ulcerative colitis

In Journal of hepatology ; h5-index 119.0

BACKGROUND AND AIMS : Liver fibrosis is a key prognostic determinant for clinical outcomes in non-alcoholic steatohepatitis (NASH). Current scoring systems have limitations, especially in assessing fibrosis regression. Second harmonic generation/two-photon excitation fluorescence (SHG/TPEF) microscopy with artificial intelligence (AI) analyses provides standardized evaluation of NASH features, especially liver fibrosis and collagen fiber quantitation on a continuous scale. This approach was applied to gain in-depth understanding of fibrosis dynamics after treatment with tropifexor (TXR), a non-bile acid farnesoid X receptor (FXR) agonist in patients participating in FLIGHT-FXR study (NCT02855164).

METHOD : Unstained sections from 198 liver biopsies (paired: baseline and end-of-treatment) from 99 patients with NASH (fibrosis stage F2 or F3) who received placebo (n=34), TXR 140 μg (n=37), or TXR 200 μg (n=28) for 48 weeks were examined. Liver fibrosis (qFibrosis ®), hepatic fat (qSteatosis®), and ballooned hepatocytes (qBallooning®) were quantitated using SHG/TPEF microscopy. Changes in septa morphology, collagen fiber parameters, and zonal distribution within liver lobules were also quantitatively assessed.

RESULTS : Digital analyses revealed treatment-associated reduction of overall liver fibrosis (qFibrosis®), unlike conventional microscopy, as well as marked regression in perisinusoidal fibrosis in patients who had either F2 or F3 fibrosis at baseline. Concomitant zonal quantitation of fibrosis and steatosis revealed that patients with greater qSteatosis reduction also have greatest reduction in perisinusoidal fibrosis. Regressive changes in septa morphology and reduction in septa parameters were observed almost exclusively in F3 patients, who were adjudged as 'unchanged' with conventional scoring.

CONCLUSION : Fibrosis regression following hepatic fat reduction occurs initially in the perisinusoidal regions, around areas of steatosis reduction. Digital pathology provides new insights in treatment-induced fibrosis regression in NASH, which are not captured by current staging systems.

LAY SUMMARY : The degree of liver fibrosis in non-alcoholic steatohepatitis (NASH) is the principal feature that predicts clinical outcomes. Accurate assessment of liver fibrosis amount and architecture is fundamental for patients' enrolment in NASH clinical trials and determining treatment efficacy. Using digital microscopy with artificial intelligence analyses, the present study demonstrates that this novel approach has greater sensitivity and granularity in demonstrating treatment-induced reversal of fibrotic changes in the liver than current systems which use ordinal assessment of liver fibrosis in patients with NASH. Furthermore, additional details are obtained regarding the pathobiology of NASH disease and effects of therapy.

Naoumov Nikolai V, Brees Dominique, Loeffler Juergen, Chng Elaine, Ren Yayun, Lopez Patricia, Tai Dean, Lamle Sophie, Sanyal Arun J

2022-Jun-29

Digital Pathology with Artificial Intelligence, Farnesoid X Receptor Agonists and NASH Treatment, Fibrosis Regression, Non-alcoholic Steatohepatitis, Perisinusoidal Fibrosis, Second Harmonic Generation Microscopy

In Computers in biology and medicine

Liu Jia, Qi Jing, Chen Wei, Nian Yongjian

2022-Jun-15

Auxiliary learning, Deep learning, Feature fusion, Multi-task learning, Pneumonia

In Neural networks : the official journal of the International Neural Network Society

Tian Chunwei, Yuan Yixuan, Zhang Shichao, Lin Chia-Wen, Zuo Wangmeng, Zhang David

2022-Jun-11

CNN, Group convolution, Image super-resolution, Signal processing

In Neural networks : the official journal of the International Neural Network Society

Venugopal Rohit, Shafqat Noman, Venugopal Ishwar, Tillbury Benjamin Mark John, Stafford Harry Demetrios, Bourazeri Aikaterini

2022-Jun-25

AI, GAN, Machine learning, Privacy, Public health data

In Studies in health technology and informatics ; h5-index 23.0

Vagliano Iacopo, Byrne Salsas Carmen, Wünn Tina, Schut Martijn C

2022-Jun-29

Acute kidney injury, ICU, clinical prediction models, external validation, machine learning

In Acta crystallographica. Section D, Structural biology

Chojnowski Grzegorz

2022-Jul-01

checkMySequence, cryo-EM, model validation, register shifts, sequence assignment

In IEEE transactions on neural networks and learning systems

Eshkiki Hassan, Mora Benjamin, Xie Xianghua

2022-Jul-01

In IEEE transactions on neural networks and learning systems

Guastavino Sabrina, Piana Michele, Benvenuto Federico

2022-Jul-01

In PloS one ; h5-index 176.0

BACKGROUND : Globally, blood donation has been disturbed due to the pandemic. Consequently, the optimization of preoperative blood preparation should be a point of concern. Machine learning (ML) is one of the modern approaches that have been applied by physicians to help decision-making. The main objective of this study was to identify the cost differences of the ML-based strategy compared with other strategies in preoperative blood products preparation. A secondary objective was to compare the effectiveness indexes of blood products preparation among strategies.

METHODS : The study utilized a retrospective cohort design conducted on brain tumor patients who had undergone surgery between January 2014 and December 2021. Overall data were divided into two cohorts. The first cohort was used for the development and deployment of the ML-based web application, while validation, comparison of the effectiveness indexes, and economic evaluation were performed using the second cohort. Therefore, the effectiveness indexes of blood preparation and cost difference were compared among the ML-based strategy, clinical trial-based strategy, and routine-based strategy.

RESULTS : Over a 2-year period, the crossmatch to transfusion (C/T) ratio, transfusion probability (Tp), and transfusion index (Ti) of the ML-based strategy were 1.10, 57.0%, and 1.62, respectively, while the routine-based strategy had a C/T ratio of 4.67%, Tp of 27.9%%, and Ti of 0.79. The overall costs of blood products preparation among the ML-based strategy, clinical trial-based strategy, and routine-based strategy were 30, 061.56$, 57,313.92$, and 136,292.94$, respectively. From the cost difference between the ML-based strategy and routine-based strategy, we observed cost savings of 92,519.97$ (67.88%) for the 2-year period.

CONCLUSION : The ML-based strategy is one of the most effective strategies to balance the unnecessary workloads at blood banks and reduce the cost of unnecessary blood products preparation from low C/T ratio as well as high Tp and Ti. Further studies should be performed to confirm the generalizability and applicability of the ML-based strategy.

Tunthanathip Thara, Sae-Heng Sakchai, Oearsakul Thakul, Kaewborisutsakul Anukoon, Taweesomboonyat Chin

2022

In PloS one ; h5-index 176.0

Fu Dong, Su Chao, Wang Wenjun, Yuan Rongyao

2022

In PloS one ; h5-index 176.0

MOTIVATION : Single-cell Chromatin ImmunoPrecipitation DNA-Sequencing (scChIP-seq) analysis is challenging due to data sparsity. High degree of sparsity in biological high-throughput single-cell data is generally handled with imputation methods that complete the data, but specific methods for scChIP-seq are lacking. We present SIMPA, a scChIP-seq data imputation method leveraging predictive information within bulk data from the ENCODE project to impute missing protein-DNA interacting regions of target histone marks or transcription factors.

RESULTS : Imputations using machine learning models trained for each single cell, each ChIP protein target, and each genomic region accurately preserve cell type clustering and improve pathway-related gene identification on real human data. Results on bulk data simulating single cells show that the imputations are single-cell specific as the imputed profiles are closer to the simulated cell than to other cells related to the same ChIP protein target and the same cell type. Simulations also show that 100 input genomic regions are already enough to train single-cell specific models for the imputation of thousands of undetected regions. Furthermore, SIMPA enables the interpretation of machine learning models by revealing interaction sites of a given single cell that are most important for the imputation model trained for a specific genomic region. The corresponding feature importance values derived from promoter-interaction profiles of H3K4me3, an activating histone mark, highly correlate with co-expression of genes that are present within the cell-type specific pathways in 2 real human and mouse datasets. The SIMPA's interpretable imputation method allows users to gain a deep understanding of individual cells and, consequently, of sparse scChIP-seq datasets.

AVAILABILITY AND IMPLEMENTATION : Our interpretable imputation algorithm was implemented in Python and is available at https://github.com/salbrec/SIMPA.

Albrecht Steffen, Andreani Tommaso, Andrade-Navarro Miguel A, Fontaine Jean Fred

2022

In PloS one ; h5-index 176.0

INTRODUCTION : We aim to apply deep learning to achieve fully automated detection and classification of the Cervical Vertebrae Maturation (CVM) stages. We propose an innovative custom-designed deep Convolutional Neural Network (CNN) with a built-in set of novel directional filters that highlight the edges of the Cervical Vertebrae in X-ray images.

METHODS : A total of 1018 Cephalometric radiographs were labeled and classified according to the Cervical Vertebrae Maturation (CVM) stages. The images were cropped to extract the cervical vertebrae using an Aggregate Channel Features (ACF) object detector. The resulting images were used to train four different Deep Learning (DL) models: our proposed CNN, MobileNetV2, ResNet101, and Xception, together with a set of tunable directional edge enhancers. When using MobileNetV2, ResNet101 and Xception, data augmentation is adopted to allow adequate network complexity while avoiding overfitting. The performance of our CNN model was compared with that of MobileNetV2, ResNet101 and Xception with and without the use of directional filters. For validation and performance assessment, k-fold cross-validation, ROC curves, and p-values were used.

RESULTS : The proposed innovative model that uses a CNN preceded with a layer of tunable directional filters achieved a validation accuracy of 84.63%84.63% in CVM stage classification into five classes, exceeding the accuracy achieved with the other DL models investigated. MobileNetV2, ResNet101 and Xception used with directional filters attained accuracies of 78.54%, 74.10%, and 80.86%, respectively. The custom-designed CNN method also achieves 75.11% in six-class CVM stage classification. The effectiveness of the directional filters is reflected in the improved performance attained in the results. If the custom-designed CNN is used without the directional filters, the test accuracy decreases to 80.75%. In the Xception model without the directional filters, the testing accuracy drops slightly to 79.42% in the five-class CVM stage classification.

CONCLUSION : The proposed model of a custom-designed CNN together with the tunable Directional Filters (CNNDF) is observed to provide higher accuracy than the commonly used pre-trained network models that we investigated in the fully automated determination of the CVM stages.

Atici Salih Furkan, Ansari Rashid, Allareddy Veerasathpurush, Suhaym Omar, Cetin Ahmet Enis, Elnagar Mohammed H

2022

In Environmental health perspectives ; h5-index 89.0

BACKGROUND : Little research has examined associations between disaster-related home loss and multiple domains of health and well-being, with extended long-term follow-up and comprehensive adjustment for pre-disaster characteristics of survivors.

OBJECTIVES : We examined the longitudinal associations between disaster-induced home loss and 34 indicators of health and well-being, assessed ∼9y post-disaster.

METHODS : We used data from a preexisting cohort study of Japanese older adults in an area directly impacted by the 2011 Japan Earthquake (n=3,350 and n=2,028, depending on the outcomes). The study was initiated in 2010, and disaster-related home loss status was measured in 2013 retrospectively. The 34 outcomes were assessed in 2020 and covered dimensions of physical health, mental health, health behaviors/sleep, social well-being, cognitive social capital, subjective well-being, and prosocial/altruistic behaviors. We estimated the associations between disaster-related home loss and the outcomes, using targeted maximum likelihood estimation and SuperLearner. We adjusted for pre-disaster characteristics from the wave conducted 7 months before the disaster (i.e., 2010), including prior outcome values that were available.

RESULTS : After Bonferroni correction for multiple testing, we found that home loss (vs. no home loss) was associated with increased posttraumatic stress symptoms (standardized difference=0.50; 95% CI: 0.35, 0.65), increased daily sleepiness (0.38; 95% CI: 0.21, 0.54), lower trust in the community (-0.36; 95% CI: -0.53, -0.18), lower community attachment (-0.60; 95% CI: -0.75, -0.45), and lower prosociality (-0.39; 95% CI: -0.55, -0.24). We found modest evidence for the associations with increased depressive symptoms, increased hopelessness, more chronic conditions, higher body mass index, lower perceived mutual help in the community, and decreased happiness. There was little evidence for associations with the remaining 23 outcomes.

DISCUSSION : Home loss due to a disaster may have long-lasting adverse impacts on the cognitive social capital, mental health, and prosociality of older adult survivors. https://doi.org/10.1289/EHP10903.

Shiba Koichiro, Hikichi Hiroyuki, Okuzono Sakurako S, VanderWeele Tyler J, Arcaya Mariana, Daoud Adel, Cowden Richard G, Yazawa Aki, Zhu David T, Aida Jun, Kondo Katsunori, Kawachi Ichiro

2022-Jul

In STAR protocols

Chen Liuyin, Qi Haoyang, Lu Di, Zhai Jianxue, Cai Kaican, Wang Long, Liang Guoyuan, Zhang Zijun

2022-Jun-22

Bioinformatics, Biotechnology and bioengineering, Cancer, Computer sciences, Health Sciences, Systems biology

In Optics letters

Pan Tuqiang, Ye Jianwei, Zhang Zhanyuan, Xu Yi

2022-Jul-01

In Optics letters

Deng Wenqiang, Xu Zhengji, Wang Jinhao, Lv Jinwen

2022-Jul-01

In Studies in health technology and informatics ; h5-index 23.0

Ali Nashva, Abd-Alrazaq Alaa, Shah Zubair, Alajlani Mohannad, Alam Tanvir, Househ Mowafa

2022-Jun-29

Artificial Intelligence, Children, Emotion Sensing, Mobile Application

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVE : Understanding public discourse on emergency use of unproven therapeutics is essential to monitor safe use and combat misinformation. We developed a natural language processing (NLP)-based pipeline to understand public perceptions of and stances on COVID-19-related drugs on Twitter across time.

METHODS : This retrospective study included 609,189 US-based tweets between January 29th, 2020 and November 30th, 2021 on four drugs that gained wide public attention during the COVID-19 pandemic: 1) Hydroxychloroquine and Ivermectin, drug therapies with anecdotal evidence; and 2) Molnupiravir and Remdesivir, FDA-approved treatment options for eligible patients. Time-trend analysis was used to understand the popularity and related events. Content and demographic analyses were conducted to explore potential rationales of people's stances on each drug.

RESULTS : Time-trend analysis revealed that Hydroxychloroquine and Ivermectin received much more discussion than Molnupiravir and Remdesivir, particularly during COVID-19 surges. Hydroxychloroquine and Ivermectin were highly politicized, related to conspiracy theories, hearsay, celebrity effects, etc. The distribution of stance between the two major US political parties was significantly different (p < 0.001); Republicans were much more likely to support Hydroxychloroquine (+55%) and Ivermectin (+30%) than Democrats. People with healthcare backgrounds tended to oppose Hydroxychloroquine (+7%) more than the general population; in contrast, the general population was more likely to support Ivermectin (+14%).

CONCLUSION : Our study found that social media users with have different perceptions and stances on off-label versus FDA-authorized drug use across different stages of COVID-19, indicating that health systems, regulatory agencies, and policymakers should design "targeted" strategies to monitor and reduce misinformation for promoting safe drug use. Our analysis pipeline and stance detection models are made public at https://github.com/ningkko/COVID-drug.

Hua Yining, Jiang Hang, Lin Shixu, Yang Jie, Plasek Joseph M, Bates David W, Zhou Li

2022-Jul-01

COVID-19, Deep Learning, Drug Safety, Natural Language Processing, Public Health, Social Media

In ACS applied materials & interfaces ; h5-index 147.0

Qiu Wenying, Li Zhaoyang, Wang Guocheng, Peng Yande, Zhang Min, Wang Xiaohao, Zhong Junwen, Lin Liwei

2022-Jul-01

haptic feedback, low voltage, moisture resistance, soft actuator, wearable electronics

In Database : the journal of biological databases and curation

Le Tuan-Dung, Nguyen Phuong D, Korkin Dmitry, Thieu Thanh

2022-Jun-30

In Database : the journal of biological databases and curation

Almeida Tiago, Antunes Rui, F Silva João, Almeida João R, Matos Sérgio

2022-Jul-01

In Investigative radiology ; h5-index 46.0

OBJECTIVES : This study aimed to examine various combinations of parallel imaging (PI) and simultaneous multislice (SMS) acceleration imaging using deep learning (DL)-enhanced and conventional reconstruction. The study also aimed at comparing the diagnostic performance of the various combinations in internal knee derangement and provided a quantitative evaluation of image noise and sharpness using edge rise distance (ERD) and noise power (NP), respectively.

MATERIALS AND METHODS : The data from adult patients who underwent knee magnetic resonance imaging using various DL-enhanced acquisitions between June 2021 and January 2022 were retrospectively analyzed. The participants underwent conventional 2-fold PI and DL protocols with 4- to 8-fold acceleration imaging (P2S2 [2-fold PI with 2-fold SMS], P3S2, and P4S2). Three readers evaluated the internal knee derangement and the overall image quality. The diagnostic performance was calculated using consensus reading as a standard reference, and we conducted comparative evaluations. We calculated the ERD and NP for quantitative evaluations of image sharpness and noise, respectively. Interreader and intermethod agreements were calculated using Fleiss κ.

RESULTS : A total of 33 patients (mean age, 49 ± 19 years; 20 women) were included in this study. The diagnostic performance for internal knee derangement and the overall image quality were similar among the evaluated protocols. The NP values were significantly lower using the DL protocols than with conventional imaging (P < 0.001), whereas the ERD values were similar among these methods (P > 0.12). Interreader and intermethod agreements were moderate-to-excellent (κ = 0.574-0.838) and good-to-excellent (κ = 0.755-1.000), respectively. In addition, the mean acquisition time was reduced by 47% when using DL with P2S2, by 62% with P3S2, and by 71% with P4S2, compared with conventional P2 imaging (2 minutes and 55 seconds).

CONCLUSIONS : The combined use of DL-enhanced 8-fold acceleration imaging (4-fold PI with 2-fold SMS) showed comparable performance with conventional 2-fold PI for the evaluation of internal knee derangement, with a 71% reduction in acquisition time.

Kim MinWoo, Lee Sang-Min, Park Chankue, Lee Dongeon, Kim Kang Soo, Jeong Hee Seok, Kim Shinyoung, Choi Min-Hyeok, Nickel Dominik

2022-Jul-01

In Journal of gastrointestinal surgery : official journal of the Society for Surgery of the Alimentary Tract

BACKGROUND : Anti-reflux mucosectomy (ARMS) is a choice for proton pump inhibitor (PPI)-dependent patients with gastroesophageal reflux disease (GERD). We present an extended anti-reflux mucosectomy, named ligation-assisted anti-reflux mucosectomy (L-ARMS). The aim of this study was to assess the feasibility of the procedure and short-term outcomes on PPI use and symptom resolution.

METHODS : Institutional review board approval was obtained for retrospective review of a prospectively collected database including patients who underwent L-ARMS. L-ARMS includes mucosa ligation and endoscopic mucosectomy without submucosal injection around the squamocolumnar junction. The GERD symptoms, endoscopy, 24-h pH monitoring results, and manometry were collected by chart review. Voluntary validated surveys assessed symptomatic improvement over time.

RESULTS : There were 69 patients available for review. The procedure was technically completed in all cases with no severe complications, and the average operation time was 33 min. At 6 months after L-ARMS, treatment with PPIs had been halted in 55.1% of the patients, 30.4% of the enrolled patients used PPIs occasionally, and the lower esophageal sphincter (LES) pressure, DeMeester scores, and GERD-health-related quality of life questionnaire (GERD-HRQL) scores showed a significant improvement compared with the baseline measurements (P < 0.001). Forty-five patients complained of mild dysphagia and were relieved in 4 weeks with no specific treatment. Compared to patients without dysphagia, patients complained of dysphagia after surgery had better clinical benefits indicated by GERD-HRQL and DeMeester score.

CONCLUSIONS : As a modified ARMS, L-ARMS is an effective procedure for controlling GERD symptoms, esophageal acid exposure, and LES pressure, which can be safely performed endoscopically in a time-saving and simple manner.

He Jian, Yin Yani, Tang Wen, Jiang Jiahui, Gu Lei, Yi Jun, Yan Lu, Chen Shuijiao, Wu Yu, Liu Xiaowei

2022-Jul-01

Anti-reflux mucosectomy, Endoscopy, Gastroesophageal reflux disease, Mucosa ligation, Short-term outcomes

In Nano-micro letters

Wu Ronghui, Seo Sangjin, Ma Liyun, Bae Juyeol, Kim Taesung

2022-Jul-01

Deep learning, Interlaced yarn sensors, Negative Poisson’s ratio yarns, Sign-language translation, Smart glove

In Journal of experimental botany

Guo Ziyue, Yang Chenghai, Yang Wangnen, Chen Guoxing, Jiang Zhao, Wang Botao, Zhang Jian

2022-Jul-01

deep convolutional neural network, effective tiller percentage, heading date, rice panicle ratio network, ultra-high-definition image, unmanned aerial vehicle

In Acta crystallographica. Section D, Structural biology

Chojnowski Grzegorz

2022-Jul-01

checkMySequence, cryo-EM, model validation, register shifts, sequence assignment

In Journal of magnetic resonance imaging : JMRI

BACKGROUND : Accurate and rapid measurement of the MRI volume of meningiomas is essential in clinical practice to determine the growth rate of the tumor. Imperfect automation and disappointing performance for small meningiomas of previous automated volumetric tools limit their use in routine clinical practice.

PURPOSE : To develop and validate a computational model for fully automated meningioma segmentation and volume measurement on contrast-enhanced MRI scans using deep learning.

STUDY TYPE : Retrospective.

POPULATION : A total of 659 intracranial meningioma patients (median age, 59.0 years; interquartile range: 53.0-66.0 years) including 554 women and 105 men.

FIELD STRENGTH/SEQUENCE : The 1.0 T, 1.5 T, and 3.0 T; three-dimensional, T₁ -weighted gradient-echo imaging with contrast enhancement.

ASSESSMENT : The tumors were manually segmented by two neurosurgeons, H.K. and C.-K.P., with 10 and 26 years of clinical experience, respectively, for use as the ground truth. Deep learning models based on U-Net and nnU-Net were trained using 459 subjects and tested for 100 patients from a single institution (internal validation set [IVS]) and 100 patients from other 24 institutions (external validation set [EVS]), respectively. The performance of each model was evaluated with the Sørensen-Dice similarity coefficient (DSC) compared with the ground truth.

STATISTICAL TESTS : According to the normality of the data distribution verified by the Shapiro-Wilk test, variables with three or more categories were compared by the Kruskal-Wallis test with Dunn's post hoc analysis.

RESULTS : A two-dimensional (2D) nnU-Net showed the highest median DSCs of 0.922 and 0.893 for the IVS and EVS, respectively. The nnU-Nets achieved superior performance in meningioma segmentation than the U-Nets. The DSCs of the 2D nnU-Net for small meningiomas less than 1 cm³ were 0.769 and 0.780 with the IVS and EVS, respectively.

DATA CONCLUSION : A fully automated and accurate volumetric measurement tool for meningioma with clinically applicable performance for small meningioma using nnU-Net was developed.

EVIDENCE LEVEL : 3 TECHNICAL EFFICACY: Stage 2.

Kang Ho, Witanto Joseph Nathanael, Pratama Kevin, Lee Doohee, Choi Kyu Sung, Choi Seung Hong, Kim Kyung-Min, Kim Min-Sung, Kim Jin Wook, Kim Yong Hwy, Park Sang Joon, Park Chul-Kee

2022-Jul-01

artificial intelligence, convolutional neural network, meningioma, nnU-Net, segmentation, volumetry

In Journal of the American Medical Informatics Association : JAMIA

OBJECTIVE : Understanding public discourse on emergency use of unproven therapeutics is essential to monitor safe use and combat misinformation. We developed a natural language processing (NLP)-based pipeline to understand public perceptions of and stances on COVID-19-related drugs on Twitter across time.

METHODS : This retrospective study included 609,189 US-based tweets between January 29th, 2020 and November 30th, 2021 on four drugs that gained wide public attention during the COVID-19 pandemic: 1) Hydroxychloroquine and Ivermectin, drug therapies with anecdotal evidence; and 2) Molnupiravir and Remdesivir, FDA-approved treatment options for eligible patients. Time-trend analysis was used to understand the popularity and related events. Content and demographic analyses were conducted to explore potential rationales of people's stances on each drug.

RESULTS : Time-trend analysis revealed that Hydroxychloroquine and Ivermectin received much more discussion than Molnupiravir and Remdesivir, particularly during COVID-19 surges. Hydroxychloroquine and Ivermectin were highly politicized, related to conspiracy theories, hearsay, celebrity effects, etc. The distribution of stance between the two major US political parties was significantly different (p < 0.001); Republicans were much more likely to support Hydroxychloroquine (+55%) and Ivermectin (+30%) than Democrats. People with healthcare backgrounds tended to oppose Hydroxychloroquine (+7%) more than the general population; in contrast, the general population was more likely to support Ivermectin (+14%).

CONCLUSION : Our study found that social media users with have different perceptions and stances on off-label versus FDA-authorized drug use across different stages of COVID-19, indicating that health systems, regulatory agencies, and policymakers should design "targeted" strategies to monitor and reduce misinformation for promoting safe drug use. Our analysis pipeline and stance detection models are made public at https://github.com/ningkko/COVID-drug.

Hua Yining, Jiang Hang, Lin Shixu, Yang Jie, Plasek Joseph M, Bates David W, Zhou Li

2022-Jul-01

COVID-19, Deep Learning, Drug Safety, Natural Language Processing, Public Health, Social Media

In Studies in health technology and informatics ; h5-index 23.0

Saborit-Torres Jose Manuel, Nadal-Almela Silvia, Montell-Serrano Joaquim Angel, Oliver-Garcia Elena, Carceller Hector, Gómez-Ádrian Jon Ander, Caparrós-Redondo Marisa, García-García Francisco, Domenech-Fernández Julio, De La Iglesia-Vayá Maria

2022-Jun-29

BIDS, Database, OMOP, Standardization

In Medical decision making : an international journal of the Society for Medical Decision Making

BACKGROUND : Policy makers are facing more complicated challenges to balance saving lives and economic development in the post-vaccination era during a pandemic. Epidemic simulation models and pandemic control methods are designed to tackle this problem. However, most of the existing approaches cannot be applied to real-world cases due to the lack of adaptability to new scenarios and micro representational ability (especially for system dynamics models), the huge computation demand, and the inefficient use of historical information.

METHODS : We propose a novel Pandemic Control decision making framework via large-scale Agent-based modeling and deep Reinforcement learning (PaCAR) to search optimal control policies that can simultaneously minimize the spread of infection and the government restrictions. In the framework, we develop a new large-scale agent-based simulator with vaccine settings implemented to be calibrated and serve as a realistic environment for a city or a state. We also design a novel reinforcement learning architecture applicable to the pandemic control problem, with a reward carefully designed by the net monetary benefit framework and a sequence learning network to extract information from the sequential epidemiological observations, such as number of cases, vaccination, and so forth.

RESULTS : Our approach outperforms the baselines designed by experts or adopted by real-world governments and is flexible in dealing with different variants, such as Alpha and Delta in COVID-19. PaCAR succeeds in controlling the pandemic with the lowest economic costs and relatively short epidemic duration and few cases. We further conduct extensive experiments to analyze the reasoning behind the resulting policy sequence and try to conclude this as an informative reference for policy makers in the post-vaccination era of COVID-19 and beyond.

LIMITATIONS : The modeling of economic costs, which are directly estimated by the level of government restrictions, is rather simple. This article mainly focuses on several specific control methods and single-wave pandemic control.

CONCLUSIONS : The proposed framework PaCAR can offer adaptive pandemic control recommendations on different variants and population sizes. Intelligent pandemic control empowered by artificial intelligence may help us make it through the current COVID-19 and other possible pandemics in the future with less cost both of lives and economy.

HIGHLIGHTS : We introduce a new efficient, large-scale agent-based epidemic simulator in our framework PaCAR, which can be applied to train reinforcement learning networks in a real-world scenario with a population of more than 10,000,000.We develop a novel learning mechanism in PaCAR, which augments reinforcement learning with sequence learning, to learn the tradeoff policy decision of saving lives and economic development in the post-vaccination era.We demonstrate that the policy learned by PaCAR outperforms different benchmark policies under various reality conditions during COVID-19.We analyze the resulting policy given by PaCAR, and the lessons may shed light on better pandemic preparedness plans in the future.

Guo Xudong, Chen Peiyu, Liang Shihao, Jiao Zengtao, Li Linfeng, Yan Jun, Huang Yadong, Liu Yi, Fan Wenhui

2022-Jul-01

COVID-19, SARS-CoV-2, agent-based modeling, artificial intelligence, epidemic simulation, health policy, infectious disease, nonpharmaceutical interventions, pandemic control, reinforcement learning

In NMR in biomedicine ; h5-index 41.0

Tessema Abel Worku, Lee Hansol, Gong Yelim, Cho Hwapyeong, Adem Hamdia Murad, Lyu Ilwoo, Lee Jae-Hyeok, Cho Hyung Joon

2022-Jul-01

Convolutional neural network, Progressive supranuclear palsy, Quantitative analysis, Segmentation, Substantia nigra

In Journal of periodontal & implant science

PURPOSE : The aim of this study was to evaluate and compare the accuracy performance of dental professionals in the classification of different types of dental implant systems (DISs) using panoramic radiographic images with and without the assistance of a deep learning (DL) algorithm.

METHODS : Using a self-reported questionnaire, the classification accuracy of dental professionals (including 5 board-certified periodontists, 8 periodontology residents, and 31 dentists not specialized in implantology working at 3 dental hospitals) with and without the assistance of an automated DL algorithm were determined and compared. The accuracy, sensitivity, specificity, confusion matrix, receiver operating characteristic (ROC) curves, and area under the ROC curves were calculated to evaluate the classification performance of the DL algorithm and dental professionals.

RESULTS : Using the DL algorithm led to a statistically significant improvement in the average classification accuracy of DISs (mean accuracy: 78.88%) compared to that without the assistance of the DL algorithm (mean accuracy: 63.13%, P<0.05). In particular, when assisted by the DL algorithm, board-certified periodontists (mean accuracy: 88.56%) showed higher average accuracy than did the DL algorithm, and dentists not specialized in implantology (mean accuracy: 77.83%) showed the largest improvement, reaching an average accuracy similar to that of the algorithm (mean accuracy: 80.56%).

CONCLUSIONS : The automated DL algorithm classified DISs with accuracy and performance comparable to those of board-certified periodontists, and it may be useful for dental professionals for the classification of various types of DISs encountered in clinical practice.

Lee Jae-Hong, Kim Young-Taek, Lee Jong-Bin, Jeong Seong-Nyum

2022-Jun

Artificial intelligence, Deep learning, Dental implants, Dentist

In Medical decision making : an international journal of the Society for Medical Decision Making

BACKGROUND : Policy makers are facing more complicated challenges to balance saving lives and economic development in the post-vaccination era during a pandemic. Epidemic simulation models and pandemic control methods are designed to tackle this problem. However, most of the existing approaches cannot be applied to real-world cases due to the lack of adaptability to new scenarios and micro representational ability (especially for system dynamics models), the huge computation demand, and the inefficient use of historical information.

METHODS : We propose a novel Pandemic Control decision making framework via large-scale Agent-based modeling and deep Reinforcement learning (PaCAR) to search optimal control policies that can simultaneously minimize the spread of infection and the government restrictions. In the framework, we develop a new large-scale agent-based simulator with vaccine settings implemented to be calibrated and serve as a realistic environment for a city or a state. We also design a novel reinforcement learning architecture applicable to the pandemic control problem, with a reward carefully designed by the net monetary benefit framework and a sequence learning network to extract information from the sequential epidemiological observations, such as number of cases, vaccination, and so forth.

RESULTS : Our approach outperforms the baselines designed by experts or adopted by real-world governments and is flexible in dealing with different variants, such as Alpha and Delta in COVID-19. PaCAR succeeds in controlling the pandemic with the lowest economic costs and relatively short epidemic duration and few cases. We further conduct extensive experiments to analyze the reasoning behind the resulting policy sequence and try to conclude this as an informative reference for policy makers in the post-vaccination era of COVID-19 and beyond.

LIMITATIONS : The modeling of economic costs, which are directly estimated by the level of government restrictions, is rather simple. This article mainly focuses on several specific control methods and single-wave pandemic control.

CONCLUSIONS : The proposed framework PaCAR can offer adaptive pandemic control recommendations on different variants and population sizes. Intelligent pandemic control empowered by artificial intelligence may help us make it through the current COVID-19 and other possible pandemics in the future with less cost both of lives and economy.

HIGHLIGHTS : We introduce a new efficient, large-scale agent-based epidemic simulator in our framework PaCAR, which can be applied to train reinforcement learning networks in a real-world scenario with a population of more than 10,000,000.We develop a novel learning mechanism in PaCAR, which augments reinforcement learning with sequence learning, to learn the tradeoff policy decision of saving lives and economic development in the post-vaccination era.We demonstrate that the policy learned by PaCAR outperforms different benchmark policies under various reality conditions during COVID-19.We analyze the resulting policy given by PaCAR, and the lessons may shed light on better pandemic preparedness plans in the future.

Guo Xudong, Chen Peiyu, Liang Shihao, Jiao Zengtao, Li Linfeng, Yan Jun, Huang Yadong, Liu Yi, Fan Wenhui

2022-Jul-01

COVID-19, SARS-CoV-2, agent-based modeling, artificial intelligence, epidemic simulation, health policy, infectious disease, nonpharmaceutical interventions, pandemic control, reinforcement learning

In Psychological medicine ; h5-index 82.0

BACKGROUND : Posttraumatic stress symptoms (PTSS) are common following traumatic stress exposure (TSE). Identification of individuals with PTSS risk in the early aftermath of TSE is important to enable targeted administration of preventive interventions. In this study, we used baseline survey data from two prospective cohort studies to identify the most influential predictors of substantial PTSS.

METHODS : Self-identifying black and white American women and men (n = 1546) presenting to one of 16 emergency departments (EDs) within 24 h of motor vehicle collision (MVC) TSE were enrolled. Individuals with substantial PTSS (⩾33, Impact of Events Scale - Revised) 6 months after MVC were identified via follow-up questionnaire. Sociodemographic, pain, general health, event, and psychological/cognitive characteristics were collected in the ED and used in prediction modeling. Ensemble learning methods and Monte Carlo cross-validation were used for feature selection and to determine prediction accuracy. External validation was performed on a hold-out sample (30% of total sample).

RESULTS : Twenty-five percent (n = 394) of individuals reported PTSS 6 months following MVC. Regularized linear regression was the top performing learning method. The top 30 factors together showed good reliability in predicting PTSS in the external sample (Area under the curve = 0.79 ± 0.002). Top predictors included acute pain severity, recovery expectations, socioeconomic status, self-reported race, and psychological symptoms.

CONCLUSIONS : These analyses add to a growing literature indicating that influential predictors of PTSS can be identified and risk for future PTSS estimated from characteristics easily available/assessable at the time of ED presentation following TSE.

Kim Raphael, Lin Tina, Pang Gehao, Liu Yufeng, Tungate Andrew S, Hendry Phyllis L, Kurz Michael C, Peak David A, Jones Jeffrey, Rathlev Niels K, Swor Robert A, Domeier Robert, Velilla Marc-Anthony, Lewandowski Christopher, Datner Elizabeth, Pearson Claire, Lee David, Mitchell Patricia M, McLean Samuel A, Linnstaedt Sarah D

2022-Jul-01

Machine learning, PTSD, prediction, risk factors, trauma

In Journal of child psychology and psychiatry, and allied disciplines

BACKGROUND : Diagnostic assessment of ASD requires substantial clinical experience and is particularly difficult in the context of other disorders with behavioral symptoms in the domain of social interaction and communication. Observation measures such as the Autism Diagnostic Observation Schedule (ADOS) do not take into account such co-occurring disorders.

METHOD : We used a well-characterized clinical sample of individuals (n = 1,251) that had received detailed outpatient evaluation for the presence of an ASD diagnosis (n = 481) and covered a range of additional overlapping diagnoses, including anxiety-related disorders (ANX, n = 122), ADHD (n = 439), and conduct disorder (CD, n = 194). We focused on ADOS module 3, covering the age range with particular high prevalence of such differential diagnoses. We used machine learning (ML) and trained random forest models on ADOS single item scores to predict a clinical best-estimate diagnosis of ASD in the context of these differential diagnoses (ASD vs. ANX, ASD vs. ADHD, ASD vs. CD), in the context of co-occurring ADHD, and an unspecific model using all available data. We employed nested cross-validation for an unbiased estimate of classification performance and made available a Webapp to showcase the results and feasibility for translation into clinical practice.

RESULTS : We obtained very good overall sensitivity (0.89-0.94) and specificity (0.87-0.89). In particular for individuals with less severe symptoms, our models showed increases of up to 35% in sensitivity or specificity. Furthermore, we analyzed item importance profiles of the ANX, ADHD, and CD models in comparison with the unspecific model revealing distinct patterns of importance for specific ADOS items with respect to differential diagnoses.

CONCLUSIONS : ML-based diagnostic classification may improve clinical decisions by utilizing the full range of information from detailed diagnostic observation instruments such as the ADOS. Importantly, this strategy might be of particular relevance for older children with less severe symptoms for whom the diagnostic decision is often particularly difficult.

Schulte-Rüther Martin, Kulvicius Tomas, Stroth Sanna, Wolff Nicole, Roessner Veit, Marschik Peter B, Kamp-Becker Inge, Poustka Luise

2022-Jul-01

Autism spectrum disorders, Machine learning, diagnosis

In JMIR research protocols ; h5-index 26.0

BACKGROUND : Prescription of psychostimulants has significantly increased in most countries worldwide for both pre-school and school-aged children. Understanding the trends of chronic medication use among children in different age groups and socio-demographic backgrounds is essential. This must be processed by distinguishing selected therapy areas is essential to help decision-makers evaluate not only the relevant expected medication costs but also the specific services related to these areas.

OBJECTIVE : This study will analyze differences in trends regarding medications considered psycho-behavioral treatments and medications considered non-psycho-behavioral treatments and will identify risk factors and predictors for chronic medication use among children.

METHODS : This is a retrospective study. Data will be extracted from the Clalit Health Services data warehouse. For each year between 2010 and 2019, there are approximately 1,500,000 children aged 0-18 years. All Medication classes will be identified using the Anatomical Therapeutic Chemical code. A time-trend analysis will be performed to investigate if there is a significant difference between the trends of children's psycho-behavioral and non-psycho-behavioral medication prescriptions. A logistic regression combined with machine learning models will be developed to identify variables that may increase the risk for specific chronic medication types and identify children likely to get such treatment.

RESULTS : The project was funded in 2019. Data analysis is currently underway, and the results are expected to be submitted for publication in 2022. Understanding trends regarding medications considered psycho-behavioral treatments and medications considered non-psycho-behavioral treatments will support the identification of risk factors and predictors for chronic medication use among children.

CONCLUSIONS : Analyzing the response of the patient (their parents or caregivers) population over time will hopefully help improve the policies for the prescriptions and the follow-up of chronic treatments in children.

Sadaka Yair, Horwitz Dana, Wolff Leor, Meyerovitch Joseph, Peleg Assaf, Bachmat Eitan, Benis Arriel

2022-Jun-30

In Pest management science

BACKGROUND : Climate warming presents physiological challenges to insects, manifesting as loss of key life-history fitness traits and survival. For interacting host-parasitoid species, physiological responses to heat stress may vary thereby potentially uncoupling trophic ecological relationships. Here, we assessed heat tolerance traits and sensitivity to prevailing and future maximum temperatures for cereal stemborer pests, Chilo partellus, Busseola fusca and Sesamia calamistis and their endo-parasitoids, Cotesia sesamiae and Cotesia flavipes. We further used the machine learning algorithm, Maximum Entropy (MaxEnt), to model current and potential distribution of these species.

RESULTS : The mean critical thermal maxima (CT_max ) ranged from 39.5±0.9^° C - 44.6±0.6^° C and 46.8±0.7^° C- 48.5±0.9^° C for parasitoids and stemborers, with C. sesamiae and C. partellus exhibiting the lowest and highest CT_max respectively. From the present climate to 2050s scenario, parasitoids recorded significant reduction in warming tolerance than their hosts. Habitat suitability for all stemborer-parasitoid species was spatially heterogeneous under current and future climatic scenarios. Cotesia sesamiae C. flavipes and B. fusca exhibited significant habitat loss while C. partellus and S. calamistis showed a significant habitat gain under future 2050s predictions. Model metrics based on mean area under the curve ranged from 0.72 to 0.84 for all species, indicating good predictive performance of the models.

CONCLUSION : These results suggest C. sesamiae and C. flavipes may face survival constraints or extirpation than their pest hosts when environmental temperature reaches their upper thermal limits earlier, likely reducing pest regulation through density-mediated effects. The results demonstrate potential destabilisation of stemborer-parasitoid trophic systems potentially compromising biocontrol efficacy under climate warming. This article is protected by copyright. All rights reserved.

Mutamiswa Reyard, Chikowore Gerald, Nyamukondiwa Casper, Mudereri Bester Tawona, Khan Zeyaur Rahman, Chidawanyika Frank

2022-Jun-30

MaxEnt, biogeography, climate change, host-parasitoid interaction, warming tolerance

In Frontiers in neurology

Background : Traumatic brain injury (TBI) is the main cause of death and severe disability in young adults worldwide. Progressive hemorrhage (PH) worsens the disease and can cause a poor neurological prognosis. Radiomics analysis has been used for hematoma expansion of hypertensive intracerebral hemorrhage. This study attempts to develop an optimal radiomics model based on non-contrast CT to predict PH by machine learning (ML) methods and compare its prediction performance with clinical-radiological models.

Methods : We retrospectively analyzed 165 TBI patients, including 89 patients with PH and 76 patients without PH, whose data were randomized into a training set and a testing set at a ratio of 7:3. A total of 10 different machine learning methods were used to predict PH. Univariate and multivariable logistic regression analyses were implemented to screen clinical-radiological factors and to establish a clinical-radiological model. Then, a combined model combining clinical-radiological factors with the radiomics score was constructed. The area under the receiver operating characteristic curve (AUC), accuracy and F1 score, sensitivity, and specificity were used to evaluate the models.

Results : Among the 10 various ML algorithms, the support vector machine (SVM) had the best prediction performance based on 12 radiomics features, including the AUC (training set: 0.918; testing set: 0.879) and accuracy (training set: 0.872; test set: 0.834). Among the clinical and radiological factors, the onset-to-baseline CT time, the scalp hematoma, and fibrinogen were associated with PH. The radiomics model's prediction performance was better than the clinical-radiological model, while the predictive nomogram combining the radiomics features with clinical-radiological characteristics performed best.

Conclusions : The radiomics model outperformed the traditional clinical-radiological model in predicting PH. The nomogram model of the combined radiomics features and clinical-radiological factors is a helpful tool for PH.

Yang Qingning, Sun Jun, Guo Yi, Zeng Ping, Jin Ke, Huang Chencui, Xu Jingxu, Hou Liran, Li Chuanming, Feng Junbang

2022

machine learning, nomogram, progressive hemorrhage, radiomics, traumatic brain injury

In ... IEEE-EMBS International Conference on Biomedical and Health Informatics. IEEE-EMBS International Conference on Biomedical and Health Informatics

Gero Zelalem, Ho Joyce C

2021-Jul

Biomedical text processing, Document Summarization, Keyphrase Extraction

In Frontiers in medicine

Background : Oncotype DX Recurrence Score (RS) has been widely used to predict chemotherapy benefits in patients with estrogen receptor-positive breast cancer. Studies showed that the features used in Magee equations correlate with RS. We aimed to examine whether deep learning (DL)-based histology image analyses can enhance such correlations.

Methods : We retrieved 382 cases with RS diagnosed between 2011 and 2015 from the Emory University and the Ohio State University. All patients received surgery. DL models were developed to detect nuclei of tumor cells and tumor-infiltrating lymphocytes (TILs) and segment tumor cell nuclei in hematoxylin and eosin (H&E) stained histopathology whole slide images (WSIs). Based on the DL-based analysis, we derived image features from WSIs, such as tumor cell number, TIL number variance, and nuclear grades. The entire patient cohorts were divided into one training set (125 cases) and two validation sets (82 and 175 cases) based on the data sources and WSI resolutions. The training set was used to train the linear regression models to predict RS. For prediction performance comparison, we used independent variables from Magee features alone or the combination of WSI-derived image and Magee features.

Results : The Pearson's correlation coefficients between the actual RS and predicted RS by DL-based analysis were 0.7058 (p-value = 1.32 × 10^-13) and 0.5041 (p-value = 1.15 × 10^-12) for the validation sets 1 and 2, respectively. The adjusted R ² values using Magee features alone are 0.3442 and 0.2167 in the two validation sets, respectively. In contrast, the adjusted R ² values were enhanced to 0.4431 and 0.2182 when WSI-derived imaging features were jointly used with Magee features.

Conclusion : Our results suggest that DL-based digital pathological features can enhance Magee feature correlation with RS.

Li Hongxiao, Wang Jigang, Li Zaibo, Dababneh Melad, Wang Fusheng, Zhao Peng, Smith Geoffrey H, Teodoro George, Li Meijie, Kong Jun, Li Xiaoxian

2022

ER+ breast cancer, Magee equation, Oncotype DX score, deep learning-based algorithm, digital pathology

In Studies in health technology and informatics ; h5-index 23.0

Al-Edresee Thamer

2022-Jun-29

Machine learning adoption by healthcare providers, Physician adoption of machine learning, machine learning ethics, physicians trust of machine learning

In Studies in health technology and informatics ; h5-index 23.0

Guerdoux Guillaume, Tiffet Théophile, Bousquet Cedric

2022-Jun-29

Artificial Intelligence, COVID-19, MLOps, Social Media, Vaccines

In Frontiers in medicine

Sharma Revati, Kannourakis George, Prithviraj Prashanth, Ahmed Nuzhat

2022

artificial intelligence, gut microbiome, nanomedicine, precision medicine, renal cell carcinoma

In Frontiers in psychology ; h5-index 92.0

Li Ya, Li Xiulai, Lou Zheng, Chen Chaofan

2022

LSTM, autoencoder, emotion, music analysis, music therapy, psychology

In Frontiers in psychology ; h5-index 92.0

Moradbakhti Laura, Schreibelmayr Simon, Mara Martina

2022

Artificial Intelligence, agency, autonomy, competence, gender stereotypes, relatedness, technology acceptance, voice assistants

In Frontiers in psychology ; h5-index 92.0

Azevedo Roger, Bouchet François, Duffy Melissa, Harley Jason, Taub Michelle, Trevors Gregory, Cloude Elizabeth, Dever Daryn, Wiedbusch Megan, Wortha Franz, Cerezo Rebeca

2022

intelligent tutoring systems, learning, metacognition, multimodal data, pedagogical agents, scaffolding, self-regulated learning, trace data

In Frontiers in big data

Wenskovitch John, Jefferson Brett, Anderson Alexander, Baweja Jessica, Ciesielski Danielle, Fallon Corey

2022

cognitive load, contingency analysis, human-machine teaming, power grid, trust evaluation

In Frontiers in plant science

Sun Chenxin, Huang Chengwei, Zhang Huaiqing, Chen Bangqian, An Feng, Wang Liwen, Yun Ting

2022

airborne LiDAR, deep learning, forest parameter retrieval, heightmap, individual tree crown segmentation

In Frontiers in plant science

Batista Thiago Barbosa, Mastrangelo Clíssia Barboza, de Medeiros André Dantas, Petronilio Ana Carolina Picinini, Fonseca de Oliveira Gustavo Roberto, Dos Santos Isabela Lopes, Crusciol Carlos Alexandre Costa, Amaral da Silva Edvaldo Aparecido

2022

Glycine max, chlorophyll fluorescence, seed maturity, seed quality, support vector machine

In Frontiers in immunology ; h5-index 100.0

Background : Differential diagnosis of demyelinating diseases of the central nervous system is a challenging task that is prone to errors and inconsistent reading, requiring expertise and additional examination approaches. Advancements in deep-learning-based image interpretations allow for prompt and automated analyses of conventional magnetic resonance imaging (MRI), which can be utilized in classifying multi-sequence MRI, and thus may help in subsequent treatment referral.

Methods : Imaging and clinical data from 290 patients diagnosed with demyelinating diseases from August 2013 to October 2021 were included for analysis, including 67 patients with multiple sclerosis (MS), 162 patients with aquaporin 4 antibody-positive (AQP4+) neuromyelitis optica spectrum disorder (NMOSD), and 61 patients with myelin oligodendrocyte glycoprotein antibody-associated disease (MOGAD). Considering the heterogeneous nature of lesion size and distribution in demyelinating diseases, multi-modal MRI of brain and/or spinal cord were utilized to build the deep-learning model. This novel transformer-based deep-learning model architecture was designed to be versatile in handling with multiple image sequences (coronal T2-weighted and sagittal T2-fluid attenuation inversion recovery) and scanning locations (brain and spinal cord) for differentiating among MS, NMOSD, and MOGAD. Model performances were evaluated using the area under the receiver operating curve (AUC) and the confusion matrices measurements. The classification accuracy between the fusion model and the neuroradiological raters was also compared.

Results : The fusion model that was trained with combined brain and spinal cord MRI achieved an overall improved performance, with the AUC of 0.933 (95%CI: 0.848, 0.991), 0.942 (95%CI: 0.879, 0.987) and 0.803 (95%CI: 0.629, 0.949) for MS, AQP4+ NMOSD, and MOGAD, respectively. This exceeded the performance using the brain or spinal cord MRI alone for the identification of the AQP4+ NMOSD (AUC of 0.940, brain only and 0.689, spinal cord only) and MOGAD (0.782, brain only and 0.714, spinal cord only). In the multi-category classification, the fusion model had an accuracy of 81.4%, which was significantly higher compared to rater 1 (64.4%, p=0.04<0.05) and comparable to rater 2 (74.6%, p=0.388).

Conclusion : The proposed novel transformer-based model showed desirable performance in the differentiation of MS, AQP4+ NMOSD, and MOGAD on brain and spinal cord MRI, which is comparable to that of neuroradiologists. Our model is thus applicable for interpretating conventional MRI in the differential diagnosis of demyelinating diseases with overlapping lesions.

Huang Chuxin, Chen Weidao, Liu Baiyun, Yu Ruize, Chen Xiqian, Tang Fei, Liu Jun, Lu Wei

2022

MRI, deep learning, demyelinating disease, differential diagnosis, multiple sclerosis, myelin oligodendrocyte glycoprotein antibody-associated disease, neuromyelitis optica spectrum disorder, transformer

In Frontiers in artificial intelligence

Fossen Frank M, Samaan Daniel, Sorgner Alina

2022

artificial intelligence, labor market, robots, software, wage dynamics

In Frontiers in robotics and AI

Auflem Marius, Kohtala Sampsa, Jung Malte, Steinert Martin

2022

artificial intelligence, facial action units, facial expression, humanoid robots, medical simulation, robot development

In Studies in health technology and informatics ; h5-index 23.0

Cooke Elizabeth A, Lemanska Agnieszka, Livings Jennifer, Thomas Spencer A

2022-Jun-29

COVID-19, Deep Learning, Mental Health, Visualization

In Studies in health technology and informatics ; h5-index 23.0

Andriani Sekar Putri, Adhyanacarira Padmanaba, Fuad Anis, Pertiwi Ariani Arista Putri

2022-Jun-29

COVID-19, artificial intelligence, mHealth apps, self-screening

In Frontiers in public health

Xu Hui, Pan Wei, Xin Meng, Pan Wulin, Hu Cheng, Wanqiang Dai, Huang Ge

2022

economic factors, environmental factors, machine learning, “residents health”, social factors

In Frontiers in human neuroscience ; h5-index 79.0

Shaw Saurabh Bhaskar, Levy Yarden, Mizzi Allison, Herman Gabrielle, McKinnon Margaret C, Heisz Jennifer J, Becker Suzanna

2022

aerobic exercise, central executive network (CEN), default mode network (DMN), intrinsic connectivity networks (ICN), mindfulness, neurofeedback, salience network (SN), tri-network model

In Computational intelligence and neuroscience

Li Dongxing, Luo Zuying

2022

In Computational intelligence and neuroscience

Alshamrani Khalaf, Alshamrani Hassan, Alqahtani F F, Alshehri Ali H

2022

In Computational intelligence and neuroscience

Jia Xiaoguang

2022

In Computational intelligence and neuroscience

Zhang Shuchang, Shan Fengjun

2022

In Computational intelligence and neuroscience

Ibrahim Ahmed Farid, Alarifi Sulaiman A, Elkatatny Salaheldin

2022

In IEEE journal of translational engineering in health and medicine

BACKGROUND : Detection and segmentation of brain tumors using MR images are challenging and valuable tasks in the medical field. Early diagnosing and localizing of brain tumors can save lives and provide timely options for physicians to select efficient treatment plans. Deep learning approaches have attracted researchers in medical imaging due to their capacity, performance, and potential to assist in accurate diagnosis, prognosis, and medical treatment technologies.

METHODS AND PROCEDURES : This paper presents a novel framework for segmenting 2D brain tumors in MR images using deep neural networks (DNN) and utilizing data augmentation strategies. The proposed approach (Znet) is based on the idea of skip-connection, encoder-decoder architectures, and data amplification to propagate the intrinsic affinities of a relatively smaller number of expert delineated tumors, e.g., hundreds of patients of the low-grade glioma (LGG), to many thousands of synthetic cases.

RESULTS : Our experimental results showed high values of the mean dice similarity coefficient (dice = 0.96 during model training and dice = 0.92 for the independent testing dataset). Other evaluation measures were also relatively high, e.g., pixel accuracy = 0.996, F1 score = 0.81, and Matthews Correlation Coefficient, MCC = 0.81. The results and visualization of the DNN-derived tumor masks in the testing dataset showcase the ZNet model's capability to localize and auto-segment brain tumors in MR images. This approach can further be generalized to 3D brain volumes, other pathologies, and a wide range of image modalities.

CONCLUSION : We can confirm the ability of deep learning methods and the proposed Znet framework to detect and segment tumors in MR images. Furthermore, pixel accuracy evaluation may not be a suitable evaluation measure for semantic segmentation in case of class imbalance in MR images segmentation. This is because the dominant class in ground truth images is the background. Therefore, a high value of pixel accuracy can be misleading in some computer vision applications. On the other hand, alternative evaluation metrics, such as dice and IoU (Intersection over Union), are more factual for semantic segmentation.

CLINICAL IMPACT : Artificial intelligence (AI) applications in medicine are advancing swiftly, however, there is a lack of deployed techniques in clinical practice. This research demonstrates a practical example of AI applications in medical imaging, which can be deployed as a tool for auto-segmentation of tumors in MR images.

Ottom Mohammad Ashraf, Rahman Hanif Abdul, Dinov Ivo D

2022

Brain tumor, augmentation, deep learning, neural networks, region segmentation

In Biomedical optics express

Yuan Zhuoqun, Yang Di, Yang Zihan, Zhao Jingzhu, Liang Yanmei

2022-May-01

In Biomedical optics express

Moradi Mousa, Du Xian, Huan Tianxiao, Chen Yu

2022-May-01

In Studies in health technology and informatics ; h5-index 23.0

Boukobza Adrien, Wack Maxime, Neuraz Antoine, Geromin Daniela, Badoual Cécile, Bats Anne-Sophie, Burgun Anita, Koual Meriem, Tsopra Rosy

2022-Jun-29

Breast cancer, Clustering, Machine learning, NLP

In Studies in health technology and informatics ; h5-index 23.0

Samo Giuseppe, Bonan Caterina, Si Fuzhen

2022-Jun-29

COVID-19, Corpora, Knowledge Reproduction, Language Models, Natural Language Processing

In Biomedical optics express

Hofer Dominik, Schmidt-Erfurth Ursula, Orlando José Ignacio, Goldbach Felix, Gerendas Bianca S, Seeböck Philipp

2022-May-01

In Chemical science

Andrews James, Gkountouna Olga, Blaisten-Barojas Estela

2022-Jun-15

In Emergency medicine international

Sun Manman, Wang Lijun

2022

In Frontiers in endocrinology ; h5-index 55.0

Bian Che, Ren Huiwen

2022

NAD+, Sirtuin (SIRT), diabetes, diabetic kidney disease, kidney

In Frontiers in aging neuroscience ; h5-index 64.0

Oh Ju-Young, Lee Ye-Seul, Hwang Tae-Yeon, Cho Seong-Jin, Jang Jae-Hwan, Ryu Yeonhee, Park Hi-Joon

2022

Parkinson’s disease, acupuncture, functional connectivity, machine learning, primary motor cortex

In Frontiers in aging neuroscience ; h5-index 64.0

Background : Detection of mild cognitive impairment (MCI) is essential to screen high risk of Alzheimer's disease (AD). However, subtle changes during MCI make it challenging to classify in machine learning. The previous pathological analysis pointed out that the hippocampus is the critical hub for the white matter (WM) network of MCI. Damage to the white matter pathways around the hippocampus is the main cause of memory decline in MCI. Therefore, it is vital to biologically extract features from the WM network driven by hippocampus-related regions to improve classification performance.

Methods : Our study proposes a method for feature extraction of the whole-brain WM network. First, 42 MCI and 54 normal control (NC) subjects were recruited using diffusion tensor imaging (DTI), resting-state functional magnetic resonance imaging (rs-fMRI), and T1-weighted (T1w) imaging. Second, mean diffusivity (MD) and fractional anisotropy (FA) were calculated from DTI, and the whole-brain WM networks were obtained. Third, regions of interest (ROIs) with significant functional connectivity to the hippocampus were selected for feature extraction, and the hippocampus (HIP)-related WM networks were obtained. Furthermore, the rank sum test with Bonferroni correction was used to retain significantly different connectivity between MCI and NC, and significant HIP-related WM networks were obtained. Finally, the classification performances of these three WM networks were compared to select the optimal feature and classifier.

Results : (1) For the features, the whole-brain WM network, HIP-related WM network, and significant HIP-related WM network are significantly improved in turn. Also, the accuracy of MD networks as features is better than FA. (2) For the classification algorithm, the support vector machine (SVM) classifier with radial basis function, taking the significant HIP-related WM network in MD as a feature, has the optimal classification performance (accuracy = 89.4%, AUC = 0.954). (3) For the pathologic mechanism, the hippocampus and thalamus are crucial hubs of the WM network for MCI.

Conclusion : Feature extraction from the WM network driven by hippocampus-related regions provides an effective method for the early diagnosis of AD.

Zhou Yu, Si Xiaopeng, Chao Yi-Ping, Chen Yuanyuan, Lin Ching-Po, Li Sicheng, Zhang Xingjian, Sun Yulin, Ming Dong, Li Qiang

2022

Alzheimer’s disease, early diagnosis, feature extraction, machine learning, mild cognitive impairment, white matter connectivity

In Journal of dental research ; h5-index 65.0

Park Y S, Choi J H, Kim Y, Choi S H, Lee J H, Kim K H, Chung C J

2022-Jun-30

3-dimensional, conditional GAN, deep learning, orthodontics, outcome simulation, soft tissue prediction

In Palliative medicine ; h5-index 47.0

BACKGROUND : Few studies have developed automatic systems for identifying social distress, spiritual pain, and severe physical and phycological symptoms from text data in electronic medical records.

AIM : To develop models to detect social distress, spiritual pain, and severe physical and psychological symptoms in terminally ill patients with cancer from unstructured text data contained in electronic medical records.

DESIGN : A retrospective study of 1,554,736 narrative clinical records was analyzed 1 month before patients died. Supervised machine learning models were trained to detect comprehensive symptoms, and the performance of the models was tested using the area under the receiver operating characteristic curve (AUROC) and precision recall curve (AUPRC).

SETTING/PARTICIPANTS : A total of 808 patients was included in the study using records obtained from a university hospital in Japan between January 1, 2018 and December 31, 2019. As training data, we used medical records labeled for detecting social distress (n = 10,000) and spiritual pain (n = 10,000), and records that could be combined with the Support Team Assessment Schedule (based on date) for detecting severe physical/psychological symptoms (n = 5409).

RESULTS : Machine learning models for detecting social distress had AUROC and AUPRC values of 0.98 and 0.61, respectively; values for spiritual pain, were 0.90 and 0.58, respectively. The machine learning models accurately identified severe symptoms (pain, dyspnea, nausea, insomnia, and anxiety) with a high level of discrimination (AUROC > 0.8).

CONCLUSION : The machine learning models could detect social distress, spiritual pain, and severe symptoms in terminally ill patients with cancer from text data contained in electronic medical records.

Masukawa Kento, Aoyama Maho, Yokota Shinichiroh, Nakamura Jyunya, Ishida Ryoka, Nakayama Masaharu, Miyashita Mitsunori

2022-Jun-30

Symptom assessment, electronic medical records, machine learning, psychosocial support systems, spirituality, terminal care

In Studies in health technology and informatics ; h5-index 23.0

Varga Gabriela, Stoicu-Tivadar Lăcrămioara, Nicola Stelian

2022-Jun-29

artificial intelligence, multimodal interaction, rheumatoid arthritis, serious games

In Studies in health technology and informatics ; h5-index 23.0

Sahadev Divya, Lovegrove Thomas, Kunz Holger

2022-Jun-29

Machine learning, Predictive Modelling, Surgery Case Duration

In Studies in health technology and informatics ; h5-index 23.0

Aldhoayan Mohammed D

2022-Jun-29

Artificial Intelligence, Covid-19, Healthcare, Machine Learning

In Studies in health technology and informatics ; h5-index 23.0

Ali Hazrat, Alam Tanvir, Househ Mowafa, Shah Zubair

2022-Jun-29

Artificial Intelligence, COVID-19, Federated Learning, Healthcare, Internet of Medical Things, Privacy

In Studies in health technology and informatics ; h5-index 23.0

Danilov Gleb, Kotik Konstantin, Shevchenko Elena, Usachev Dmitriy, Shifrin Michael, Strunina Yulia, Tsukanova Tatyana, Ishankulov Timur, Lukshin Vasiliy, Potapov Alexander

2022-Jun-29

Length of stay, deep learning, natural language processing, neural networks, neurosurgery, prediction

In Studies in health technology and informatics ; h5-index 23.0

Shifrin Michael, Khavtorin Anton, Danilov Gleb

2022-Jun-29

Artificial intelligence, blockchain, medical decision support systems, trust

In Studies in health technology and informatics ; h5-index 23.0

Mohsen Farida, Biswas Md Rafiul, Ali Hazrat, Alam Tanvir, Househ Mowafa, Shah Zubair

2022-Jun-29

AutoML, Diabetes classification, Ensemble model, Machine learning

In Studies in health technology and informatics ; h5-index 23.0

Yoon Sunmoo, Mendes Alexandra, Burgio Louis, Mittelman Mary, Dunner Ilana, Levine Jed A, Hoyos Carolina, Tipiani Dante, Ramirez Mildred, Teresi Jeanne A, Luchsinger José A

2022-Jun-29

aging, dementia caregiving, disparities, machine learning, social work

In Studies in health technology and informatics ; h5-index 23.0

Feretzakis Georgios, Sakagianni Aikaterini, Kalles Dimitris, Loupelis Evangelos, Tzelves Lazaros, Panteris Vasileios, Chatzikyriakou Rea, Trakas Nikolaos, Kolokytha Stavroula, Batiani Polyxeni, Rakopoulou Zoi, Tika Aikaterini, Petropoulou Stavroula, Dalainas Ilias, Kaldis Vasileios

2022-Jun-29

Machine learning, clustering, emergency department, hospital admission, k-means, unsupervised learning

In Studies in health technology and informatics ; h5-index 23.0

Gharehbaghi Arash, Babic Ankica

2022-Jun-29

A-Test method, Deep time growing neural network, deep learning, heart sounds, intelligent phonocardiography

In Studies in health technology and informatics ; h5-index 23.0

Tzelves Lazaros, Feretzakis Georgios, Kalles Dimitris, Manolitsis Ioannis, Katsimperis Stamatis, Bellos Themistoklis, Berdempes Marinos, Anastasiou Athanasios, Koutsouris Dimitrios, Kofopoulou Stavroula, Verykios Vassilios S, Skolarikos Andreas, Varkarakis Ioannis

2022-Jun-29

Benign prostatic enlargement, artificial intelligence, clustering analysis, transurethral prostate resection

In Studies in health technology and informatics ; h5-index 23.0

Manolitsis Ioannis, Feretzakis Georgios, Tzelves Lazaros, Kalles Dimitris, Loupelis Evangelos, Katsimperis Stamatis, Kosmidis Thanos, Anastasiou Athanasios, Koutsouris Dimitrios, Kofopoulou Stavroula, Verykios Vassilios S, Skolarikos Andreas, Varkarakis Ioannis

2022-Jun-29

AMR, Antimicrobial Resistance, Association rules, unsupervised ML

In Studies in health technology and informatics ; h5-index 23.0

Perbix Mona, Löbe Matthias, Stäubert Sebastian, Sinaci A Anil, Gencturk Mert, Quintero Miriam, Martinez-Garcia Alicia, Alvarez-Romero Celia, Parra-Calderon Carlos L, Winter Alfred

2022-Jun-29

Health Information Systems, Organizational Models, Systems Analysis

In Studies in health technology and informatics ; h5-index 23.0

Sakagianni Aikaterini, Feretzakis Georgios, Kalles Dimitris, Loupelis Evangelos, Rakopoulou Zoi, Dalainas Ilias, Fildisis Georgios

2022-Jun-29

Antimicrobial resistance, Association rules, Machine Learning

In Studies in health technology and informatics ; h5-index 23.0

Iqbal Mohammad Sharique, Abd-Alrazaq Alaa, Househ Mowafa

2022-Jun-29

Fraud, artificial intelligence, deep learning, healthcare settings, machine learning

In Studies in health technology and informatics ; h5-index 23.0

Cooke Elizabeth A, Lemanska Agnieszka, Livings Jennifer, Thomas Spencer A

2022-Jun-29

COVID-19, Deep Learning, Mental Health, Visualization

In Studies in health technology and informatics ; h5-index 23.0

Noll Richard, Minor Mirjam, Berger Alexandra, Naab Lukas, Bay Matthias, Storf Holger, Schaaf Jannik

2022-Jun-29

Artificial Intelligence, Classification, Coding Support, Rare Diseases

In Studies in health technology and informatics ; h5-index 23.0

Danilov Gleb, Kotik Konstantin, Shifrin Michael, Strunina Yulia, Pronkina Tatiana, Tsukanova Tatiana, Nepomnyashiy Vladimir, Konovalov Nikolay, Potapov Alexander

2022-Jun-29

Neurosurgery, artificial intelligence, classification, deep learning, machine learning, neurosurgical procedures

In Studies in health technology and informatics ; h5-index 23.0

Poly Tahmina Nasrin, Islam Md Mohaimenul, Li Yu-Chuan Jack

2022-Jun-29

Diabetes, early-stage prediction, machine learning, random forest

In Studies in health technology and informatics ; h5-index 23.0

Feretzakis Georgios, Sakagianni Aikaterini, Kalles Dimitris, Loupelis Evangelos, Panteris Vasileios, Tzelves Lazaros, Chatzikyriakou Rea, Trakas Nikolaos, Kolokytha Stavroula, Batiani Polyxeni, Rakopoulou Zoi, Tika Aikaterini, Petropoulou Stavroula, Dalainas Ilias, Kaldis Vasileios

2022-Jun-29

Artificial intelligence, R programming language, emergency department, machine learning, predict hospitalization

In Studies in health technology and informatics ; h5-index 23.0

Shapiro Michael, Shahar Yuval

2022-Jun-29

Decision support, ICU, Temporal deep learning

In Studies in health technology and informatics ; h5-index 23.0

Zubillaga Aitor, Laccourreye Paula, Kerexeta Jon, Larburu Nekane, Alonso Eduardo, Gómez D Jesús, Martínez Francisco, Alonso-Arce Maykel

2022-Jun-29

Hospital readmissions, machine learning, natural language processing, sentiment analysis, unstructured data

In Studies in health technology and informatics ; h5-index 23.0

Cui Wanting, Finkelstein Joseph

2022-Jun-29

No-show visits, supervised machine learning, telemedicine

In Studies in health technology and informatics ; h5-index 23.0

Azarpira Mohammadreza, Redjdal Akram, Bouaud Jacques, Seroussi Brigitte

2022-Jun-29

Clinical practice guidelines, machine learning, natural language processing, ontology

In Studies in health technology and informatics ; h5-index 23.0

Malihi Leila, Hüsers Jens, Richter Mats L, Moelleken Maurice, Przysucha Mareike, Busch Dorothee, Heggemann Jan, Hafer Guido, Wiemeyer Stefan, Heidemann Gunther, Dissemond Joachim, Erfurt-Berge Cornelia, Hübner Ursula

2022-Jun-29

Clinical Decision Support System, Convolutional Neural Networks, Diabetic Foot Ulcer, Health Information Technology, Image Classification, Transfer Learning, Wound Care

In Studies in health technology and informatics ; h5-index 23.0

Borycki Elizabeth M, Farghali Amr, Kushniruk Andre W

2022-Jun-29

Patient safety, health technology, health technology safety, technology-induced error

In Studies in health technology and informatics ; h5-index 23.0

** : The early warning system alarms the rapid response team (RRT) for clinical deterioration monitoring and prediction. Available systems do not perform well to decrease the number of ICU transfers or death. This study aimed to address the requirement of an intelligent warning system for timely and accurate RRT activation.

METHODOLOGY : A literature review was conducted in scientific databases to extract data. Then, a questionnaire was developed for experts' views collection (N=12). The collected data were analyzed using the Content Validity Ratio (CVR). According to the Lawshe table for the corresponding number of experts, the cut-off=0.56 for items to be accepted/rejected was considered. A schematic structure was suggested.

FINDINGS : The analysis of the extracted papers (N=24) and qualitative analysis addressed 44 requirements in the frame of five involved sub-systems, including a patient monitoring system, electronic health record, clinical decision support system, remote monitoring patient, and dashboard &registries. They were confirmed by meeting the least cut-off value (CVR= 0.86).

CONCLUSION : An integrated approach and technologies of IoT, deep and machine learning techniques, big data, advanced databases, and standards to create an intelligent EWS are required.

Rostam Niakan Kalhori Sharareh, Deserno Thomas M

2022-Jun-29

Clinical deterioration, artificial intelligence, monitoring, warning system

In Studies in health technology and informatics ; h5-index 23.0

Aldhoayan Mohammed D

2022-Jun-29

Artificial Intelligence, Covid-19, Healthcare, Machine Learning

In Studies in health technology and informatics ; h5-index 23.0

Guerdoux Guillaume, Tiffet Théophile, Bousquet Cedric

2022-Jun-29

Artificial Intelligence, COVID-19, MLOps, Social Media, Vaccines

In Studies in health technology and informatics ; h5-index 23.0

Yoon Sunmoo, Broadwell Peter, Sun Frederick F, Jang Sun Joo, Lee Haeyoung

2022-Jun-29

Dementia caregiving, emotional valence, natural language processing

In Studies in health technology and informatics ; h5-index 23.0

Beltramin Diva, Lamas Eugenia, Bousquet Cédric

2022-Jun-29

Artificial intelligence, Black boxes, Decision making, Ethics, Trust

In Studies in health technology and informatics ; h5-index 23.0

Andriani Sekar Putri, Adhyanacarira Padmanaba, Fuad Anis, Pertiwi Ariani Arista Putri

2022-Jun-29

COVID-19, artificial intelligence, mHealth apps, self-screening

In Studies in health technology and informatics ; h5-index 23.0

Samo Giuseppe, Bonan Caterina, Si Fuzhen

2022-Jun-29

COVID-19, Corpora, Knowledge Reproduction, Language Models, Natural Language Processing

In Studies in health technology and informatics ; h5-index 23.0

Shah Uzair, Ali Hazrat, Alam Tanvir, Househ Mowafa, Shah Zubair

2022-Jun-29

deep learning, machine learning, tweets, vaccines

In Studies in health technology and informatics ; h5-index 23.0

Ali Hazrat, Alam Tanvir, Househ Mowafa, Shah Zubair

2022-Jun-29

Artificial Intelligence, COVID-19, Federated Learning, Healthcare, Internet of Medical Things, Privacy

In Studies in health technology and informatics ; h5-index 23.0

Nicola Stelian, Chirila Oana-Sorina, Stoicu-Tivadar Lacramioara

2022-Jun-29

Leap Motion, Linear-SVM, MLP, Machine learning, Multimodal interaction, Recovery

In The Canadian journal of cardiology

Picard Fabien, Pighi Michele, Marquis-Gravel Guillaume, Labinaz Marino, Cohen Eric A, Tanguay Jean-François

2022-Jun-28

In Chest ; h5-index 81.0

BACKGROUND : Prognostic prediction of nontuberculous mycobacteria pulmonary disease using a deep learning technique has not been attempted.

RESEARCH QUESTION : Can a deep learning model using chest radiograph predict the prognosis of nontuberculous mycobacteria pulmonary disease?

STUDY DESIGN AND METHODS : Patients diagnosed with nontuberculous mycobacteria pulmonary disease at Seoul National University Hospital (train/validation dataset) between January 2000 and December 2015 and at Seoul Metropolitan Government-Boramae Medical Center (test dataset) between January 2006 and December 2015 were included. We trained deep learning models to predict the 3-, 5-, and 10-year overall mortality using baseline chest radiographs at diagnosis. We tested the predictability for the corresponding mortality using only deep learning-driven radiographic scores and using both radiographic scores and clinical information (age, sex, body mass index, and mycobacterial species).

RESULTS : The datasets comprised 1,638 (train/validation set) and 566 (test set) chest radiographs from 1,034 and 200 patients, respectively. The deep learning-driven radiographic score provided areas under the receiver operating characteristic curve of 0.844, 0.781, and 0.792 for the 10-, 5-, and 3-year mortality, respectively. The logistic regression model using both the radiographic score and clinical information provided areas under the receiver operating characteristic curves of 0.922, 0.942, and 0.865 for the 10-, 5, and 3-year mortality, respectively.

INTERPRETATION : The deep learning model we developed could predict the mid- to-long-term mortality of patients with nontuberculous mycobacteria pulmonary disease using a baseline radiograph at diagnosis, and the predictability increased with clinical information.

Lee Seowoo, Lee Hyun Woo, Kim Hyung-Jun, Kim Deog Kyeom, Yim Jae-Joon, Yoon Soon Ho, Kwak Nakwon

2022-Jun-28

Artificial Intelligence, Mortality, Mycobacterium Infections, Nontuberculous, Predictive Value of Tests, Prognosis

In Studies in health technology and informatics ; h5-index 23.0

Castellanos Julio, Raposo Gonzalo, Antunez Lucia

2022-Jun-29

Artificial Intelligence, Data Federation, Healthcare Systems

In Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie

Ahmed Faheem, Soomro Afaque Manzoor, Chethikkattuveli Salih Abdul Rahim, Samantasinghar Anupama, Asif Arun, Kang In Suk, Choi Kyung Hyun

2022-Jun-28

AI on networks, Deep learning, Drug repurposing, Machine learning, Network analysis, Network diffusion, Network proximity

In Stem cell reports

Yoshihara Masahito, Kirjanov Ida, Nykänen Sonja, Sokka Joonas, Weltner Jere, Lundin Karolina, Gawriyski Lisa, Jouhilahti Eeva-Mari, Varjosalo Markku, Tervaniemi Mari H, Otonkoski Timo, Trokovic Ras, Katayama Shintaro, Vuoristo Sanna, Kere Juha

2022-Jun-16

DUX4, NaPi2b, SLC34A2, blastomere, embryonic genome activation, embryonic stem cells, human embryo, reprogramming

In Forensic science international. Genetics

Freire-Aradas A, Girón-Santamaría L, Mosquera-Miguel A, Ambroa-Conde A, Phillips C, Casares de Cal M, Gómez-Tato A, Álvarez-Dios J, Pospiech E, Aliferi A, Syndercombe Court D, Branicki W, Lareu M V

2022-Jun-25

DNA methylation, EpiTYPER®, Forensic age estimation, Machine learning, Quantile regression

In Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie

Ahmed Faheem, Soomro Afaque Manzoor, Chethikkattuveli Salih Abdul Rahim, Samantasinghar Anupama, Asif Arun, Kang In Suk, Choi Kyung Hyun

2022-Jun-28

AI on networks, Deep learning, Drug repurposing, Machine learning, Network analysis, Network diffusion, Network proximity

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVES : The detection and delineation of atherosclerotic plaque are usually manually performed by medical experts on the carotid artery. Evidence suggests that this manual process is subject to errors and has a large variability between experts, equipment, and datasets. This paper proposes a robust end-to-end framework for automatic atherosclerotic plaque detection.

METHODS : The proposed framework is composed of: (1) a semantic segmentation model based on U-Net, with EfficientNet as the backbone, that obtains a segmentation mask with the carotid intima-media region; and (2) a convolutional neural network designed using Bayesian optimization that simultaneously performs a regression to get the average and maximum carotid intima media thickness, and a classification to determine the presence of plaque.

RESULTS : Our approach improves the state-of-the-art in both co and bulb territories in the REGICOR database, with more than 8000 images, while providing predictions in real-time. The correlation coefficient was 0.89 in the common carotid artery and 0.74 for bulb region, and the F1 score for atherosclerotic plaque detecting was 0.60 and 0.59, respectively. The experimentation carried out includes a comparison with other fully automatic methods for carotid intima media thickness estimation found in the literature. Additionally, we present an extensive experimental study to evaluate the robustness of our proposal, as well as its suitability and efficiency compared to different versions of the framework.

CONCLUSIONS : The proposed end-to-end framework significantly improves the automatic characterization of atherosclerotic plaque. The generation of the segmented mask can be helpful for practitioners since it allows them to evaluate and interpret the model's results by visual inspection. Furthermore, the proposed framework overcomes the limitations of previous research based on ad-hoc post-processing, which could lead to overestimations in the case of oblique forms of the carotid artery.

Gago Lucas, Vila Maria Del Mar, Grau Maria, Remeseiro Beatriz, Igual Laura

2022-Jun-15

Atherosclerotic plaque, CIMT estimation, Deep learning, Semantic segmentation

In Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society

Liu Yashu, Wang Wei, Luo Gongning, Wang Kuanquan, Li Shuo

2022-Jun-16

Contrastive learning, Left atrium segmentation, Semi-supervised learning

In Neural networks : the official journal of the International Neural Network Society

Malik Nahiyan, Bzdok Danilo

2022-Jun-18

Brain imaging, Convolutional neural network algorithms, Deep learning, Imaging neuroscience, Machine learning, Transfer learning

In Journal of environmental management

Pal Swades, Singha Pankaj

2022-Jun-28

Ensemble machine learning and predicted restoration sites, Hydrological parameters, Spectral indices, Wetland restoration

In Journal of environmental management

Kim Kyung-Min, Ahn Johng-Hwa

2022-Jun-28

Artificial intelligence, Chlorophyll-a, Feature importance, Han river basin, Machine learning, Random forest

In Phytomedicine : international journal of phytotherapy and phytopharmacology

BACKGROUND : The field of network pharmacology showed significant development. The concept of network pharmacology has many similarities to the philosophy of traditional Chinese medicine (TCM), making it suitable to understand the action mechanisms of TCM in treating complex diseases, such as ischemic heart diseases (IHDs).

PURPOSE : This review summarizes the representative applications of network pharmacology in deciphering the mechanism underlying the treatment of IHDs with TCM.

METHODS : In this report, we used "ischemic heart disease" OR "coronary heart disease" OR "coronary artery disease" OR "myocardial ischemia" AND ("network pharmacology" OR "systematic pharmacology") as keywords to search for publications from PubMed, the Web of Science, and Google Scholar databases and then analyzed the representative research reports that summarized and validated the active components and targets network of TCM in improving IHDs to show the advantages and deficiencies of network pharmacology applied in TCM research.

RESULTS : The network pharmacology research indicated that HGF, PGF, MMP3, INSR, PI3K, MAPK1, SRC, VEGF, VEGFR-1, NO, eNOS, NO3, IL-6, TNF-α, and more are the main targets of TCM. Apigenin, 25S-macrostemonoside P, ginsenosides Re, Rb3, Rg3, SheXiang XinTongNing, colchicine, dried ginger-aconite decoction, Suxiao Xintong dropping pills, Ginseng-Danshen drug pair and Shenlian and more are the active ingredients, extracts, and formulations of TCM to ameliorate IHDs. These active compounds, extract, and formulations of TCM treat IHDs by delaying ventricular remodeling, reducing myocardial fibrosis, decreasing reactive oxygen species, regulating myocardial energy metabolism, ameliorating inflammation, mitigating apoptosis, and many other aspects.

CONCLUSIONS : The network pharmacology supplies a novel research exemplification for understanding the treatment of IHDs with TCM. However, the application of network pharmacology in TCM studies is still at a superficial level. By rational combining artificial intelligence technology and network pharmacology, molecular biology, metabolomics, and other advanced theories and technologies, and systematically studying the metabolic process and the network among products, targets, and pathways of TCM from the clinical perspective may be a potential development trend in network pharmacology.

Yang Hua-Yi, Liu Men-Lan, Luo Pei, Yao Xin-Sheng, Zhou Hua

2022-Jun-12

Database, Ischemic heart diseases, Myocardial ischemia, Network pharmacology, Traditional Chinese medicine

In Clinical nutrition (Edinburgh, Scotland)

BACKGROUND & AIMS : The association between body composition parameters measured on computed tomography (CT) and severity of acute pancreatitis (AP) is conflicting because these composition parameters vary considerably by sex and age. We previously developed normative body composition data, in healthy subjects. Z-score calculated from the normative data gives age and sex adjusted body composition parameters. We studied the above association using this novel Z-score in a large cohort of patients with AP.

METHODS : Between January 2014 and March 2018, patients admitted with AP and had CT scans within a week of admission, were enrolled. Body composition data including skeletal muscle (SM), subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) were calculated from the CT scan using deep learning automated algorithm. Then we converted the value to Z-score, and then compared the same score between mild AP, moderately severe AP and severe AP defined by revised Atlanta criteria.

RESULTS : Out of 514 patients, 336 (65.4%) are mild AP, 130 (25.3%) moderately severe AP, and 48 (9.3%) severe AP. Patients with moderately severe AP had significantly lower SM-z-score than those with mild AP (1.21 vs1.73, p = 0.048) and patients with severe AP had significantly lower SAT-z-score than those with mild AP (0.70 vs.1.29, p = 0.016). VAT-z-score was not significantly different between three groups. (p = 0.76).

CONCLUSION : Lower SM-z-score and SAT-z-score were associated with moderately severe and severe types of AP, respectively. Future prospective studies in patients with AP using Z-scores, may define the association between body composition and severity of AP, and explain the inconsistencies reported in previous studies.

Horibe Masayasu, Takahashi Naoki, Weston Alexander D, Philbrick Kenneth, Yamamoto Satoshi, Takahashi Hiroaki, Vege Santhi Swaroop

2022-Jun-18

Obesity, Skeletal muscle, Subcutaneous adipose tissue and visceral adipose tissue

In Studies in health technology and informatics ; h5-index 23.0

Tyulkova Tatyana, Chernavin Pavel, Chernavin Nikolai, Chugaev Yuri, Chernyaev Igor

2022-Jun-29

committee machine, machine learning, tuberculosis

In Database : the journal of biological databases and curation

Le Tuan-Dung, Nguyen Phuong D, Korkin Dmitry, Thieu Thanh

2022-Jun-30

In Computers in biology and medicine

Gollapalli Mohammed, Alansari Aisha, Alkhorasani Heba, Alsubaii Meelaf, Sakloua Rasha, Alzahrani Reem, Al-Hariri Mohammed, Alfares Maiadah, AlKhafaji Dania, Al Argan Reem, Albaker Waleed

2022-Jun-20

Machine learning, Permutation feature importance, Pre-diabetes, Stacking, Type 1 diabetes, Type 2 diabetes

In Computers in biology and medicine

Chen Hedan, Tan Weimin, Li Jichun, Guan Pengfei, Wu Lingjie, Yan Bo, Li Jian, Wang Yunfeng

2022-Jun-22

Deep learning, Label noise, Medical image diagnosis, Object detection, Otosclerosis

In Computers in biology and medicine

Monteiro Nelson R C, Oliveira José L, Arrais Joel P

2022-Jun-21

Attention, Binding affinity, Deep learning, Drug–target interaction, Transformer

In Computers in biology and medicine

Tyagi Shweta, Talbar Sanjay N

2022-Jun-22

CT scan, Computer-aided diagnosis, Deep learning, Generative adversarial network, Lung cancer, Squeeze & excitation

In Medicine

BACKGROUND : Transdermal delivery is very important in pharmaceutics. However, the barrier function of the stratum corneum hinders drugs absorption. How to improve transdermal delivery efficiency is a hot topic. The key advantages of physical technologies are their wide application for the delivery of previously nonappropriate transdermal drugs, such as proteins, peptides, and hydrophilic drugs. Based on the improved permeation of drugs delivered via multiple physical techniques, many more diseases may be treated, and transdermal vaccinations become possible. However, their wider application depends on the related convenient and portable devices. Combined products comprising medicine and devices represent future commercial directions of artificial intelligence and 3D printing.

METHODS : A comprehensive search about transdermal delivery assisted by physical techniques has been carried out on Web of Science, EMBASE database, PubMed, Wanfang Database, China National Knowledge Infrastructure, and Cochrane Library. The search identified and retrieved the study describing multiple physical technologies to promote transdermal penetration.

RESULTS : Physical technologies, including microneedles, lasers, iontophoresis, sonophoresis, electroporation, magnetophoresis, and microwaves, are summarized and compared. The characteristics, mechanism, advantages and disadvantages of physical techniques are clarified. The individual or combined applicable examples of physical techniques to improve transdermal delivery are summarized.

CONCLUSION : This review will provide more useful guidance for efficient transdermal delivery. More therapeutic agents by transdermal routes become possible with the assistance of various physical techniques.

Gao Yan, Du Lina, Li Qian, Li Qi, Zhu Lin, Yang Meiyan, Wang Xiu, Zhao Bonian, Ma Shan

2022-Jul-01

In Advances in nutrition (Bethesda, Md.)

Gibbons Sean M, Gurry Thomas, Lampe Johanna W, Chakrabarti Anirikh, Dam Veerle, Everard Amandine, Goas Almudena, Gabriele Gross, Kleerebez Michiel, Lane Jonathan, Maukonen Johanna, Penna Ana Lucia Barretto, Pot Bruno, Valdes Ana M, Walton Gemma, Weiss Adrienne, Zanzer Yoghatama Cindya, Venlet Naomi V, Miani Michela

2022-Jul-01

diet, microbiome, microbiota, personalized healthcare, personalized nutrition, prebiotic, precision healthcare, precision nutrition, probiotic

In The Journal of physiology ; h5-index 67.0

Ibáñez Jaime, Zicher Blanka, Brown Katlyn E, Rocchi Lorenzo, Casolo Andrea, Del Vecchio Alessandro, Spampinato Danny, Vollette Carole-Anne, Rothwell John C, Baker Stuart N, Farina Dario

2022-Jul-01

electromyography, motor neurons, movement, neuromodulation, transcranial alternating current stimulation

In IEEE journal of biomedical and health informatics

Liu Min, Hu Lanlan, Tang Ying, Wang Chu, He Yu, Zeng Chunyan, Lin Kun, He Zhizi, Huo Wujie

2022-Jul-01

In IEEE transactions on bio-medical engineering

Zhu Taiyu, Li Kezhi, Herrero Pau, Georgiou Pantelis

2022-Jul-01

In IEEE transactions on bio-medical engineering

OBJECTIVE : Epileptogenic zone (EZ) localization is a crucial step during diagnostic work up and therapeutic planning in medication refractory epilepsy. In this paper, we present the first deep learning approach to localize the EZ based on resting-state fMRI (rs-fMRI) data.

METHODS : Our network, called DeepEZ, uses a cascade of graph convolutions that emphasize signal propagation along expected anatomical pathways. We also integrate domain-specific information, such as an asymmetry term on the predicted EZ and a learned subject-specific bias to mitigate environmental confounds.

RESULTS : We validate DeepEZ on rs-fMRI collected from 14 patients with focal epilepsy at the University of Wisconsin Madison. Using cross validation, we demonstrate that DeepEZ achieves consistently high EZ localization performance (Accuracy: 0.88 ± 0.03; AUC: 0.73 ± 0.03) that far outstripped any of the baseline methods. This performance is notable given the variability in EZ locations and scanner type across the cohort.

CONCLUSION : Our results highlight the promise of using DeepEZ as an accurate and noninvasive therapeutic planning tool for medication refractory epilepsy.

SIGNIFICANCE : While prior work in EZ localization focused on identifying localized aberrant signatures, there is growing evidence that epileptic seizures affect inter-regional connectivity in the brain. DeepEZ allows clinicians to harness this information from noninvasive imaging that can easily be integrated into the existing clinical workflow.

Nandakumar Naresh, Hsu David, Ahmed Raheel, Venkataraman Archana

2022-Jul-01

In Computational intelligence and neuroscience

Jia Xiaoguang

2022

In Computational intelligence and neuroscience

Fu Jianru, Zhou Xu, Mei Guoping

2022

In Briefings in bioinformatics

Kurata Hiroyuki, Tsukiyama Sho, Manavalan Balachandran

2022-Jul-01

anti-coronavirus peptide, bioinformatics, deep learning, random forest, transformer, word2vec

In Environmental science & technology ; h5-index 132.0

Xiong Rui, Zheng Yi, Chen Nengwang, Tian Qing, Liu Wei, Han Feng, Jiang Shijie, Lu Mengqian, Zheng Yan

2022-Jun-30

LSTM, artificial intelligence, deep learning, nitrogen, nonpoint sources, riverine export, transfer learning

In Magnetic resonance imaging

PURPOSE : Free-breathing Magnetization Transfer Contrast Bright blOOd phase SensiTive (MTC-BOOST) is a prototype balanced-Steady-State Free Precession sequence for 3D whole-heart imaging, that employs the endogenous magnetisation transfer contrast mechanism. This achieves reduction of flow and off-resonance artefacts, that often arise with the clinical T2prepared balanced-Steady-State Free Precession sequence, enabling high quality, contrast-agent free imaging of the thoracic cardiovascular anatomy. Fully-sampled MTC-BOOST acquisition requires long scan times (~10-24 min) and therefore acceleration is needed to permit its clinical incorporation. The aim of this study is to enable and clinically validate the 5-fold accelerated MTC-BOOST acquisition with joint Multi-Scale Variational Neural Network (jMS-VNN) reconstruction.

METHODS : Thirty-six patients underwent free-breathing, 3D whole-heart imaging with the MTC-BOOST sequence, which is combined with variable density spiral-like Cartesian sampling and 2D image navigators for translational motion estimation. This sequence acquires two differently weighted bright-blood volumes in an interleaved fashion, which are then joined in a phase sensitive inversion recovery reconstruction to obtain a complementary fully co-registered black-blood volume. Data from eighteen patients were used for training, whereas data from the remaining eighteen patients were used for testing/evaluation. The proposed deep-learning based approach adopts a supervised multi-scale variational neural network for joint reconstruction of the two differently weighted bright-blood volumes acquired with the 5-fold accelerated MTC-BOOST. The two contrast images are stacked as different channels in the network to exploit the shared information. The proposed approach is compared to the fully-sampled MTC-BOOST and 5-fold undersampled MTC-BOOST acquisition with Compressed Sensing (CS) reconstruction in terms of scan/reconstruction time and bright-blood image quality. Comparison against conventional 2-fold undersampled T2-prepared 3D bright-blood whole-heart clinical sequence (T2prep-3DWH) is also included.

RESULTS : Acquisition time was 3.0 ± 1.0 min for the 5-fold accelerated MTC-BOOST versus 9.0 ± 1.1 min for the fully-sampled MTC-BOOST and 11.1 ± 2.6 min for the T2prep-3DWH (p < 0.001 and p < 0.001, respectively). Reconstruction time was significantly lower with the jMS-VNN method compared to CS (10 ± 0.5 min vs 20 ± 2 s, p < 0.001). Image quality was higher for the proposed 5-fold undersampled jMS-VNN versus conventional CS, comparable or higher to the corresponding T2prep-3DWH dataset and similar to the fully-sampled MTC-BOOST.

CONCLUSION : The proposed 5-fold accelerated jMS-VNN MTC-BOOST framework provides efficient 3D whole-heart bright-blood imaging in fast acquisition and reconstruction time with concomitant reduction of flow and off-resonance artefacts, that are frequently encountered with the clinical sequence. Image quality of the cardiac anatomy and thoracic vasculature is comparable or superior to the clinical scan and 5-fold CS reconstruction in faster reconstruction time, promising potential clinical adoption.

Fotaki Anastasia, Fuin Niccolo, Nordio Giovanna, Jimeno Carlos Velasco, Qi Haikun, Emmanuel Yaso, Pushparajah Kuberan, Botnar René M, Prieto Claudia

2022-Jun-27

3D whole-heart imaging, Cardiac MRI, Free-breathing, Neural network

In Magnetic resonance imaging

PURPOSE : To assess the possibility of reducing the image acquisition time for diffusion-weighted whole-body imaging with background body signal suppression (DWIBS) by denoising with deep learning-based reconstruction (dDLR).

METHODS : Seventeen patients with prostate cancer who underwent DWIBS by 1.5 T magnetic resonance imaging with a number of excitations of 2 (NEX2) and 8 (NEX8) were prospectively enrolled. The NEX2 image data were processed by dDLR (dDLR-NEX2), and the NEX2, dDLR-NEX2, and NEX8 image data were analyzed. In qualitative analysis, two radiologists rated the perceived coarseness, conspicuity of metastatic lesions (lymph nodes and bone), and overall image quality. The contrast-to-noise ratios (CNRs), contrast ratios, and mean apparent diffusion coefficients (ADCs) of metastatic lesions were calculated in a quantitative analysis.

RESULTS : The image acquisition time of NEX2 was 2.8 times shorter than that of NEX8 (3 min 30 s vs 9 min 48 s). The perceived coarseness and overall image quality scores reported by both readers were significantly higher for dDLR-NEX2 than for NEX2 (P = 0.005-0.040). There was no significant difference between dDLR-NEX2 and NEX8 in the qualitative analysis. The CNR of bone metastasis was significantly greater for dDLR-NEX2 than for NEX2 and NEX8 (P = 0.012 for both comparisons). The contrast ratios and mean ADCs were not significantly different among the three image types.

CONCLUSIONS : dDLR improved the image quality of DWIBS with NEX2. In the context of lymph node and bone metastasis evaluation with DWIBS in patients with prostate cancer, dDLR-NEX2 has potential to be an alternative to NEX8 and reduce the image acquisition time.

Tajima Taku, Akai Hiroyuki, Sugawara Haruto, Furuta Toshihiro, Yasaka Koichiro, Kunimatsu Akira, Yoshioka Naoki, Akahane Masaaki, Abe Osamu, Ohtomo Kuni, Kiryu Shigeru

2022-Jun-27

DWIBS, Deep learning, Denoise, Fast MRI, Prostate cancer, Whole-body MRI

In Computational intelligence and neuroscience

Ramezani Majid, Feizi-Derakhshi Mohammad-Reza, Balafar Mohammad-Ali

2022

In The Science of the total environment

Shu Zhangkang, Zhou You, Zhang Jianyun, Jin Junliang, Wang Lin, Cui Ningbo, Wang Guoqing, Zhang Jiangjiang, Wu Houfa, Wu Zongjun, Chen Xi

2022-Jun-27

Data deficient regions, Empirical model, Machine learning, Reference evapotranspiration, Regionalization

In Computers in biology and medicine

BACKGROUND AND OBJECTIVE : Cardiac segmentation of atriums, ventricles, and myocardium in computed tomography (CT) images is an important first-line task for presymptomatic cardiovascular disease diagnosis. In several recent studies, deep learning models have shown significant breakthroughs in medical image segmentation tasks. Unlike other organs such as the lungs and liver, the cardiac organ consists of multiple substructures, i.e., ventricles, atriums, aortas, arteries, veins, and myocardium. These cardiac substructures are proximate to each other and have indiscernible boundaries (i.e., homogeneous intensity values), making it difficult for the segmentation network focus on the boundaries between the substructures.

METHODS : In this paper, to improve the segmentation accuracy between proximate organs, we introduce a novel model to exploit shape and boundary-aware features. We primarily propose a shape-aware attention module, that exploits distance regression, which can guide the model to focus on the edges between substructures so that it can outperform the conventional contour-based attention method.

RESULTS : In the experiments, we used the Multi-Modality Whole Heart Segmentation dataset that has 20 CT cardiac images for training and validation, and 40 CT cardiac images for testing. The experimental results show that the proposed network produces more accurate results than state-of-the-art networks by improving the Dice similarity coefficient score by 4.97%.

CONCLUSION : Our proposed shape-aware contour attention mechanism demonstrates that distance transformation and boundary features improve the actual attention map to strengthen the responses in the boundary area. Moreover, our proposed method significantly reduces the false-positive responses of the final output, resulting in accurate segmentation.

Park Sanguk, Chung Minyoung

2022-Jun-21

Cardiac CT segmentation, Contour attention map, Distance transform-based segmentation, Shape-aware contour attention

In Computers in biology and medicine

Ali Syed Danish, Tayara Hilal, Chong Kil To

2022-Jun-21

Arginine methylation, Cross-validation, Machine learning, Two-step feature selection

In Medical image analysis

Aly Ahmed H, Khandelwal Pulkit, Aly Abdullah H, Kawashima Takayuki, Mori Kazuki, Saito Yoshiaki, Hung Judy, Gorman Joseph H, Pouch Alison M, Gorman Robert C, Yushkevich Paul A

2022-Jun-12

3D transesophageal echocardiography, Deep learning, Diffeomorphic medial modeling, Ischemic mitral regurgitation

In Journal of environmental management

Chandra Pal Subodh, Towfiqul Islam Abu Reza Md, Chakrabortty Rabin, Islam Md Saiful, Saha Asish, Shit Manisa

2022-Jun-27

Groundwater development, Indo-gangetic plain, Machine learning, Vulnerability, Water resource

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVE : Preoperative imaging diagnosis of axillary lymph node (ALN) metastasis is particularly important for breast cancer patients. This paper focuses on developing non-invasive and automatic schemes for accurate localization and classification (metastasis prediction) of ALN via contrast-enhanced computed tomography (CECT) image and deep learning models.

METHODS : Based on a two-stage strategy, a novel detection neural network is proposed, where the convolutional block attention module is utilized to extract spacial information and the bottleneck feature fusion module is designed for feature fusion in different scales.

RESULTS : Owing to the two embedded modules, the proposed convolutional neural network (CNN) model outperforms Faster R-CNN, YOLOv3, and EfficientDet in the sense that the achieved mAP is 0.454, higher than 0.247, 0.335, and 0.329, respectively. In particular, considering the function of classification only, the proposed model reaches the best performance on most indices (accuracy of 0.968, positive predictive value of 0.972, negative predictive value of 0.966, specificity of 0.983), compared with the methods that have been frequently adopted to predict ALN. In addition, the proposed CNN model has the function of locating ALN, which is lacking in existing models.

CONCLUSIONS : In this paper, a supervised deep learning method is proposed to detect ALN in CECT images. The positive effect of new added modules are verified, and the benefits of spatial information in ALN detection are confirmed. Further, the two subtasks called localization and classification are evaluated separately, where the proposed model achieves the best performance on most indices. The source code mentioned in this article will be released later.

Liu Ziyi, Huang Deqing, Yang Chunmei, Shu Jian, Li Jinhan, Qin Na

2022-Jun-14

Axillary lymph node metastasis, CECT image, Convolutional neural network, Lesion location

In Computer methods and programs in biomedicine

BACKGROUND AND OBJECTIVE : Incomplete Kawasaki disease (KD) has often been misdiagnosed due to a lack of the clinical manifestations of classic KD. However, it is associated with a markedly higher prevalence of coronary artery lesions. Identifying coronary artery lesions by echocardiography is important for the timely diagnosis of and favorable outcomes in KD. Moreover, similar to KD, coronavirus disease 2019, currently causing a worldwide pandemic, also manifests with fever; therefore, it is crucial at this moment that KD should be distinguished clearly among the febrile diseases in children. In this study, we aimed to validate a deep learning algorithm for classification of KD and other acute febrile diseases.

METHODS : We obtained coronary artery images by echocardiography of children (n = 138 for KD; n = 65 for pneumonia). We trained six deep learning networks (VGG19, Xception, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) using the collected data.

RESULTS : SE-ResNext50 showed the best performance in terms of accuracy, specificity, and precision in the classification. SE-ResNext50 offered a precision of 81.12%, a sensitivity of 84.06%, and a specificity of 58.46%.

CONCLUSIONS : The results of our study suggested that deep learning algorithms have similar performance to an experienced cardiologist in detecting coronary artery lesions to facilitate the diagnosis of KD.

Lee Haeyun, Eun Yongsoon, Hwang Jae Youn, Eun Lucy Youngmin

2022-Jun-21

Coronary artery lesion, Deep learning, Explanable AI, Kawasaki disease, Ultrasound Image

In Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology

OBJECTIVE : Although fasciculation on muscle ultrasonography (MUS) is useful in diagnosing amyotrophic lateral sclerosis (ALS), its applicability to early diagnosis remains unclear. We aimed to develop and validate diagnostic models especially beneficial to early-stage ALS via machine learning.

METHODS : We investigated 100 patients with ALS, including 50 with early-stage ALS within 9 months from onset, and 100 without ALS. Fifteen muscles were bilaterally observed for 10 s each and the presence of fasciculations was recorded. Hierarchical clustering and nominal logistic regression, neural network, or ensemble learning were applied to the training cohort comprising the early-stage ALS to develop MUS-based diagnostic models, and they were tested in the validation cohort comprising the later-stage ALS.

RESULTS : Fasciculations on MUS in the brainstem or thoracic region had high specificity but limited sensitivities and predictive profiles for diagnosis of ALS. A machine learning-based model comprising eight muscles in the four body regions had a high sensitivity (recall), specificity, and positive predictive value (precision) for both early- and later-stage ALS patients.

CONCLUSIONS : We developed and validated MUS-fasciculation-based diagnostic models for early- and later-stage ALS.

SIGNIFICANCE : Fasciculation detected in relevant muscles on MUS can contribute to the diagnosis of ALS from the early stage.

Fukushima Koji, Takamatsu Naoko, Yamamoto Yuki, Yamazaki Hiroki, Yoshida Takeshi, Osaki Yusuke, Haji Shotaro, Fujita Koji, Sugie Kazuma, Izumi Yuishin

2022-Jun-17

Amyotrophic lateral sclerosis, Early diagnosis, Fasciculation, Machine learning, Muscle ultrasonography

In Asia-Pacific journal of ophthalmology (Philadelphia, Pa.)

PURPOSE : Artificial intelligence (AI) technology is poised to revolutionize modern delivery of health care services. We set to evaluate the patient perspective of AI use in diabetic retinal screening.

DESIGN : Survey.

METHODS : Four hundred thirty-eight patients undergoing diabetic retinal screening across New Zealand participated in a survey about their opinion of AI technology in retinal screening. The survey consisted of 13 questions covering topics of awareness, trust, and receptivity toward AI systems.

RESULTS : The mean age was 59 years. The majority of participants identified as New Zealand European (50%), followed by Asian (31%), Pacific Islander (10%), and Maori (5%). Whilst 73% of participants were aware of AI, only 58% have heard of it being implemented in health care. Overall, 78% of respondents were comfortable with AI use in their care, with 53% saying they would trust an AI-assisted screening program as much as a health professional. Despite having a higher awareness of AI, younger participants had lower trust in AI systems. A higher proportion of Maori and Pacific participants indicated a preference toward human-led screening. The main perceived benefits of AI included faster diagnostic speeds and greater accuracy.

CONCLUSIONS : There is low awareness of clinical AI applications among our participants. Despite this, most are receptive toward the implementation of AI in diabetic eye screening. Overall, there was a strong preference toward continual involvement of clinicians in the screening process. There are key recommendations to enhance the receptivity of the public toward incorporation of AI into retinal screening programs.

Yap Aaron, Wilkinson Benjamin, Chen Eileen, Han Lydia, Vaghefi Ehsan, Galloway Chris, Squirrell David

2022-May-01

In Asia-Pacific journal of ophthalmology (Philadelphia, Pa.)

Tan Ting Fang, Li Yong, Lim Jane Sujuan, Gunasekeran Dinesh Visva, Teo Zhen Ling, Ng Wei Yan, Ting Daniel Sw

2022-May-01

In Computational intelligence and neuroscience

Luo Hui, Zeng Qiang

2022

In PloS one ; h5-index 176.0

Oliveira Fabio F de, Dias Leonardo A, Fernandes Marcelo A C

2022

In The Journal of physiology ; h5-index 67.0

KEY POINTS : A central and unresolved question is how spinal motor neurons are controlled to generate movement; We decoded the spiking activities of dozens of spinal motor neurons innervating six muscles during a multi-joint task, and we used a purely data-driven method grounded on graph theory to extract networks of motor neurons based on their correlated activity (considered as common input); The vast majority of the identified motor neurons shared common inputs with other motor neuron(s); Groups of motor neurons were partly decoupled from their innervated muscle, such that motor neurons innervating the same muscle did not necessarily receive common inputs. Conversely, some motor neurons from different muscles - including distant muscles - received common inputs. It supports the theory that movement is produced through the control of groups of motor neurons via common inputs and that there is a partial mismatch between these groups of motor neurons and muscle anatomy.

ABSTRACT : Movements are reportedly controlled through the combination of synergies that generate specific motor outputs by imposing an activation pattern on a group of muscles. To date, the smallest unit of analysis of these synergies has been the muscle through the measurement of its activation. However, the muscle is not the lowest neural level of movement control. In this human study (n = 10), we used a purely data-driven method grounded on graph theory to extract networks of motor neurons based on their correlated activity during an isometric multi-joint task. Specifically, high-density surface electromyography recordings from six lower limb muscles were decomposed into motor neurons spiking activity. We analyzed these activities by identifying their common low-frequency components, from which networks of correlated activity to the motor neurons were derived and interpreted as networks of common synaptic inputs. The vast majority of the identified motor neurons shared common inputs with other motor neuron(s). In addition, groups of motor neurons were partly decoupled from their innervated muscle, such that motor neurons innervating the same muscle did not necessarily receive common inputs. Conversely, some motor neurons from different muscles - including distant muscles - received common inputs. Our study supports the theory that movements are produced through the control of small numbers of groups of motor neurons via common inputs and that there is a partial mismatch between these groups of motor neurons and muscle anatomy. We provide a new neural framework for a deeper understanding of the structure of common inputs to motor neurons. Abstract figure legend Ten participants performed an isometric multi-joint task, which consisted in producing force on an instrumented pedal. Adhesive grids of 64 electrodes were placed over six lower limb muscles (gastrocnemius medialis [GM] and lateralis [GL], vastus lateralis [VL] and medialis [VM], biceps femoris [BF], semitendinosus [ST]). The high-density EMG signals were decomposed into motor unit spike trains. For each pair of motor neurons, we assessed the correlation between their smoothed discharge rates to determine whether they shared common input. Then, we used a purely data-driven method grounded on graph theory to extract networks of common inputs and we applied a clustering procedure to group the motor neurons according to their positions in the graph (i.e., their correlated activity). Results support the theory that movement is produced through the control of small numbers of groups of motor neurons via common inputs and that there is a partial mismatch between these groups of motor neurons and muscle anatomy. This article is protected by copyright. All rights reserved.

Hug François, Avrillon Simon, Sarcher Aurélie, Del Vecchio Alessandro, Farina Dario

2022-Jun-30

coherence, common drive, common input, electromyography, motor units, muscle synergies

In Biopreservation and biobanking

Rahimzadeh Vasiliki, Lawson Jonathan, Rushton Greg, Dove Edward S

2022-Jun-30

automated decision system, data access committee, ethics, genomics, health

In JMIR research protocols ; h5-index 26.0

BACKGROUND : The French organized population-based cervical cancer screening (CCS) programme shifted from a cytology-based to a human papillomavirus (HPV)-based screening strategy in August 2020. HPV testing is offered every 5 years, starting at age 30 years. In the new programme, women are invited to have the HPV test at a gynaecologist's, primary care physician's, or midwife's office, a private clinic or health centre, family planning centre, or hospital. HPV self-sampling (HPVss) was also made available as an additional approach. However, French studies reported that less than 20% of non-compliant women performed vaginal self-sampling when a kit was sent to their home. Women with lower income and educational levels participate less in CCS. Lack of information about the disease and the benefits of CCS was reported as one of the major barriers among non-compliant women. This barrier could be addressed by overcoming disparities in HPV- and CC-related knowledge and perceptions about CCS.

OBJECTIVE : The main objective of this study is to assess the effectiveness of a chatbot-based decision aid to improve women's participation in the HPVss detection-based CCS care pathway.

METHODS : AppDate-You is a two-arm cluster randomized controlled trial (cRCT) nested within the French organized CCS programme. Eligible women are those aged 30-65 years who have not been screened for CC for more than 4 years and live in the disadvantaged clusters in the Occitanie Region, France. Thirty-two clusters will be allocated to the intervention and control arms, 16 in each arm (approximately 4000 women). Eligible women living in randomly selected disadvantaged clusters will be identified using the Regional Cancer Screening Coordinating Centre of Occitanie (CRCDC-OC) database. Women in the experimental group will receive screening reminder letters and HPVss kits, combined with access to a chatbot-based decision aid tailored to women with lower educational attainment. Women in the control group will receive the reminder letters and HPVss kits (standard of care). The CRCDC-OC database will be used to check the progress of the trial and assess the impact of the intervention. The trial has two primary outcomes: 1) the proportion of screening participation within 12 months among women recalled for CCS, and 2) the proportion of HPVss-positive women who are "well-managed" as stipulated in the French guidelines.

RESULTS : To date, the AppDate-You study group is preparing and developing the chatbot-based decision aid (intervention). The cRCT will be conducted once the decision aid has been completed and validated. Recruitment of women is expected to begin in January 2023.

CONCLUSIONS : This study is the first to evaluate the impact of a chatbot-based decision aid to promote the CCS programme and increase its performance. The study results will inform policy-makers and health professionals as well as the research community.

CLINICALTRIAL : The study was registered on clinicaltrials.gov: NCT05286034, on March 18, 2022.

Selmouni Farida, Guy Marine, Muwonge Richard, Nassiri Abdelhak, Lucas Eric, Basu Partha, Sauvaget Catherine

2022-Jun-03

In PloS one ; h5-index 176.0

Herbuela Von Ralph Dane Marquez, Karita Tomonori, Furukawa Yoshiya, Wada Yoshinori, Toya Akihiro, Senba Shuichiro, Onishi Eiko, Saeki Tatsuo

2022

In IEEE transactions on neural networks and learning systems

Atto Abdourrahmane Mahamane

2022-Jun-30

In IEEE transactions on neural networks and learning systems

Wei Susan, Murfet Daniel, Gong Mingming, Li Hui, Gell-Redman Jesse, Quella Thomas

2022-Jun-30

In IEEE transactions on neural networks and learning systems

Dai Ben, Shen Xiaotong, Pan Wei

2022-Jun-30

In PLoS neglected tropical diseases ; h5-index 79.0

BACKGROUND AND OBJECTIVE : Differentiating tropical infections are difficult due to its homogenous nature of clinical and laboratorial presentations among them. Sophisticated differential tests and prediction tools are better ways to tackle this issue. Here, we aimed to develop a clinician assisted decision making tool to differentiate the common tropical infections.

METHODOLOGY : A cross sectional study through 9 item self-administered questionnaire were performed to understand the need of developing a decision making tool and its parameters. The most significant differential parameters among the identified infections were measured through a retrospective study and decision tree was developed. Based on the parameters identified, a multinomial logistic regression model and a machine learning model were developed which could better differentiate the infection.

RESULTS : A total of 40 physicians involved in the management of tropical infections were included for need analysis. Dengue, malaria, leptospirosis and scrub typhus were the common tropical infections in our settings. Sodium, total bilirubin, albumin, lymphocytes and platelets were the laboratory parameters; and abdominal pain, arthralgia, myalgia and urine output were the clinical presentation identified as better predictors. In multinomial logistic regression analysis with dengue as a reference revealed a predictability of 60.7%, 62.5% and 66% for dengue, malaria and leptospirosis, respectively, whereas, scrub typhus showed only 38% of predictability. The multi classification machine learning model observed to have an overall predictability of 55-60%, whereas a binary classification machine learning algorithms showed an average of 79-84% for one vs other and 69-88% for one vs one disease category.

CONCLUSION : This is a first of its kind study where both statistical and machine learning approaches were explored simultaneously for differentiating tropical infections. Machine learning techniques in healthcare sectors will aid in early detection and better patient care.

Shenoy Shreelaxmi, Rajan Asha K, Rashid Muhammed, Chandran Viji Pulikkel, Poojari Pooja Gopal, Kunhikatta Vijayanarayana, Acharya Dinesh, Nair Sreedharan, Varma Muralidhar, Thunga Girish

2022-Jun

In PloS one ; h5-index 176.0

Krieg Steven J, Smith Christian W, Chatterjee Rusha, Chawla Nitesh V

2022

In Digital discovery

Guo Kai, Buehler Markus J

2022-Jun-13

ArXiv Preprint

Sanat Ramesh, Vinkle Srivastav, Deepak Alapatt, Tong Yu, Aditya Murali, Luca Sestini, Chinedu Innocent Nwoye, Idris Hamoud, Antoine Fleurentin, Georgios Exarchakis, Alexandros Karargyris, Nicolas Padoy

2022-07-01

In Clinical chemistry and laboratory medicine ; h5-index 46.0

Pei Qin, Luo Yanan, Chen Yiyu, Li Jingyuan, Xie Dan, Ye Ting

2022-Jun-30

artificial intelligence, diagnosis, lung cancer, prognosis, treatment

In Journal of magnetic resonance imaging : JMRI

BACKGROUND : Noninvasive detection of TP53 mutations is useful for the molecular stratification of breast cancer.

PURPOSE : To explore MRI radiomics features reflecting TP53 mutations in breast cancer and propose a classifier for detecting such mutations.

STUDY TYPE : Retrospective.

POPULATION/SUBJECTS : A total of 139 breast cancer patients with TP53 expression profiling (98 with TP53 mutations and 41 without TP53 mutations).

FIELD STRENGTH/SEQUENCE : 1.5 T, T1-weighted (T1W) DCE-MRI.

ASSESSMENT : Lesions were manually segmented using subtracted T1WI. A total of 944 radiomics features (including 744 wavelet-related features) and 7 clinicopathological features were extracted from each lesion. Principal component analysis and Pearson's correlation analysis were used to preprocess the features. Linear discriminant analysis, logistic regression (LR), support vector machine (SVM), and random forest (RF) were used as the classifiers.

STATISTICAL TESTS : Analysis of variance, Kruskal-Wallis and recursive features elimination were used to select features. Receiver operating characteristic (ROC) analysis was performed to compare the diagnostic accuracy.

RESULTS : For the radiomics model, the validation cohorts AUCs of the four classifiers ranged from 0.69 (RF) to 0.74 (LR), and LR (0.74) attained the highest AUCs. For the clinicopathological-radiomics combined model, the validation AUCs of the four classifiers ranged from 0.68 (RF) to 0.86 (SVM), and SVM (0.86) attained highest AUCs. In the subgroup analysis of triple-negative (TN) and luminal type breast cancer, RF achieved the highest AUCs (0.83 and 0.94).

DATA CONCLUSION : Clinicopathological-radiomics combined model with SVM could be used as noninvasive biomarkers for predicting TP53 mutations. RF was recommended for the detection of TP53 mutations in TN and luminal type breast cancer.

LEVEL OF EVIDENCE : 3 TECHNICAL EFFICACY: Stage 2.

Sun Kun, Zhu Hong, Chai Weimin, Yan Fuhua

2022-Jun-30

breast cancer, machine learning, radiomics

In Clinical chemistry ; h5-index 61.0

BACKGROUND : Cell-free DNA (cfDNA) is emerging as a biomarker for sepsis. Previous studies have been focused mainly on identifying blood infections or simply quantifying cfDNA. We propose that by characterizing multifaceted unexplored components, cfDNA could be more informative for assessing this complex syndrome.

METHODS : We explored multiple aspects of cfDNA in septic and nonseptic intensive care unit (ICU) patients by metagenomic sequencing, with longitudinal measurement and integrative assessment of plasma cfDNA quantity, human cfDNA fragmentation patterns, infecting pathogens, and overall microbial composition.

RESULTS : Septic patients had significantly increased cfDNA quantity and altered human cfDNA fragmentation pattern. Moreover, human cfDNA fragments appeared to comprise information about cellular oxidative stress and could indicate disease severity. Metagenomic sequencing was more sensitive than blood culture in detecting bacterial infections and allowed for simultaneous detection of viral pathogens. We found differences in microbial composition between septic and nonseptic patients and between survivors and nonsurvivors by 28-day mortality, both on the first day of ICU admission and across the study period. By integrating all the information into a machine learning model, we achieved improved performance in identifying sepsis and prediction of clinical outcome for ICU patients with areas under the curve of 0.992 (95% CI 0.969-1.000) and 0.802 (95% CI 0.605-0.999), respectively.

CONCLUSIONS : We were able to diagnose sepsis and predict mortality as soon as the first day of ICU admission by integrating multifaceted cfDNA information obtained in a single metagenomic assay; this approach could provide important advantages for clinical management and for improving outcomes in ICU patients.

Jing Qiuyu, Leung Chi Hung Czarina, Wu Angela Ruohao

2022-Jun-30

biomarker, cell-free DNA, diagnosis, metagenomics, prognosis, sepsis

In Bioinformatics (Oxford, England)

MOTIVATION : Characterization of protein subcellular localization has become an important and long-standing task in bioinformatics and computational biology, which provides valuable information for elucidating various cellular functions of proteins and guiding drug design.

RESULTS : Here, we develop a novel bioimage-based computational approach, termed PScL-DDCFPred, to accurately predict protein subcellular localizations in human tissues. PScL-DDCFPred first extracts multiview image features, including global and local features, as base or pure features; Next, it applies a new integrative feature selection method based on stepwise discriminant analysis and generalized discriminant analysis to identify the optimal feature sets from the extracted pure features; Finally, a classifier based on deep neural network (DNN) and deep-cascade forest (DCF) is established. Stringent ten-fold cross-validation tests on the new protein subcellular localization training dataset, constructed from the human protein atlas databank, illustrates that PScL-DDCFPred achieves a better performance than several existing state-of-the-art methods. Moreover, the independent test set further illustrates the generalization capability and superiority of PScL-DDCFPred over existing predictors. In-depth analysis shows that the excellent performance of PScL-DDCFPred can be attributed to three critical factors, namely the effective combination of the DNN and DCF models, complementarity of global and local features, and use of the optimal feature sets selected by the integrative feature selection algorithm.

AVAILABILITY : https://github.com/csbio-njust-edu/PScL-DDCFPred.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Ullah Matee, Hadi Fazal, Song Jiangning, Yu Dong-Jun

2022-Jun-30

In Bioinformatics (Oxford, England)

MOTIVATION : With the advancement of technology, we can generate and access large-scale, high dimensional and diverse genomics data, especially through single-cell RNA sequencing (scRNA-seq). However, integrative downstream analysis from multiple scRNA-seq datasets remains challenging due to batch effects.

RESULTS : In this paper, we propose a light-structured deep learning framework called ResPAN for scRNA-seq data integration. ResPAN is based on Wasserstein Generative Adversarial Network (WGAN) combined with random walk mutual nearest neighbor pairing and fully skip-connected autoencoders to reduce the differences among batches. We also discuss the limitations of existing methods and demonstrate the advantages of our model over seven other methods through extensive benchmarking studies on both simulated data under various scenarios and real datasets across different scales. Our model achieves leading performance on both batch correction and biological information conservation and maintains scalable to datasets with over half a million cells.

AVAILABILITY : An open-source implementation of ResPAN and scripts to reproduce the results can be downloaded from: https://github.com/AprilYuge/ResPAN.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Wang Yuge, Liu Tianyu, Zhao Hongyu

2022-Jun-30

In Bioinformatics (Oxford, England)

MOTIVATION : Computational methods for the prediction of protein-protein interactions, while important tools for researchers, are plagued by challenges in generalising to unseen proteins. Datasets used for modelling protein-protein predictions are particularly predisposed to information leakage and sampling biases.

RESULTS : In this study, we introduce RAPPPID, a method for the Regularised Automatic Prediction of Protein-Protein Interactions using Deep Learning. RAPPPID is a twin AWD-LSTM network which employs multiple regularisation methods during training time to learn generalised weights. Testing on stringent interaction datasets composed of proteins not seen during training, RAPPPID outperforms state-of-the-art methods. Further experiments show that RAPPPID's performance holds regardless of the particular proteins in the testing set and its performance is higher for experimentally supported edges. This study serves to demonstrate that appropriate regularisation is an important component of overcoming the challenges of creating models for protein-protein interaction prediction that generalise to unseen proteins. Additionally, as part of this study, we provide datasets corresponding to several data splits of various strictness, in order to facilitate assessment of PPI reconstruction methods by others in the future.

AVAILABILITY : Code and datasets are freely available at https://github.com/jszym/rapppid and https://zenodo.org.

SUPPLEMENTARY INFORMATION : Supplementary data are available at Bioinformatics online.

Szymborski Joseph, Emad Amin

2022-Jun-30

In mAbs

Negron Christopher, Fang Joyce, McPherson Michael J, Stine W Blaine, McCluskey Andrew J

Developability, drug discovery, machine learning, repertoire antibodies, therapeutic antibodies

In JAMA otolaryngology-- head & neck surgery

Importance : Patient-reported symptom burden was recently found to be associated with emergency department use and unplanned hospitalization (ED/Hosp) in patients with head and neck cancer. It was hypothesized that symptom scores could be combined with administrative health data to accurately risk stratify patients.

Objective : To develop and validate a machine learning approach to predict future ED/Hosp in patients with head and neck cancer.

Design, Setting, and Participants : This was a population-based predictive modeling study of patients in Ontario, Canada, diagnosed with head and neck cancer from January 2007 through March 2018. All outpatient clinical encounters were identified. Edmonton Symptom Assessment System (ESAS) scores and clinical and demographic factors were abstracted. Training and test cohorts were randomly generated in a 4:1 ratio. Various machine learning algorithms were explored, including (1) logistic regression using a least absolute shrinkage and selection operator, (2) random forest, (3) gradient boosting machine, (4) k-nearest neighbors, and (5) an artificial neural network. Data analysis was performed from September 2021 to January 2022.

Main Outcomes and Measures : The main outcome was any 14-day ED/Hosp event following symptom assessment. The performance of each model was assessed on the test cohort using the area under the receiver operator characteristic (AUROC) curve and calibration plots. Shapley values were used to identify the variables with greatest contribution to the model.

Results : The training cohort consisted of 9409 patients (mean [SD] age, 63.3 [10.9] years) undergoing 59 089 symptom assessments (80%). The remaining 2352 patients (mean [SD] age, 63.3 [11] years) and 14 193 symptom assessments were set aside as the test cohort (20%). Several models had high predictive accuracy, particularly the gradient boosting machine (validation AUROC, 0.80 [95% CI, 0.78-0.81]). A Youden-based cutoff corresponded to a validation sensitivity of 0.77 and specificity of 0.66. Patient-reported symptom scores were consistently identified as being the most predictive features within models. A second model built only with symptom severity data had an AUROC of 0.72 (95% CI, 0.70-0.74).

Conclusions and Relevance : In this study, machine learning approaches predicted with a high degree of accuracy ED/Hosp in patients with head and neck cancer. These tools could be used to accurately risk stratify patients and may help direct targeted intervention.

Noel Christopher W, Sutradhar Rinku, Gotlib Conn Lesley, Forner David, Chan Wing C, Fu Rui, Hallet Julie, Coburn Natalie G, Eskander Antoine

2022-Jun-30

In Physical and engineering sciences in medicine

Bhattacharjee Ananya, Murugan R, Soni Badal, Goel Tripti

2022-Jun-30

Ada Boost, Computer-aided diagnosis, Grid search, Hyperparameter optimization, Lung cancer

In La Radiologia medica

Vicini Simone, Bortolotto Chandra, Rengo Marco, Ballerini Daniela, Bellini Davide, Carbone Iacopo, Preda Lorenzo, Laghi Andrea, Coppola Francesca, Faggioni Lorenzo

2022-Jun-30

Artificial intelligence, Cancer imaging, Deep learning, Machine learning, Oncology, Radiomics

In PeerJ

Routhier Etienne, Mozziconacci Julien

2022

Bioinformatics, Deep learning, Epigenomics, Genetics, Genomics, Metagenomics, Neural networks, Personalized medecine, Review, Synthetic genomes

ArXiv Preprint

Changgee Chang, Zhiqi Bu, Qi Long

2022-07-01

In European journal of nuclear medicine and molecular imaging ; h5-index 66.0

PURPOSE : Although treatment planning and individualized dose application for emerging prostate-specific membrane antigen (PSMA)-targeted radioligand therapy (RLT) are generally recommended, it is still difficult to implement in practice at the moment. In this study, we aimed to prove the concept of pretherapeutic prediction of dosimetry based on imaging and laboratory measurements before the RLT treatment.

METHODS : Twenty-three patients with metastatic castration-resistant prostate cancer (mCRPC) treated with ¹⁷⁷Lu-PSMA I&T RLT were included retrospectively. They had available pre-therapy ⁶⁸ Ga-PSMA-HEBD-CC PET/CT and at least 3 planar and 1 SPECT/CT imaging for dosimetry. Overall, 43 cycles of ¹⁷⁷Lu-PSMA I&T RLT were applied. Organ-based standard uptake values (SUVs) were obtained from pre-therapy PET/CT scans. Patient dosimetry was calculated for the kidney, liver, spleen, and salivary glands using Hermes Hybrid Dosimetry 4.0 from the planar and SPECT/CT images. Machine learning methods were explored for dose prediction from organ SUVs and laboratory measurements. The uncertainty of these dose predictions was compared with the population-based dosimetry estimates. Mean absolute percentage error (MAPE) was used to assess the prediction uncertainty of estimated dosimetry.

RESULTS : An optimal machine learning method achieved a dosimetry prediction MAPE of 15.8 ± 13.2% for the kidney, 29.6% ± 13.7% for the liver, 23.8% ± 13.1% for the salivary glands, and 32.1 ± 31.4% for the spleen. In contrast, the prediction based on literature population mean has significantly larger MAPE (p < 0.01), 25.5 ± 17.3% for the kidney, 139.1% ± 111.5% for the liver, 67.0 ± 58.3% for the salivary glands, and 54.1 ± 215.3% for the spleen.

CONCLUSION : The preliminary results confirmed the feasibility of pretherapeutic estimation of treatment dosimetry and its added value to empirical population-based estimation. The exploration of dose prediction may support the implementation of treatment planning for RLT.

Xue Song, Gafita Andrei, Dong Chao, Zhao Yu, Tetteh Giles, Menze Bjoern H, Ziegler Sibylle, Weber Wolfgang, Afshar-Oromieh Ali, Rominger Axel, Eiber Matthias, Shi Kuangyu

2022-Jun-30

177Lu-PSMA I&T, Dosimetry, Machine learning, Radioligand therapy, Treatment planning

In Journal of cancer research and clinical oncology

PURPOSE : To investigate the value of the combined diagnosis of multiparametric MRI-based deep learning models to differentiate triple-negative breast cancer (TNBC) from fibroadenoma magnetic resonance Breast Imaging-Reporting and Data System category 4 (BI-RADS 4) lesions and to evaluate whether the combined diagnosis of these models could improve the diagnostic performance of radiologists.

METHODS : A total of 319 female patients with 319 pathologically confirmed BI-RADS 4 lesions were randomly divided into training, validation, and testing sets in this retrospective study. The three models were established based on contrast-enhanced T1-weighted imaging, diffusion-weighted imaging, and T2-weighted imaging using the training and validation sets. The artificial intelligence (AI) combination score was calculated according to the results of three models. The diagnostic performances of four radiologists with and without AI assistance were compared with the AI combination score on the testing set. The area under the curve (AUC), sensitivity, specificity, accuracy, and weighted kappa value were calculated to assess the performance.

RESULTS : The AI combination score yielded an excellent performance (AUC = 0.944) on the testing set. With AI assistance, the AUC for the diagnosis of junior radiologist 1 (JR1) increased from 0.833 to 0.885, and that for JR2 increased from 0.823 to 0.876. The AUCs of senior radiologist 1 (SR1) and SR2 slightly increased from 0.901 and 0.950 to 0.925 and 0.975 after AI assistance, respectively.

CONCLUSION : Combined diagnosis of multiparametric MRI-based deep learning models to differentiate TNBC from fibroadenoma magnetic resonance BI-RADS 4 lesions can achieve comparable performance to that of SRs and improve the diagnostic performance of JRs.

Yin Hao-Lin, Jiang Yu, Xu Zihan, Jia Hui-Hui, Lin Guang-Wu

2022-Jun-30

Breast MRI, Breast cancer, Deep learning, Neural network, Triple-negative breast cancer

In European radiology ; h5-index 62.0

OBJECTIVE : The stratification of microsatellite instability (MSI) status assists clinicians in making treatment decisions for colorectal cancer (CRC) patients. This study aimed to establish a CT-based radiomics signature to predict MSI status in patients with CRC.

METHODS : A total of 837 CRC patients who underwent preoperative enhanced CT and had available MSI status data were recruited from two hospitals. Radiomics features were extracted from segmented tumours, and a series of data balancing and feature selection strategies were used to select MSI-related features. Finally, an MSI-related radiomics signature was constructed using a genetic algorithm-enhanced artificial neural network model. Combined and clinical models were constructed using multivariate logistic regression analyses by integrating the clinical factors with or without the signature. A Kaplan-Meier survival analysis was conducted to explore the prognostic information of the signature in patients with CRC.

RESULTS : Ten features were selected to construct a signature which showed robust performance in both the internal and external validation cohorts, with areas under the curves (AUC) of 0.788 and 0.775, respectively. The performance of the signature was comparable to that of the combined model (AUCs of 0.777 and 0.767, respectively) and it outperformed the clinical model constituting age and tumour location (AUCs of 0.768 and 0.623, respectively). Survival analysis demonstrated that the signature could stratify patients with stage II CRC according to prognosis (HR: 0.402, p = 0.029).

CONCLUSIONS : This study built a robust radiomics signature for identifying the MSI status of CRC patients, which may assist individualised treatment decisions.

KEY POINTS : • Our well-designed modelling strategies helped overcome the problem of data imbalance caused by the low incidence of MSI. • Genetic algorithm-enhanced artificial neural network-based CT radiomics signature can effectively distinguish the MSI status of CRC patients. • Kaplan-Meier survival analysis demonstrated that our signature could significantly stratify stage II CRC patients into high- and low-risk groups.

Chen Xiaobo, He Lan, Li Qingshu, Liu Liu, Li Suyun, Zhang Yuan, Liu Zaiyi, Huang Yanqi, Mao Yun, Chen Xin

2022-Jun-30

Colorectal neoplasms, Microsatellite instability, Neural networks, Survival analysis

In Journal of biomechanical engineering ; h5-index 32.0

Viguerie Alex, Grave Malú, Barros Gabriel F, Lorenzo Guillermo, Reali Alessandro, Coutinho Alvaro

2022-Jun-30

In Molecular imaging and radionuclide therapy

Objectives : This study aimed to evaluate the ability of ¹⁸fluorine-fluorodeoxyglucose (¹⁸F-FDG) positron emission tomography/computed tomography (PET/CT) radiomic features combined with machine learning methods to distinguish between benign and malignant solitary pulmonary nodules (SPN).

Methods : Data of 48 patients with SPN detected on ¹⁸F-FDG PET/CT scan were evaluated retrospectively. The texture feature extraction from PET/CT images was performed using an open-source application (LIFEx). Deep learning and classical machine learning algorithms were used to build the models. Final diagnosis was confirmed by pathology and follow-up was accepted as the reference. The performances of the models were assessed by the following metrics: Sensitivity, specificity, accuracy, and area under the receiver operator characteristic curve (AUC).

Results : The predictive models provided reasonable performance for the differential diagnosis of SPNs (AUCs ~0.81). The accuracy and AUC of the radiomic models were similar to the visual interpretation. However, when compared to the conventional evaluation, the sensitivity of the deep learning model (88% vs. 83%) and specificity of the classic learning model were higher (86% vs. 79%).

Conclusion : Machine learning based on ¹⁸F-FDG PET/CT texture features can contribute to the conventional evaluation to distinguish between benign and malignant lung nodules.

Salihoğlu Yavuz Sami, Uslu Erdemir Rabiye, Aydur Püren Büşra, Özdemir Semra, Uyulan Çağlar, Ergüzel Türker Tekin, Tekin Hüseyin Ozan

2022-Jun-27

PET/CT, Solitary pulmonary nodule, machine learning, radiomic

In Human brain mapping

Vallarino Elisabetta, Sommariva Sara, Famà Francesco, Piana Michele, Nobili Flavio, Arnaldi Dario

2022-Jun-30

clustering, machine learning, neurodegenerative diseases, power spectrum, quantitative EEG, transition frequency

In Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine

OBJECTIVES : To determine the feasibility of using a deep learning (DL) algorithm to assess the quality of focused assessment with sonography in trauma (FAST) exams.

METHODS : Our dataset consists of 441 FAST exams, classified as good-quality or poor-quality, with 3161 videos. We first used convolutional neural networks (CNNs), pretrained on the Imagenet dataset and fine-tuned on the FAST dataset. Second, we trained a CNN autoencoder to compress FAST images, with a 20-1 compression ratio. The compressed codes were input to a two-layer classifier network. To train the networks, each video was labeled with the quality of the exam, and the frames were labeled with the quality of the video. For inference, a video was classified as poor-quality if half the frames were classified as poor-quality by the network, and an exam was classified as poor-quality if half the videos were classified as poor-quality.

RESULTS : The results with the encoder-classifier networks were much better than the transfer learning results with CNNs. This was primarily because the Imagenet dataset is not a good match for the ultrasound quality assessment problem. The DL models produced video sensitivities and specificities of 99% and 98% on held-out test sets.

CONCLUSIONS : Using an autoencoder to compress FAST images is a very effective way to obtain features that can be used to predict exam quality. These features are more suitable than those obtained from CNNs pretrained on Imagenet.

Taye Mesfin, Morrow Dustin, Cull John, Smith Dane Hudson, Hagan Martin

2022-Jun-30

FAST, autoencoder, convolutional neural network, deep learning, ultrasound

In Medical physics ; h5-index 59.0

PURPOSE : Coronary computed tomographic angiography (CCTA) plays a vital role in the diagnosis of cardiovascular diseases, among which automatic coronary artery segmentation (CAS) serves as one of the most challenging tasks. To computationally assist the task, this paper proposes a novel end-to-end deep learning-based (DL) solution for automatic CAS.

METHODS : Inspired by the Di-Vnet network, a fully automatic multistage DL solution is proposed. The new solution aims to preserve the integrity of blood vessels in terms of both their shape details and continuity. The solution is developed using 338 CCTA cases, among which 133 cases (33865 axial images) have their ground-truth cardiac masks pre-annotated and 205 cases (53365 axial images) have their ground-truth coronary artery (CA) masks pre-annotated. The solution's accuracy is measured using dice similarity coefficient (DSC), 95th percentile Hausdorff Distance (95% HD), Recall, and Precision scores for CAS.

RESULTS : The proposed solution attains 90.29% in DSC, 2.11 mm in 95% HD, 97.02% in Recall, and 92.17% in Precision, respectively, which consumes 0.112 seconds per image and 30 seconds per case on average. Such performance of our method is superior to other state-of-the-art segmentation methods.

CONCLUSIONS : The novel DL solution is able to automatically learn to perform CAS in an end-to-end fashion, attaining a high accuracy, efficiency and robustness simultaneously. This article is protected by copyright. All rights reserved.

Dong Caixia, Xu Songhua, Li Zongfang

2022-Jun-30

blood vessel integrity, coronary artery segmentation, deep learning

In Soft matter

Vieira Luiz Fernando, Weinhofer Alexandra C, Oltjen William C, Yu Cindy, de Souza Mendes Paulo Roberto, Hore Michael J A

2022-Jun-30

In Revista espanola de enfermedades digestivas : organo oficial de la Sociedad Espanola de Patologia Digestiva

Ortiz Zúñiga Oswaldo, Fernández Esparrach María Glòria, Daca María, Pellisé María

2022-Jun-30

In Current research in structural biology

Tran-Nguyen Viet-Khoa, Simeon Saw, Junaid Muhammad, Ballester Pedro J

2022

ArXiv Preprint

Ignjat Pejic, Rui Wang, Kaitai Liang

2022-07-01

In Revista espanola de enfermedades digestivas : organo oficial de la Sociedad Espanola de Patologia Digestiva

Tejedor Marta, Herrero Antonio, Castresana Carlos, Mesón Raúl, Taracido Juan Carlos, Sánchez Marta, Delgado María

2022-Jun-30

In Molecular nutrition & food research ; h5-index 56.0

Holzapfel Christina, Waldenberger Melanie, Lorkowski Stefan, Daniel Hannelore

2022-Jun-29

Obesity, cardiovascular diseases, diabetes, methylation, single nucleotide polymorphism

In Turkish journal of ophthalmology

Objectives : To evaluate the performance of convolutional neural network (CNN) architectures to distinguish eyes with glaucoma from normal eyes.

Materials and Methods : A total of 9,950 fundus photographs of 5,388 patients from the database of Eskişehir Osmangazi University Faculty of Medicine Ophthalmology Clinic were labelled as glaucoma, glaucoma suspect, or normal by three different experienced ophthalmologists. The categorized fundus photographs were evaluated using a state-of-the-art two-dimensional CNN and compared with deep residual networks (ResNet) and very deep neural networks (VGG). The accuracy, sensitivity, and specificity of glaucoma detection with the different algorithms were evaluated using a dataset of 238 normal and 320 glaucomatous fundus photographs. For the detection of suspected glaucoma, ResNet-101 architectures were tested with a data set of 170 normal, 170 glaucoma, and 167 glaucoma-suspect fundus photographs.

Results : Accuracy, sensitivity, and specificity in detecting glaucoma were 96.2%, 99.5%, and 93.7% with ResNet-50; 97.4%, 97.8%, and 97.1% with ResNet-101; 98.9%, 100%, and 98.1% with VGG-19, and 99.4%, 100%, and 99% with the 2D CNN, respectively. Accuracy, sensitivity, and specificity values in distinguishing glaucoma suspects from normal eyes were 62%, 68%, and 56% and those for differentiating glaucoma from suspected glaucoma were 92%, 81%, and 97%, respectively. While 55 photographs could be evaluated in 2 seconds with CNN, a clinician spent an average of 24.2 seconds to evaluate a single photograph.

Conclusion : An appropriately designed and trained CNN was able to distinguish glaucoma with high accuracy even with a small number of fundus photographs.

Atalay Eray, Özalp Onur, Devecioğlu Özer Can, Erdoğan Hakika, İnce Türker, Yıldırım Nilgün

2022-Jun-29

Glaucoma, artificial intelligence, convolutional neural network, telemedicine

In IEEE open journal of engineering in medicine and biology

Prabhakar Sunil Kumar, Lee Seong-Whan

2022

Deep learning, EEG, PSO, Q-learning, reinforcement learning

In Frontiers in cardiovascular medicine

Kappel Coralea, Rushton-Marovac Moira, Leong Darryl, Dent Susan

2022

artificial intelligence, cardio-oncology, care delivery model, innovation, telehealth

In Frontiers in cardiovascular medicine

Xu Lixue, He Yi, Luo Nan, Guo Ning, Hong Min, Jia Xibin, Wang Zhenchang, Yang Zhenghan

2022

computed tomographic angiography, coronary artery disease, deep learning, diagnostic test, invasive coronary angiography (ICA)

In Frontiers in cardiovascular medicine

Haugg Fridolin, Elgendi Mohamed, Menon Carlo

2022

blood pressure, digital health, hypertension, machine learning, smartphone

In Frontiers in cardiovascular medicine

Background : Albumin, an important component of fluid balance, is associated with kidney, liver, nutritional, and cardiovascular diseases (CVD) and is measured by blood tests. Since fluid balance is associated with electrocardiography (ECG) changes, we established a deep learning model (DLM) to estimate albumin via ECG.

Objective : This study aimed to develop a DLM to estimate albumin via ECG and explored its contribution to future complications.

Materials and Methods : A DLM was trained for estimating ECG-based albumin (ECG-Alb) using 155,078 ECGs corresponding to albumin from 79,111 patients, and another independent 13,335 patients from an academic medical center and 11,370 patients from a community hospital were used for internal and external validation. The primary analysis focused on distinguishing patients with mild to severe hypoalbuminemia, and the secondary analysis aimed to provide additional prognostic value from ECG-Alb for future complications, which included mortality, new-onset hypoalbuminemia, chronic kidney disease (CKD), new onset hepatitis, CVD mortality, new-onset acute myocardial infarction (AMI), new-onset stroke (STK), new-onset coronary artery disease (CAD), new-onset heart failure (HF), and new-onset atrial fibrillation (Afib).

Results : The AUC to identify hypoalbuminemia was 0.8771 with a sensitivity of 56.0% and a specificity of 90.7% in the internal validation set, and the Pearson correlation coefficient was 0.69 in the continuous analysis. The most important ECG features contributing to ECG-Alb were ordered in terms of heart rate, corrected QT interval, T wave axis, sinus rhythm, P wave axis, etc. The group with severely low ECG-Alb had a higher risk of all-cause mortality [hazard ratio (HR): 2.45, 95% CI: 1.81-3.33] and the other hepatorenal and cardiovascular events in the internal validation set. The external validation set yielded similar results.

Conclusion : Hypoalbuminemia and its complications can be predicted using ECG-Alb as a novel biomarker, which may be a non-invasive tool to warn asymptomatic patients.

Lee Yung-Tsai, Lin Chin-Sheng, Fang Wen-Hui, Lee Chia-Cheng, Ho Ching-Liang, Wang Chih-Hung, Tsai Dung-Jang, Lin Chin

2022

artificial intelligence, deep learning, electrocardiogram, hypoalbuminemia, liver failure events, previvor

In Frontiers in artificial intelligence

Zhu Xinting, Lin Yu, He Yuxin, Tsui Kwok-Leung, Chan Pak Wai, Li Lishuai

2022

air traffic network, airport network, complex network, deep learning, graph neural network, throughput prediction

In Frontiers in genetics ; h5-index 62.0

Bak Marieke, Madai Vince Istvan, Fritzsche Marie-Christine, Mayrhofer Michaela Th, McLennan Stuart

2022

artificial intelligence, data access, data privacy, digital health, ethics, fairness, resource allocation

In Clinical chemistry ; h5-index 61.0

BACKGROUND : Cell-free DNA (cfDNA) analysis holds great promise for non-invasive cancer screening, diagnosis, and monitoring. We hypothesized that mining the patterns of cfDNA shallow whole-genome sequencing datasets from patients with cancer could improve cancer detection.

METHODS : By applying unsupervised clustering and supervised machine learning on large cfDNA shallow whole-genome sequencing datasets from healthy individuals (n = 367) and patients with different hematological (n = 238) and solid malignancies (n = 320), we identified cfDNA signatures that enabled cancer detection and typing.

RESULTS : Unsupervised clustering revealed cancer type-specific sub-grouping. Classification using a supervised machine learning model yielded accuracies of 96% and 65% in discriminating hematological and solid malignancies from healthy controls, respectively. The accuracy of disease type prediction was 85% and 70% for the hematological and solid cancers, respectively. The potential utility of managing a specific cancer was demonstrated by classifying benign from invasive and borderline adnexal masses with an area under the curve of 0.87 and 0.74, respectively.

CONCLUSIONS : This approach provides a generic analytical strategy for non-invasive pan-cancer detection and cancer type prediction.

Che Huiwen, Jatsenko Tatjana, Lenaerts Liesbeth, Dehaspe Luc, Vancoillie Leen, Brison Nathalie, Parijs Ilse, Van Den Bogaert Kris, Fischerova Daniela, Heremans Ruben, Landolfo Chiara, Testa Antonia Carla, Vanderstichele Adriaan, Liekens Lore, Pomella Valentina, Wozniak Agnieszka, Dooms Christophe, Wauters Els, Hatse Sigrid, Punie Kevin, Neven Patrick, Wildiers Hans, Tejpar Sabine, Lambrechts Diether, Coosemans An, Timmerman Dirk, Vandenberghe Peter, Amant Frédéric, Vermeesch Joris Robert

2022-Jun-30

cfDNA, ctDNA, hematological malignancies, liquid biopsy, machine learning, ovarian tumors, solid tumors

ArXiv Preprint

Tobias Goodwin-Allcock, Jason McEwen, Robert Gray, Parashkev Nachev, Hui Zhang

2022-07-01

In iScience

Cheng Wei, Ramachandran Sohini, Crawford Lorin

2022-Jul-15

Artificial intelligence, Bioinformatics, Genetics

In Frontiers in psychology ; h5-index 92.0

Tsai Chia-Wei, Ma Yi-Wei, Chang Yao-Chung, Lai Ying-Hsun

2022

AI-assisted program, expectancy-value theory, learning effectiveness, multiculturalism, program education

In Frontiers in psychology ; h5-index 92.0

Sun Huilin, Zafar Muhammad Zeeshan, Hasan Naveed

2022

Pakistan, Think-aloud, attention, cognition, emotion, product advertisement, qualitative research, tweets

In Neurophotonics

Dehkharghanian Taher, Hashemiaghdam Arsalan, Ashrafi Ghazaleh

2022-Oct

ATP, bioluminescence, image analysis, machine learning, nerve terminals

In Frontiers in neuroscience ; h5-index 72.0

Wang Jianqing, Mo Weitao, Wu Yan, Xu Xiaomei, Li Yi, Ye Jianming, Lai Xiaobo

2022

artificial intelligence, automated recognition, computational intelligence, intelligent data analysis, spatial attention module

In Frontiers in neuroscience ; h5-index 72.0

Lu Wen, Li Zhuangzhuang, Li Yini, Li Jie, Chen Zhengnong, Feng Yanmei, Wang Hui, Luo Qiong, Wang Yiqing, Pan Jun, Gu Lingyun, Yu Dongzhen, Zhang Yudong, Shi Haibo, Yin Shankai

2022

benign paroxysmal positional vertigo, deep learning, neural network, nystagmus detection, vertigo

In BioMed research international ; h5-index 102.0

Tao Zhou, XiaoYu Chang, HuiLing Lu, XinYu Ye, YunCan Liu, XiaoMin Zheng

2022

In Frontiers in aging neuroscience ; h5-index 64.0

Objectives : [18F]9-fluoropropyl-(+)-dihydrotetrabenazine ([18F]-FP-DTBZ) positron emission tomography (PET) provides reliable information for the diagnosis of Parkinson's disease (PD). In this study, we proposed a multi-atlas-based [18F]-FP-DTBZ PET image segmentation method for PD quantification assessment.

Methods : A total of 99 subjects from Xuanwu Hospital of Capital Medical University were included in this study, and both brain PET and magnetic resonance (MR) scans were conducted. Data from 20 subjects were used to generate atlases, based on which a multi-atlas-based [18F]-FP-DTBZ PET segmentation method was developed especially for striatum and its subregions. The proposed method was compared with the template-based method through striatal subregion parcellation performance and the standard uptake value ratio (SUVR) quantification accuracy. Discriminant analysis between healthy controls (HCs) and PD patients was further performed.

Results : Segmentation results of the multi-atlas-based method showed better consistency than the template-based method with the ground truth, yielding a dice coefficient of 0.81 over 0.73 on the full striatum. The SUVRs calculated by the multi-atlas-based method had an average interclass correlation coefficient (ICC) of 0.953 with the standardized result, whereas the template-based method only reached 0.815. The SUVRs of HCs were generally higher than that of patients with PD and showed significant differences in all of the striatal subregions (all p < 0.001). The median and posterior putamen performed best in discriminating patients with PD from HCs.

Conclusion : The proposed multi-atlas-based [18F]-FP-DTBZ PET image segmentation method achieved better performance than the template-based method, indicating great potential in improving accuracy and efficiency for PD diagnosis in clinical routine.

Pan Yiwei, Liu Shuying, Zeng Yao, Ye Chenfei, Qiao Hongwen, Song Tianbing, Lv Haiyan, Chan Piu, Lu Jie, Ma Ting

2022

Parkinson’s disease, SUVR quantification, [18F]-FP-DTBZ, image segmentation, striatum subregion

In Frontiers in immunology ; h5-index 100.0

Xiong Tao, Lv Xiao-Shuo, Wu Gu-Jie, Guo Yao-Xing, Liu Chang, Hou Fang-Xia, Wang Jun-Kui, Fu Yi-Fan, Liu Fu-Qiang

2022

abdominal aortic aneurysm, differentially expressed genes, multiple machine learning methods, single-cell sequencing, weighted co-expression network analysis

In Frontiers in immunology ; h5-index 100.0

Objective : This study aims to identify prognostic factors for low-grade glioma (LGG) via different machine learning methods in the whole genome and to predict patient prognoses based on these factors. We verified the results through in vitro experiments to further screen new potential therapeutic targets.

Method : A total of 940 glioma patients from The Cancer Genome Atlas (TCGA) and The Chinese Glioma Genome Atlas (CGGA) were included in this study. Two different feature extraction algorithms - LASSO and Random Forest (RF) - were used to jointly screen genes significantly related to the prognosis of patients. The risk signature was constructed based on these screening genes, and the K-M curve and ROC curve evaluated it. Furthermore, we discussed the differences between the high- and low-risk groups distinguished by the signature in detail, including differential gene expression (DEG), single-nucleotide polymorphism (SNP), copy number variation (CNV), immune infiltration, and immune checkpoint. Finally, we identified the function of a novel molecule, METTL7B, which was highly correlated with PD-L1 expression on tumor cell, as verified by in vitro experiments.

Results : We constructed an accurate prediction model based on seven genes (AUC at 1, 3, 5 years= 0.91, 0.85, 0.74). Further analysis showed that extracellular matrix remodeling and cytokine and chemokine release were activated in the high-risk group. The proportion of multiple immune cell infiltration was upregulated, especially macrophages, accompanied by the high expression of most immune checkpoints. According to the in vitro experiment, we preliminarily speculate that METTL7B affects the stability of PD-L1 mRNA by participating in the modification of m6A.

Conclusion : The seven gene signatures we constructed can predict the prognosis of patients and identify the potential benefits of immune checkpoint inhibitors (ICI) therapy for LGG. More importantly, METTL7B, one of the risk genes, is a crucial molecule that regulates PD-L1 and could be used as a new potential therapeutic target.

Luo Cheng, Wang Songmao, Shan Wenjie, Liao Weijie, Zhang Shikuan, Wang Yanzhi, Xin Qilei, Yang Tingpeng, Hu Shaoliang, Xie Weidong, Xu Naihan, Zhang Yaou

2022

METTL7B, PD-L1, RNA stability, glioma, m6A (N6-methyladenose), prognosis prediction

In Briefings in bioinformatics

MOTIVATION : Bacteriophages are viruses infecting bacteria. Being key players in microbial communities, they can regulate the composition/function of microbiome by infecting their bacterial hosts and mediating gene transfer. Recently, metagenomic sequencing, which can sequence all genetic materials from various microbiome, has become a popular means for new phage discovery. However, accurate and comprehensive detection of phages from the metagenomic data remains difficult. High diversity/abundance, and limited reference genomes pose major challenges for recruiting phage fragments from metagenomic data. Existing alignment-based or learning-based models have either low recall or precision on metagenomic data.

RESULTS : In this work, we adopt the state-of-the-art language model, Transformer, to conduct contextual embedding for phage contigs. By constructing a protein-cluster vocabulary, we can feed both the protein composition and the proteins' positions from each contig into the Transformer. The Transformer can learn the protein organization and associations using the self-attention mechanism and predicts the label for test contigs. We rigorously tested our developed tool named PhaMer on multiple datasets with increasing difficulty, including quality RefSeq genomes, short contigs, simulated metagenomic data, mock metagenomic data and the public IMG/VR dataset. All the experimental results show that PhaMer outperforms the state-of-the-art tools. In the real metagenomic data experiment, PhaMer improves the F1-score of phage detection by 27%.

Shang Jiayu, Tang Xubo, Guo Ruocheng, Sun Yanni

2022-Jun-30

deep learning, phage identification, protein cluster-based token, transformer

In Briefings in bioinformatics

Kurata Hiroyuki, Tsukiyama Sho, Manavalan Balachandran

2022-Jul-01

anti-coronavirus peptide, bioinformatics, deep learning, random forest, transformer, word2vec

ArXiv Preprint

Botond Fazekas, Guilherme Aresta, Dmitrii Lachinov, Sophie Riedl, Julia Mai, Ursula Schmidt-Erfurth, Hrvoje Bogunovic

2022-07-01

In Neuro-oncology advances

Background : Automated brain tumor identification facilitates diagnosis and treatment planning. We evaluate the performance of traditional machine learning (TML) and deep learning (DL) in brain tumor detection and segmentation, using MRI.

Methods : A systematic literature search from January 2000 to May 8, 2021 was conducted. Study quality was assessed using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). Detection meta-analysis was performed using a unified hierarchical model. Segmentation studies were evaluated using a random effects model. Sensitivity analysis was performed for externally validated studies.

Results : Of 224 studies included in the systematic review, 46 segmentation and 38 detection studies were eligible for meta-analysis. In detection, DL achieved a lower false positive rate compared to TML; 0.018 (95% CI, 0.011 to 0.028) and 0.048 (0.032 to 0.072) (P < .001), respectively. In segmentation, DL had a higher dice similarity coefficient (DSC), particularly for tumor core (TC); 0.80 (0.77 to 0.83) and 0.63 (0.56 to 0.71) (P < .001), persisting on sensitivity analysis. Both manual and automated whole tumor (WT) segmentation had "good" (DSC ≥ 0.70) performance. Manual TC segmentation was superior to automated; 0.78 (0.69 to 0.86) and 0.64 (0.53 to 0.74) (P = .014), respectively. Only 30% of studies reported external validation.

Conclusions : The comparable performance of automated to manual WT segmentation supports its integration into clinical practice. However, manual outperformance for sub-compartmental segmentation highlights the need for further development of automated methods in this area. Compared to TML, DL provided superior performance for detection and sub-compartmental segmentation. Improvements in the quality and design of studies, including external validation, are required for the interpretability and generalizability of automated models.

Kouli Omar, Hassane Ahmed, Badran Dania, Kouli Tasnim, Hossain-Ibrahim Kismet, Steele J Douglas

artificial intelligence, brain tumor, machine learning, meta-analysis, segmentation

In IEEE journal of translational engineering in health and medicine

BACKGROUND : Artificial intelligence techniques are widely used in solving medical problems. Recently, researchers have used various deep learning techniques for the severity classification of Chikungunya disease. But these techniques suffer from overfitting and hyper-parameters tuning problems.

METHODS : In this paper, an artificial intelligence-based cyber-physical system (CPS) is proposed for the severity classification of Chikungunya disease. In CPS system, the physical components are integrated with computational algorithms to provide better results. Random forest (RF) is used to design the severity classification model for Chikungunya disease. However, RF suffers from overfitting and poor computational speed problems due to complex architectures and large amounts of connection weights. Therefore, an evolving RF model is proposed using the adaptive crossover-based genetic algorithm (ACGA).

RESULTS : ACGA can efficiently optimize the architecture of RF to achieve better results with better computational speed. Extensive experiments are performed by utilizing the Chikungunya disease dataset.

CONCLUSION : Performance analysis demonstrates that ACGA-RF achieves higher performance as compared to the competitive models in terms of F-measure, accuracy, sensitivity, and specificity. The proposed CPS system can prevent users from visiting hospitals and can render services to patients living far away from hospitals.

Singh Dilbag, Kaur Manjit, Kumar Vijay, Jabarulla Mohamed Yaseen, Lee Heung-No

2022

Artificial intelligence, Chikungunya disease, adaptive crossover, automated diagnosis, cyber-physical system, genetic algorithm, random forest, severity classification

In Journal of healthcare engineering

Alharbi Mafawez T, Almutiq Mutiq M

2022

In Journal of medical imaging (Bellingham, Wash.)

Jason Jeong Jiwoong, Patel Bhavik, Banerjee Imon

2022-May

CT, data augmentation, generative adversarial networks, intracranial hemorrhage, multiclass classification

In Frontiers in plant science

Jiang Xuetao, Jiang Meiyu, Gou YuChun, Li Qian, Zhou Qingguo

2022

Landsat 7, digital twin, machine learning, remote sensing, spatial temporal prediction

In Computational intelligence and neuroscience

Liu Mengqiong

2022

In Computational intelligence and neuroscience

Bu Xiangwei, Jiang Mingyang

2022

In Computational intelligence and neuroscience

Jia Tiejun, Wang Cheng, Tian Zhiqiang, Wang Bingyin, Tian Feng

2022

In Computational intelligence and neuroscience

Sasikumar A, Ravi Logesh, Kotecha Ketan, Saini Jatinderkumar R, Varadarajan Vijayakumar, Subramaniyaswamy V

2022

In Computational intelligence and neuroscience

Yan Yupei, Ma Weimin, Li Yangmin, Wong Sengfat, He Ping, Zhu Shaoping, Yin Xuemei

2022

In Evolutionary intelligence

Aswathy A L, Anand Hareendran S, Chandra S S Vinod

2022-Jun-24

AlexNet, Computed tomography, DenseNet-201, Neural network, ResNet-50, Transfer learning

In PloS one ; h5-index 176.0

Saad Eysha, Sadiq Saima, Jamil Ramish, Rustam Furqan, Mehmood Arif, Choi Gyu Sang, Ashraf Imran

2022

ArXiv Preprint

Andrey Malinin, Andreas Athanasopoulos, Muhamed Barakovic, Meritxell Bach Cuadra, Mark J. F. Gales, Cristina Granziera, Mara Graziani, Nikolay Kartashev, Konstantinos Kyriakopoulos, Po-Jui Lu, Nataliia Molchanova, Antonis Nikitakis, Vatsal Raina, Francesco La Rosa, Eli Sivena, Vasileios Tsarsitalidis, Efi Tsompopoulou, Elena Volf

2022-06-30

In GeoHealth

Conibear Luke, Reddington Carly L, Silver Ben J, Chen Ying, Arnold Stephen R, Spracklen Dominick V

2022-Jun

China, air quality, emissions, emulators, health impact assessment, machine learning

In IEEE transactions on medical imaging ; h5-index 74.0

Hochberg Dana Cohen, Greenspan Hayit, Giryes Raja

2022-Jun-29

ArXiv Preprint

Atanu R Sinha, Navita Goyal, Sunny Dhamnani, Tanay Asija, Raja K Dubey, M V Kaarthik Raja, Georgios Theocharous

2022-06-30

In GeoHealth

Conibear Luke, Reddington Carly L, Silver Ben J, Chen Ying, Knote Christoph, Arnold Stephen R, Spracklen Dominick V

2022-Jun

China, air quality, emulator, health impact assessment, machine learning, particulate matter

In Software impacts

Tavakolian Alireza, Hajati Farshid, Rezaee Alireza, Fasakhodi Amirhossein Oliaei, Uddin Shahadat

2022-Jun-22

COVID-19, Coronavirus, Deep learning, H1N1 virus, Outbreak, Screening

ArXiv Preprint

Haomiao Ni, Yuan Xue, Kelvin Wong, John Volpi, Stephen T. C. Wong, James Z. Wang, Xiaolei Huang

2022-06-30

In Journal of the American Society of Nephrology : JASN

BACKGROUND : Total kidney volume (TKV) is an important imaging biomarker in autosomal dominant polycystic kidney disease (ADPKD). Manual computation of TKV, particularly with the exclusion of exophytic cysts, is laborious and time consuming.

METHODS : We developed a fully automated segmentation method for TKV using a deep learning network to selectively segment kidney regions while excluding exophytic cysts. We used abdominal T₂ -weighted magnetic resonance images from 210 individuals with ADPKD who were divided into two groups: one group of 157 to train the network and a second group of 53 to test it. With a 3D U-Net architecture using dataset fingerprints, the network was trained by K-fold cross-validation, in that 80% of 157 cases were for training and the remaining 20% were for validation. We used Dice similarity coefficient, intraclass correlation coefficient, and Bland-Altman analysis to assess the performance of the automated segmentation method compared with the manual method.

RESULTS : The automated and manual reference methods exhibited excellent geometric concordance (Dice similarity coefficient: mean±SD, 0.962±0.018) on the test datasets, with kidney volumes ranging from 178.9 to 2776.0 ml (mean±SD, 1058.5±706.8 ml) and exophytic cysts ranging from 113.4 to 2497.6 ml (mean±SD, 549.0±559.1 ml). The intraclass correlation coefficient was 0.9994 (95% confidence interval, 0.9991 to 0.9996; P<0.001) with a minimum bias of -2.424 ml (95% limits of agreement, -49.80 to 44.95).

CONCLUSIONS : We developed a fully automated segmentation method to measure TKV that excludes exophytic cysts and has an accuracy similar to that of a human expert. This technique may be useful in clinical studies that require automated computation of TKV to evaluate progression of ADPKD and response to treatment.

Kim Youngwoo, Tao Cheng, Kim Hyungchan, Oh Geum-Yoon, Ko Jeongbeom, Bae Kyongtae T

2022-Jun-29

ADPKD, chronic kidney disease, chronic kidney failure, cystic kidney, deep learning, exophytic cyst, image segmentation, kidney volume, risk factors

In Journal of experimental botany

Chen Qiaomin, Zheng Bangyou, Chen Tong, Chapman Scott C

2022-Jun-30

APSIM, PROSAIL, biological constraints, canopy and leaf biophysical traits, canopy reflectance, unmanned aerial vehicle

In BMJ open

INTRODUCTION : Traumatic brain injury (TBI) in children can be associated with poor outcome in crucial functional domains, including motor, neurocognitive and behavioural functioning. However, outcome varies between patients and is mediated by complex interplay between demographic factors, premorbid functioning and (sub)acute clinical characteristics. At present, methods to understand let alone predict outcome on the basis of these variables are lacking, which contributes to unnecessary follow-up as well as undetected impairments in children. Therefore, this study aims to develop prognostic models for the individual outcome of children with TBI in a range of important developmental domains. In addition, the potential added value of advanced neuroimaging data and the use of machine learning algorithms in the development of prognostic models will be assessed.

METHODS AND ANALYSIS : 210 children aged 4-18 years diagnosed with mild-to-severe TBI will be prospectively recruited from a research network of Dutch hospitals. They will be matched 2:1 to a control group of neurologically healthy children (n=105). Predictors in the model will include demographic, premorbid and clinical measures prospectively registered from the TBI hospital admission onwards as well as MRI metrics assessed at 1 month post-injury. Outcome measures of the prognostic models are (1) motor functioning, (2) intelligence, (3) behavioural functioning and (4) school performance, all assessed at 6 months post-injury.

ETHICS AND DISSEMINATION : Ethics has been obtained from the Medical Ethical Board of the Amsterdam UMC (location AMC). Findings of our multicentre prospective study will enable clinicians to identify TBI children at risk and aim towards a personalised prognosis. Lastly, findings will be submitted for publication in open access, international and peer-reviewed journals.

TRIAL REGISTRATION NUMBER : NL71283.018.19 and NL9051.

Kooper Cece C, Oosterlaan Jaap, Bruining Hilgo, Engelen Marc, Pouwels Petra J W, Popma Arne, van Woensel Job B M, Buis Dennis R, Steenweg Marjan E, Hunfeld Maayke, Königs Marsh

2022-Jun-29

Magnetic resonance imaging, Paediatric intensive & critical care, Paediatric neurology, Paediatric neurosurgery, Paediatric radiology

In Physics in medicine and biology

OBJECTIVE : Photon-counting CT (PCCT) has better dose efficiency and spectral resolution than energy-integrating CT, which is advantageous for material decomposition. Unfortunately, the accuracy of PCCT-based material decomposition is limited due to spectral distortions in the photon-counting detector (PCD).

APPROACH : In this work, we demonstrate a deep learning (DL) approach that compensates for spectral distortions in the PCD and improves accuracy in material decomposition by using decomposition maps provided by high-dose multi-energy-integrating detector (EID) data as training labels. We use a 3D U-net architecture and compare networks with PCD filtered backprojection (FBP) reconstruction (FBP2Decomp), PCD iterative reconstruction (Iter2Decomp), and PCD decomposition (Decomp2Decomp) as the input.

MAIN RESULTS : We found that our Iter2Decomp approach performs best, but DL outperforms matrix inversion decomposition regardless of the input. Compared to PCD matrix inversion decomposition, Iter2Decomp gives 27.50% lower root mean squared error (RMSE) in the iodine (I) map and 59.87% lower RMSE in the photoelectric effect (PE) map. In addition, it increases the structural similarity (SSIM) by 1.92%, 6.05%, and 9.33% in the I, Compton scattering (CS), and PE maps, respectively. When taking measurements from iodine and calcium vials, Iter2Decomp provides excellent agreement with multi-EID decomposition. One limitation is some blurring caused by our DL approach, with a decrease from 1.98 line pairs/mm at 50% modulation transfer function (MTF) with PCD matrix inversion decomposition to 1.75 line pairs/mm at 50% MTF when using Iter2Decomp.

SIGNIFICANCE : Overall, this work demonstrates that our DL approach with high-dose multi-EID derived decomposition labels is effective at generating more accurate material maps from PCD data. More accurate preclinical spectral PCCT imaging such as this could serve for developing nanoparticles that show promise in the field of theranostics (therapy and diagnostics).

Nadkarni Rohan, Allphin Alex, Clark Darin P, Badea Cristian T

2022-Jun-29

CNN, deep learning, material decomposition, photon-counting CT, theranostics

In Physics in medicine and biology

OBJECTIVE : Glioma is one of the most fatal cancers in the world which has been divided into Low Grade Glioma (LGG) and High Grade Glioma (HGG), and its image grading has become a hot topic of contemporary research. Magnetic Resonance Imaging (MRI) is a vital diagnostic tool for brain tumor detection, analysis, and surgical planning. Accurate and automatic glioma grading is crucial for speeding up diagnosis and treatment planning. Aiming at the problems of 1) large number of parameters, 2) complex calculation, and 3) poor speed of the current glioma grading algorithms based on deep learning, this paper proposes a lightweight 3D UNet deep learning framework, which can improve classification accuracy in comparison with the existing methods.

APPROACH : To improve efficiency while maintaining accuracy, existing 3D UNet has been excluded, and depthwise separable convolution has been applied to 3D convolution to reduce the number of network parameters. The weight of parameters on the basis of space and channel compression & excitation module has been strengthened to improve the model in the feature map, reduce the weight of redundant parameters, and strengthen the performance of the model.

MAIN RESULTS : A total of 560 patients with glioma were retrospectively reviewed. All patients underwent MRI before surgery. The experiments were carried out on T1w, T2w, FLAIR, and CET1w images. Additionally, a way of marking tumor area by cube bounding box is presented which has no significant difference in model performance with the manually drawn ground truth. Evaluated on test data sets using the proposed model has shown good results (with accuracy of 89.29%).

SIGNIFICANCE : This work serves to achieve LGG/HGG grading by simple, effective, and non-invasive diagnostic approaches to provide diagnostic suggestions for clinical usage, thereby facilitating hasten treatment decisions.

Yu Xuan, Wu Yaping, Bai Yan, Han Hui, Chen Lijuan, Gao Haiyan, Wei Huanhuan, Wang Meiyun

2022-Jun-29

MRIs, depthwise separable convolution, glioma grading, lightweight 3D UNet, scSE block

In Neurocomputing

Zhang Yong, Su Li, Liu Zhenxing, Tan Wei, Jiang Yinuo, Cheng Cheng

2022-Jun-23

Attention mechanisms, COVID-19, Computed tomography, Deep learning, Semi-supervised learning

In Chaos, solitons, and fractals

Roster Kirstin, Connaughton Colm, Rodrigues Francisco A

2022-Aug

COVID-19, Epidemic forecasting, Machine learning, Transfer learning, Zika

ArXiv Preprint

Joona Pohjonen, Carolin Stürenberg, Atte Föhr, Esa Pitkänen, Antti Rannikko, Tuomas Mirtti

2022-06-30

In Bioinspiration & biomimetics

Zhou Yang, Wang Wei, Zhang Han, Zheng Xingwen, Li Liang, Wang Chen, Xu Gang, Xie Guangming

2022-Jun-29

distributed controller, electrocommunication, network protocol, robot coordination, underwater robots

In Journal of neural engineering ; h5-index 52.0

OBJECTIVE : Significant progress has been witnessed in within-subject seizure detection from Electroencephalography (EEG) signals. Consequently, more and more works have been shifted from within-subject seizure detection to cross-subject scenarios. However, the progress is hindered by inter-patient variations caused by gender, seizure type, etc. Approach: To tackle this problem, we propose a multi-view cross-object seizure detection model with information bottleneck attribution. Feature representations specific to seizures are learned from raw EEG data by adversarial deep learning. Combined with the manually designed discriminative features, the model can detect seizures across different subjects. In addition, we introduce information bottleneck attribution to provide insights into the decision-making of the adversarial learning process, thus enhancing the interpretability of the model.

MAIN RESULTS : Extensive experiments are conducted on two benchmark datasets. The experimental results verify the efficacy of the model.

Zhao Yanna, Zhang Gaobo, Zhang Yongfeng, Xiao Tiantian, Wang Ziwei, Xu Fangzhou, Zheng Yuanjie

2022-Jun-29

EEG, adversarial learning, cross-subject, information bottleneck attribution, seizure detection

In Digestion

INTRODUCTION : Computer-aided detection (CADe) helps increase colonoscopic polyp detection. However, little is known about other performance metrics like the number and duration of false-positive (FP) activations or how stable the detection of a polyp is.

METHODS : 111 colonoscopy videos with total 1,793,371 frames were analyzed on a frame-by-frame basis using a commercially available CADe system (GI-Genius, Medtronic Inc.). Primary endpoint was the number and duration of FP activations per colonoscopy. Additionally, we analyzed other CADe performance parameters, including per-polyp sensitivity, per-frame sensitivity, and first detection time of a polyp. We additionally investigated whether a threshold for withholding CADe activations can be set to suppress short FP activations and how this threshold alters the CADe performance parameters.

RESULTS : A mean of 101 ± 88 FPs per colonoscopy were found. Most of the FPs consisted of less than three frames with a maximal 66-ms duration. The CADe system detected all 118 polyps and achieved a mean per-frame sensitivity of 46.6 ± 26.6%, with the lowest value for flat polyps (37.6 ± 24.8%). Withholding CADe detections up to 6 frames length would reduce the number of FPs by 87.97% (p < 0.001) without a significant impact on CADe performance metrics.

CONCLUSIONS : The CADe system works reliable but generates many FPs as a side effect. Since most FPs are very short, withholding short-term CADe activations could substantially reduce the number of FPs without impact on other performance metrics. Clinical practice would benefit from the implementation of customizable CADe thresholds.

Brand Markus, Troya Joel, Krenzer Adrian, De Maria Costanza, Mehlhase Niklas, Götze Sebastian, Walter Benjamin, Meining Alexander, Hann Alexander

2022-Jun-29

Artificial intelligence, Colonoscopy, Computer-aided detection, Deep learning

In European journal of radiology ; h5-index 47.0

Li Qingneng, Zhu Xiaohua, Zou Sijuan, Zhang Na, Liu Xin, Yang Yongfeng, Zheng Hairong, Liang Dong, Hu Zhanli

2022-Jun-23

Attenuation correction, Clinical examination, Computed tomography, Deep learning, Positron emission tomography

In Medical image analysis

Cui Jianan, Gong Kuang, Guo Ning, Kim Kyungsang, Liu Huafeng, Li Quanzheng

2022-Jun-23

Deep image prior, Logan plot, PET Parametric image estimation, Unsupervised learning

In Clinical orthopaedics and related research ; h5-index 71.0

BACKGROUND : Femoral neck fractures are common and are frequently treated with internal fixation. A major disadvantage of internal fixation is the substantially high number of conversions to arthroplasty because of nonunion, malunion, avascular necrosis, or implant failure. A clinical prediction model identifying patients at high risk of conversion to arthroplasty may help clinicians in selecting patients who could have benefited from arthroplasty initially.

QUESTION/PURPOSE : What is the predictive performance of a machine-learning (ML) algorithm to predict conversion to arthroplasty within 24 months after internal fixation in patients with femoral neck fractures?

METHODS : We included 875 patients from the Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trial. The FAITH trial consisted of patients with low-energy femoral neck fractures who were randomly assigned to receive a sliding hip screw or cancellous screws for internal fixation. Of these patients, 18% (155 of 875) underwent conversion to THA or hemiarthroplasty within the first 24 months. All patients were randomly divided into a training set (80%) and test set (20%). First, we identified 27 potential patient and fracture characteristics that may have been associated with our primary outcome, based on biomechanical rationale and previous studies. Then, random forest algorithms (an ML learning, decision tree-based algorithm that selects variables) identified 10 predictors of conversion: BMI, cardiac disease, Garden classification, use of cardiac medication, use of pulmonary medication, age, lung disease, osteoarthritis, sex, and the level of the fracture line. Based on these variables, five different ML algorithms were trained to identify patterns related to conversion. The predictive performance of these trained ML algorithms was assessed on the training and test sets based on the following performance measures: (1) discrimination (the model's ability to distinguish patients who had conversion from those who did not; expressed with the area under the receiver operating characteristic [AUC]), (2) calibration (the plotted estimated versus the observed probabilities; expressed with the calibration curve intercept and slope), and (3) the overall model performance (Brier score: a composite of discrimination and calibration).

RESULTS : None of the five ML algorithms performed well in predicting conversion to arthroplasty in the training set and the test set; AUCs of the algorithms in the training set ranged from 0.57 to 0.64, slopes of calibration plots ranged from 0.53 to 0.82, calibration intercepts ranged from --0.04 to 0.05, and Brier scores ranged from 0.14 to 0.15. The algorithms were further evaluated in the test set; AUCs ranged from 0.49 to 0.73, calibration slopes ranged from 0.17 to 1.29, calibration intercepts ranged from -1.28 to 0.34, and Brier scores ranged from 0.13 to 0.15.

CONCLUSION : The predictive performance of the trained algorithms was poor, despite the use of one of the best datasets available worldwide on this subject. If the current dataset consisted of different variables or more patients, the performance may have been better. Also, various reasons for conversion to arthroplasty were pooled in this study, but the separate prediction of underlying pathology (such as, avascular necrosis or nonunion) may be more precise. Finally, it may be possible that it is inherently difficult to predict conversion to arthroplasty based on preoperative variables alone. Therefore, future studies should aim to include more variables and to differentiate between the various reasons for arthroplasty.

LEVEL OF EVIDENCE : Level III, prognostic study.

van de Kuit Anouk, Oosterhoff Jacobien H F, Dijkstra Hidde, Sprague Sheila, Bzovsky Sofia, Bhandari Mohit, Swiontkowski Marc, Schemitsch Emil H, IJpma Frank F A, Poolman Rudolf W, Doornberg Job N, Hendrickx Laurent A M

2022-Jun-21

In Clinical orthopaedics and related research ; h5-index 71.0

BACKGROUND : Aseptic revision THA and TKA are associated with an increased risk of adverse outcomes compared with primary THA and TKA. Understanding the risk profiles for patients undergoing aseptic revision THA or TKA may provide an opportunity to decrease the risk of postsurgical complications. There are risk stratification tools for postoperative complications after aseptic revision TKA or THA; however, current tools only include nonmodifiable risk factors, such as medical comorbidities, and do not include modifiable risk factors.

QUESTIONS/PURPOSES : (1) Can machine learning predict 30-day mortality and complications for patients undergoing aseptic revision THA or TKA using a cohort from the American College of Surgeons National Surgical Quality Improvement Program database? (2) Which patient variables are the most relevant in predicting complications?

METHODS : This was a temporally validated, retrospective study analyzing the 2014 to 2019 National Surgical Quality Improvement Program database, as this database captures a large cohort of aseptic revision THA and TKA patients across a broad range of clinical settings and includes preoperative laboratory values. The training data set was 2014 to 2018, and 2019 was the validation data set. Given that predictive models learn expected prevalence of outcomes, this split allows assessment of model performance in contemporary patients. Between 2014 and 2019, a total of 24,682 patients underwent aseptic revision TKA and 17,871 patients underwent aseptic revision THA. Of those, patients with CPT codes corresponding to aseptic revision TKA or THA were considered as potentially eligible. Based on excluding procedures involving unclean wounds, 78% (19,345 of 24,682) of aseptic revision TKA procedures and 82% (14,711 of 17,871) of aseptic revision THA procedures were eligible. Ten percent of patients in each of the training and validation cohorts had missing predictor variables. Most of these missing data were preoperative sodium or hematocrit (8% in both the training and validation cohorts). No patients had missing outcome data. No patients were excluded due to missing data. The mean patient was age 66 ± 12 years, the mean BMI was 32 ± 7 kg/m2, and the mean American Society of Anesthesiologists (ASA) Physical Score was 3 (56%). XGBoost was then used to create a scoring tool for 30-day adverse outcomes. XGBoost was chosen because it can handle missing data, it is nonlinear, it can assess nuanced relationships between variables, it incorporates techniques to reduce model complexity, and it has a demonstrated record of producing highly accurate machine-learning models. Performance metrics included discrimination and calibration. Discrimination was assessed by c-statistics, which describe the area under the receiver operating characteristic curve. This quantifies how well a predictive model discriminates between patients who have the outcome of interest versus those who do not. Relevant ranges for c-statistics include good (0.70 to 0.79), excellent (0.80 to 0.89), and outstanding (> 0.90). We estimated 95% confidence intervals (CIs) for c-statistics by 500-sample bootstrapping. Calibration curves quantify reliability of model predictions. Reliable models produce prediction probabilities for outcomes that are similar to observed probabilities of those outcomes, so a well-calibrated model should demonstrate a calibration curve that does not deviate substantially from a line of slope 1 and intercept 0. Calibration curves were generated on the 2019 validation data. Shapley Additive Explanations (SHAP) visualizations were used to investigate feature importance to gain insight into how models made predictions. The models were built into an online calculator for ongoing testing and validation. The risk calculator, which is freely available (http://nb-group.org/rev2/), allows a user to input patient data to calculate postoperative risk of 30-day mortality, cardiac, and respiratory complications after aseptic revision TKA or THA. A post hoc analysis was performed to assess whether using data from 2020 would improve calibration on 2019 data.

RESULTS : The model accurately predicted mortality, cardiac complications, and respiratory complications after aseptic revision THA or TKA, with c-statistics of 0.88 (95% CI 0.83 to 0.93), 0.80 (95% CI 0.75 to 0.84), and 0.78 (95% CI 0.74 to 0.82), respectively, on internal validation and 0.87 (95% CI 0.77 to 0.96), 0.70 (95% CI 0.61 to 0.78), and 0.82 (95% CI 0.75 to 0.88), respectively, on temporal validation. Calibration curves demonstrated slight over-confidence in predictions (most predicted probabilities were higher than observed probabilities). Post hoc analysis of 2020 data did not yield improved calibration on the 2019 validation set. Important risk factors for all models included increased age and higher ASA, BMI, hematocrit level, and sodium level. Hematocrit and ASA were in the top three most important features for all models. The factor with the strongest association for mortality and cardiac complication models was age, and for the respiratory model, chronic obstructive pulmonary disease. Risk related to sodium followed a U-shaped curve. Preoperative hyponatremia and hypernatremia predicted an increased risk of mortality and respiratory complications, with a nadir of 138 mmol/L; hyponatremia was more strongly associated with mortality than hypernatremia. A hematocrit level less than 36% predicted an increased risk of all three adverse outcomes. A BMI less than 24 kg/m2-and especially less than 20 kg/m2-predicted an increased risk of all three adverse outcomes, with little to no effect for higher BMI.

CONCLUSION : This temporally validated model predicted 30-day mortality, cardiac complications, and respiratory complications after aseptic revision THA or TKA with c-statistics ranging from 0.78 to 0.88. This freely available risk calculator can be used preoperatively by surgeons to educate patients on their individual postoperative risk of these specific adverse outcomes. Unanswered questions that remain include whether altering the studied preoperative patient variables, such as sodium or hematocrit, would affect postoperative risk of adverse outcomes; however, a prospective cohort study is needed to answer this question.

LEVEL OF EVIDENCE : Level III, therapeutic study.

Abraham Vivek Mathew, Booth Greg, Geiger Phillip, Balazs George Christian, Goldman Ashton

2022-Jun-20

In ACS applied materials & interfaces ; h5-index 147.0

Wang Mao, Jiang Jianwen

2022-Jun-29

Fractional free volume, fragmentation, machine learning, molecular simulation, polymer

In Journal of personality assessment

Costello Thomas H, Patrick Christopher J

2022-Jun-29

In Science robotics

Sandamirskaya Yulia, Kaboli Mohsen, Conradt Jorg, Celikel Tansu

2022-Jun-29

In Critical care explorations

** : There is only low-certainty evidence on the use of predictive models to assist COVID-19 patient's ICU admission decision-making process. Accumulative evidence suggests that lung ultrasound (LUS) assessment of COVID-19 patients allows accurate bedside evaluation of lung integrity, with the added advantage of repeatability, absence of radiation exposure, reduced risk of virus dissemination, and low cost. Our goal is to assess the performance of a quantified indicator resulting from LUS data compared with standard clinical practice model to predict critical respiratory illness in the 24 hours following hospital admission.

DESIGN : Prospective cohort study.

SETTING : Critical Care Unit from University Hospital Purpan (Toulouse, France) between July 2020 and March 2021.

PATIENTS : Adult patients for COVID-19 who were in acute respiratory failure (ARF), defined as blood oxygen saturation as measured by pulse oximetry less than 90% while breathing room air or respiratory rate greater than or equal to 30 breaths/min at hospital admission. Linear multivariate models were used to identify factors associated with critical respiratory illness, defined as death or mild/severe acute respiratory distress syndrome (Pao₂/Fio₂ < 200) in the 24 hours after patient's hospital admission.

INTERVENTION : LUS assessment.

MEASUREMENTS AND MAIN RESULTS : One hundred and forty COVID-19 patients with ARF were studied. This cohort was split into two independent groups: learning sample (first 70 patients) and validation sample (last 70 patients). Interstitial lung water, thickening of the pleural line, and alveolar consolidation detection were strongly associated with patient's outcome. The LUS model predicted more accurately patient's outcomes than the standard clinical practice model (DeLong test: Testing: z score = 2.50, p value = 0.01; Validation: z score = 2.11, p value = 0.03).

CONCLUSIONS : LUS assessment of COVID-19 patients with ARF at hospital admission allows a more accurate prediction of the risk of critical respiratory illness than standard clinical practice. These results hold the promise of improving ICU resource allocation process, particularly in the case of massive influx of patients or limited resources, both now and in future anticipated pandemics.

Aguersif Amazigh, Sarton Benjamine, Bouharaoua Sihem, Gaillard Lucien, Standarovski Denis, Faucoz Orphée, Martin Blondel Guillaume, Khallel Hatem, Thalamas Claire, Sommet Agnes, Riu Béatrice, Morand Eric, Bataille Benoit, Silva Stein

2022-Jun

COVID-19, acute respiratory distress syndrome, acute respiratory failure, intensive care unit admission decision-making, lung ultrasound, machine learning

In Evolutionary intelligence

Aswathy A L, Anand Hareendran S, Chandra S S Vinod

2022-Jun-24

AlexNet, Computed tomography, DenseNet-201, Neural network, ResNet-50, Transfer learning

ArXiv Preprint

Yi Lin, Zeyu Wang, Kwang-Ting Cheng, Hao Chen

2022-06-30

In Biomedizinische Technik. Biomedical engineering

Ji Li, Zhang Chen, Li Haiwei, Zhang Ningning, Zheng Peng, Guo Changhao, Zhang Yong, Tang Xiaoyu

2022-Jun-28

EEG map, electroencephalogram (EEG), safe flight, take-off and landing, β-wave

In Science advances

Allesøe Rosa Lundbye, Nudel Ron, Thompson Wesley K, Wang Yunpeng, Nordentoft Merete, Børglum Anders D, Hougaard David M, Werge Thomas, Rasmussen Simon, Benros Michael Eriksen

2022-Jul

In Sleep

STUDY OBJECTIVES : Wearable sleep technology has rapidly expanded across the consumer market due to advances in technology and increased interest in personalized sleep assessment to improve health and mental performance. We tested the performance of a novel device, the Happy Ring, alongside other commercial wearables (Actiwatch 2, Fitbit Charge 4, Whoop 3.0, Oura Ring V2), against in-lab polysomnography (PSG) and an at-home EEG-derived sleep monitoring device, the Dreem 2 Headband.

METHODS : 36 healthy adults with no diagnosed sleep disorders and no recent use of medications or substances known to affect sleep pattern were assessed across 77 nights. Subjects participated in a single night of in-lab PSG and 2 nights of at-home data collection. The Happy Ring includes sensors for skin conductance, movement, heart rate, and skin temperature. The Happy Ring utilized two machine-learning derived scoring algorithms: a "generalized" algorithm that applied broadly to all users, and a "personalized" algorithm that adapted to individual subjects' data. Epoch-by-epoch analyses compared the wearable devices to in-lab PSG and to at-home EEG Headband.

RESULTS : Compared to in-lab PSG, the "generalized" and "personalized" algorithms demonstrated good sensitivity (94% and 93%, respectively) and specificity (70% and 83%, respectively). The Happy Personalized model demonstrated a lower bias and more narrow limits of agreement across Bland-Altman measures.

CONCLUSION : The Happy Ring performed well at home and in the lab, especially regarding sleep/wake detection. The personalized algorithm demonstrated improved detection accuracy over the generalized approach and other devices, suggesting that adaptable, dynamic algorithms can enhance sleep detection accuracy.

Grandner Michael A, Bromberg Zohar, Hadley Aaron, Morrell Zoe, Graf Arnulf, Hutchison Stephen, Freckleton Dustin

2022-Jun-29

actigraphy, polysomnography, sensors, sleep technology, validation, wearables

In PLoS computational biology

Lu Alex X, Lu Amy X, Pritišanac Iva, Zarin Taraneh, Forman-Kay Julie D, Moses Alan M

2022-Jun-29

In ACS applied materials & interfaces ; h5-index 147.0

Sang Shengbo, Pei Zhen, Zhang Fan, Ji Chao, Li Qiang, Ji Jianlong, Yang Kun, Zhang Qiang

2022-Jun-29

3D printing, electronic skin, hair penetrable, high resolution, porous structure, pressure−temperature bimodal sensing

In PloS one ; h5-index 176.0

Saad Eysha, Sadiq Saima, Jamil Ramish, Rustam Furqan, Mehmood Arif, Choi Gyu Sang, Ashraf Imran

2022

In PloS one ; h5-index 176.0

Figà-Talamanca Gianna, Tanzi Paola Musile, D’Urzo Eleonora

2022

In PloS one ; h5-index 176.0

Chappuis Cyrielle, Grandjean Didier

2022

In IEEE transactions on medical imaging ; h5-index 74.0

Hochberg Dana Cohen, Greenspan Hayit, Giryes Raja

2022-Jun-29

In IEEE transactions on neural networks and learning systems

Wang Siqi, Liu Jiyuan, Yu Guang, Liu Xinwang, Zhou Sihang, Zhu En, Yang Yuexiang, Yin Jianping, Yang Wenjing

2022-Jun-29

In Applied soft computing

Mar-Cupido Ricardo, García Vicente, Rivera Gilberto, Sánchez J Salvador

2022-Jun-23

COVID-19, Deep learning, Face mask, Recognition, Transfer learning

In Neurocomputing

Zhang Yong, Su Li, Liu Zhenxing, Tan Wei, Jiang Yinuo, Cheng Cheng

2022-Jun-23

Attention mechanisms, COVID-19, Computed tomography, Deep learning, Semi-supervised learning

ArXiv Preprint

Yunlong Zhang, Yuxuan Sun, Honglin Li, Sunyi Zheng, Chenglu Zhu, Lin Yang

2022-06-30

In IEEE transactions on neural networks and learning systems

Li Shuo, Liu Fang, Jiao Licheng, Chen Puhua, Li Lingling

2022-Jun-29

In JMIR medical informatics ; h5-index 23.0

BACKGROUND : The tenth revision of the International Classification of Diseases (ICD-10) is widely used for epidemiological research and health management. The clinical modification (CM) and procedure coding system (PCS) of ICD-10 were developed to describe more clinical details with increasing diagnosis and procedure codes and applied in disease-related groups for reimbursement. The expansion of codes made the coding time-consuming and less accurate. The state-of-the-art model using deep contextual word embeddings was used for automatic multilabel text classification of ICD-10. In addition to input discharge diagnoses (DD), the performance can be improved by appropriate preprocessing methods for the text from other document types, such as medical history, comorbidity and complication, surgical method, and special examination.

OBJECTIVE : This study aims to establish a contextual language model with rule-based preprocessing methods to develop the model for ICD-10 multilabel classification.

METHODS : We retrieved electronic health records from a medical center. We first compared different word embedding methods. Second, we compared the preprocessing methods using the best-performing embeddings. We compared biomedical bidirectional encoder representations from transformers (BioBERT), clinical generalized autoregressive pretraining for language understanding (Clinical XLNet), label tree-based attention-aware deep model for high-performance extreme multilabel text classification (AttentionXLM), and word-to-vector (Word2Vec) to predict ICD-10-CM. To compare different preprocessing methods for ICD-10-CM, we included DD, medical history, and comorbidity and complication as inputs. We compared the performance of ICD-10-CM prediction using different preprocesses, including definition training, external cause code removal, number conversion, and combination code filtering. For the ICD-10 PCS, the model was trained using different combinations of DD, surgical method, and key words of special examination. The micro F₁ score and the micro area under the receiver operating characteristic curve were used to compare the model's performance with that of different preprocessing methods.

RESULTS : BioBERT had an F₁ score of 0.701 and outperformed other models such as Clinical XLNet, AttentionXLM, and Word2Vec. For the ICD-10-CM, the model had an F₁ score that significantly increased from 0.749 (95% CI 0.744-0.753) to 0.769 (95% CI 0.764-0.773) with the ICD-10 definition training, external cause code removal, number conversion, and combination code filter. For the ICD-10-PCS, the model had an F₁ score that significantly increased from 0.670 (95% CI 0.663-0.678) to 0.726 (95% CI 0.719-0.732) with a combination of discharge diagnoses, surgical methods, and key words of special examination. With our preprocessing methods, the model had the highest area under the receiver operating characteristic curve of 0.853 (95% CI 0.849-0.855) and 0.831 (95% CI 0.827-0.834) for ICD-10-CM and ICD-10-PCS, respectively.

CONCLUSIONS : The performance of our model with the pretrained contextualized language model and rule-based preprocessing method is better than that of the state-of-the-art model for ICD-10-CM or ICD-10-PCS. This study highlights the importance of rule-based preprocessing methods based on coder coding rules.

Chen Pei-Fu, Chen Kuan-Chih, Liao Wei-Chih, Lai Feipei, He Tai-Liang, Lin Sheng-Che, Chen Wei-Jen, Yang Chi-Yu, Lin Yu-Cheng, Tsai I-Chang, Chiu Chi-Hao, Chang Shu-Chih, Hung Fang-Ming

2022-Jun-29

International Classification of Diseases, algorithm, coding system, data mining, deep learning, electronic health record, medical records, multilabel text classification, natural language processing

In Journal of biomechanical engineering ; h5-index 32.0

Kobeissi Hiba, Mohammadzadeh Saeed, Lejeune Emma

2022-Jun-29

In JMIR formative research

BACKGROUND : In recent years, social media has become a major channel for health-related information in Saudi Arabia. Prior health informatics studies have suggested that a large proportion of health-related posts on social media are inaccurate. Given the subject matter and the scale of dissemination of such information, it is important to be able to automatically discriminate between accurate and inaccurate health-related posts in Arabic.

OBJECTIVE : The first aim of this study is to generate a data set of generic health-related tweets in Arabic, labeled as either accurate or inaccurate health information. The second aim is to leverage this data set to train a state-of-the-art deep learning model for detecting the accuracy of health-related tweets in Arabic. In particular, this study aims to train and compare the performance of multiple deep learning models that use pretrained word embeddings and transformer language models.

METHODS : We used 900 health-related tweets from a previously published data set extracted between July 15, 2019, and August 31, 2019. Furthermore, we applied a pretrained model to extract an additional 900 health-related tweets from a second data set collected specifically for this study between March 1, 2019, and April 15, 2019. The 1800 tweets were labeled by 2 physicians as accurate, inaccurate, or unsure. The physicians agreed on 43.3% (779/1800) of tweets, which were thus labeled as accurate or inaccurate. A total of 9 variations of the pretrained transformer language models were then trained and validated on 79.9% (623/779 tweets) of the data set and tested on 20% (156/779 tweets) of the data set. For comparison, we also trained a bidirectional long short-term memory model with 7 different pretrained word embeddings as the input layer on the same data set. The models were compared in terms of their accuracy, precision, recall, F₁ score, and macroaverage of the F₁ score.

RESULTS : We constructed a data set of labeled tweets, 38% (296/779) of which were labeled as inaccurate health information, and 62% (483/779) of which were labeled as accurate health information. We suggest that this was highly efficacious as we did not include any tweets in which the physician annotators were unsure or in disagreement. Among the investigated deep learning models, the Transformer-based Model for Arabic Language Understanding version 0.2 (AraBERTv0.2)-large model was the most accurate, with an F₁ score of 87%, followed by AraBERT version 2-large and AraBERTv0.2-base.

CONCLUSIONS : Our results indicate that the pretrained language model AraBERTv0.2 is the best model for classifying tweets as carrying either inaccurate or accurate health information. Future studies should consider applying ensemble learning to combine the best models as it may produce better results.

Albalawi Yahya, Nikolov Nikola S, Buckley Jim

2022-Jun-29

BERT, bidirectional encoder representations from transformers, deep learning, health informatics, health information, infodemiology, language model, machine learning, misinformation, pretrained language models, social media, tweets

In Topics in magnetic resonance imaging : TMRI

OBJECTIVES : Automated whole brain segmentation from magnetic resonance images is of great interest for the development of clinically relevant volumetric markers for various neurological diseases. Although deep learning methods have demonstrated remarkable potential in this area, they may perform poorly in nonoptimal conditions, such as limited training data availability. Manual whole brain segmentation is an incredibly tedious process, so minimizing the data set size required for training segmentation algorithms may be of wide interest. The purpose of this study was to compare the performance of the prototypical deep learning segmentation architecture (U-Net) with a previously published atlas-free traditional machine learning method, Classification using Derivative-based Features (C-DEF) for whole brain segmentation, in the setting of limited training data.

MATERIALS AND METHODS : C-DEF and U-Net models were evaluated after training on manually curated data from 5, 10, and 15 participants in 2 research cohorts: (1) people living with clinically diagnosed HIV infection and (2) relapsing-remitting multiple sclerosis, each acquired at separate institutions, and between 5 and 295 participants' data using a large, publicly available, and annotated data set of glioblastoma and lower grade glioma (brain tumor segmentation). Statistics was performed on the Dice similarity coefficient using repeated-measures analysis of variance and Dunnett-Hsu pairwise comparison.

RESULTS : C-DEF produced better segmentation than U-Net in lesion (29.2%-38.9%) and cerebrospinal fluid (5.3%-11.9%) classes when trained with data from 15 or fewer participants. Unlike C-DEF, U-Net showed significant improvement when increasing the size of the training data (24%-30% higher than baseline). In the brain tumor segmentation data set, C-DEF produced equivalent or better segmentations than U-Net for enhancing tumor and peritumoral edema regions across all training data sizes explored. However, U-Net was more effective than C-DEF for segmentation of necrotic/non-enhancing tumor when trained on 10 or more participants, probably because of the inconsistent signal intensity of the tissue class.

CONCLUSIONS : These results demonstrate that classical machine learning methods can produce more accurate brain segmentation than the far more complex deep learning methods when only small or moderate amounts of training data are available (n ≤ 15). The magnitude of this advantage varies by tissue and cohort, while U-Net may be preferable for deep gray matter and necrotic/non-enhancing tumor segmentation, particularly with larger training data sets (n ≥ 20). Given that segmentation models often need to be retrained for application to novel imaging protocols or pathology, the bottleneck associated with large-scale manual annotation could be avoided with classical machine learning algorithms, such as C-DEF.

Dieckhaus Henry, Meijboom Rozanna, Okar Serhat, Wu Tianxia, Parvathaneni Prasanna, Mina Yair, Chandran Siddharthan, Waldman Adam D, Reich Daniel S, Nair Govind

2022-Jun-01

In NMR in biomedicine ; h5-index 41.0

OBJECTIVE : To investigate the performance of various deep learning (DL) architectures for MyoMapNet, a DL model for T₁ estimation using accelerated cardiac T₁ mapping from four T₁ -weighted images collected after a single inversion pulse (Look-Locker, LL4).

METHODS : We implemented and tested three DL architectures for MyoMapNet: (a) a fully connected neural network (FC), (b) convolutional neural networks (VGG19, ResNet50), and (c) encoder-decoder networks with skip connections (ResUNet, U-Net). Modified Look-Locker Inversion Recovery (MOLLI) images from 749 patients at 3T were used for training, validation, and testing. The first four T₁ -weighted images from MOLLI5(3)3 and/or MOLLI4(1)3(1)2 protocols were extracted to create accelerated cardiac T₁ mapping data. We also prospectively collected data from 28 subjects using MOLLI and LL4 to further evaluate model performance.

RESULTS : Despite rigorous training, conventional VGG19 and ResNet50 models failed to produce anatomically correct T₁ maps, and T₁ values had significant errors. While ResUNet yielded good quality maps, it significantly under-estimated T₁ . Both FC and U-Net, however, yielded excellent image quality with good T₁ accuracy for both native (FC/U-Net/MOLLI= 1217 ± 64/ 1208 ± 61/1199 ± 61 ms, all P<0.05) and post-contrast myocardial T₁ (FC/U-Net/MOLLI= 578 ± 57/ 567 ± 54/574 ± 55 ms, all P<0.05). In terms of precision, the U-Net model yielded better T₁ precision compared to the FC architecture (standard deviation of 61 ms vs. 67 ms for the myocardium for native (P<0.05), and 31 ms vs. 38 ms (P<0.05), for post-contrast). Similar findings were observed in prospectively collected LL4 data.

CONCLUSION : U-Net and FC DL models in MyoMapNet enable fast myocardial T₁ mapping using only four T₁ -weighted images collected from a single Lock-Locker sequence with comparable accuracy. U-Net also provides slight improvement in precision.

Amyar Amine, Guo Rui, Cai Xiaoying, Assana Salah, Chow Kelvin, Rodriguez Jennifer, Yankama Tuyen, Cirillo Julia, Pierce Patrick, Goddu Beth, Ngo Long, Nezafat Reza

2022-Jun-29

Cardiac MRI, Deep learning, Inversion-recovery cardiac T1 mapping, Myocardial tissue characterization

In NMR in biomedicine ; h5-index 41.0

Lam Luu Ho Thanh, Do Duyen Thi, Diep Doan Thi Ngoc, Nguyet Dang Le Nhu, Truong Quang Dinh, Tri Tran Thanh, Thanh Huynh Ngoc, Le Nguyen Quoc Khanh

2022-Jun-29

In Psychophysiology

Hao Ziyu, Li Huanhuan, Ouyang Lisheng, Sun Fang, Wen Xiaotong, Wang Xiang

2022-Jun-29

fMRI, functional connectivity, gray matter volume, suicide attempts, three-dimensional psychological pain

In Journal of magnetic resonance imaging : JMRI

BACKGROUND : Left ventricular (LV) strain measurements can be derived using cardiac MRI from routinely acquired balanced steady-state free precession (bSSFP) cine images.

PURPOSE : To compare the interfield strength agreement of global systolic strain, peak strain rates and artificial intelligence (AI) landmark-based global longitudinal shortening at 1.5 T and 3 T.

STUDY TYPE : Prospective.

SUBJECTS : A total of 22 healthy individuals (mean age 36 ± 12 years; 45% male) completed two cardiac MRI scans at 1.5 T and 3 T in a randomized order within 30 minutes. FIELD STRENGTH/SEQUENCE: bSSFP cine images at 1.5 T and 3 T.

ASSESSMENT : Two software packages, Tissue Tracking (cvi42, Circle Cardiovascular Imaging) and QStrain (Medis Suite, Medis Medical Imaging Systems), were used to derive LV global systolic strain in the longitudinal, circumferential and radial directions and peak (systolic, early diastolic, and late diastolic) strain rates. Global longitudinal shortening and mitral annular plane systolic excursion (MAPSE) were measured using an AI deep neural network model.

STATISTICAL TESTS : Comparisons between field strengths were performed using Wilcoxon signed-rank test (P value < 0.05 considered statistically significant). Agreement was determined using intraclass correlation coefficients (ICCs) and Bland-Altman plots.

RESULTS : Minimal bias was seen in all strain and strain rate measurements between field strengths. Using Tissue Tracking, strain and strain rate values derived from long-axis images showed poor to fair agreement (ICC range 0.39-0.71), whereas global longitudinal shortening and MAPSE showed good agreement (ICC = 0.81 and 0.80, respectively). Measures derived from short-axis images showed good to excellent agreement (ICC range 0.78-0.91). Similar results for the agreement of strain and strain rate measurements were observed with QStrain.

CONCLUSION : The interfield strength agreement of short-axis derived LV strain and strain rate measurements at 1.5 T and 3 T was better than those derived from long-axis images; however, the agreement of global longitudinal shortening and MAPSE was good.

EVIDENCE LEVEL : 2 TECHNICAL EFFICACY: Stage 2.

Ayton Sarah L, Alfuhied Aseel, Gulsin Gaurav S, Parke Kelly S, Wormleighton Joanne V, Arnold J Ranjit, Moss Alastair J, Singh Anvesha, Xue Hui, Kellman Peter, Graham-Brown Matthew P M, McCann Gerry P

2022-Jun-29

cardiac MRI, field strength, left ventricular strain, myocardial deformation analysis

In Journal of assisted reproduction and genetics ; h5-index 39.0

PURPOSE : To dynamically assess the evolution of live birth predictive factors' impact throughout the in vitro fertilization (IVF) process, for each fresh and subsequent frozen embryo transfers.

METHODS : In this multicentric study, data from 13,574 fresh IVF cycles and 6,770 subsequent frozen embryo transfers were retrospectively analyzed. Fifty-seven descriptive parameters were included and split into four categories: (1) demographic (couple's baseline characteristics), (2) ovarian stimulation, (3) laboratory data, and (4) embryo transfer (fresh and frozen). All these parameters were used to develop four successive predictive models with the outcome being a live birth event.

RESULTS : Eight parameters were predictive of live birth in the first step after the first consultation, 9 in the second step after the stimulation, 11 in the third step with laboratory data, and 13 in the 4th step at the transfer stage. The predictive performance of the models increased at each step. Certain parameters remained predictive in all 4 models while others were predictive only in the first models and no longer in the subsequent ones when including new parameters. Moreover, some parameters were predictive in fresh transfers but not in frozen transfers.

CONCLUSION : This work evaluates the chances of live birth for each embryo transfer individually and not the cumulative outcome after multiple IVF attempts. The different predictive models allow to determine which parameters should be taken into account or not at each step of an IVF cycle, and especially at the time of each embryo transfer, fresh or frozen.

Grzegorczyk-Martin Véronika, Roset Julie, Di Pizio Pierre, Fréour Thomas, Barrière Paul, Pouly Jean Luc, Grynberg Michael, Parneix Isabelle, Avril Catherine, Pacheco Joe, Grzegorczyk Tomasz M

2022-Jun-29

In vitro fertilization, Live birth, Predictive factors, Predictive models

In ERJ open research

Background : Patients with coronavirus disease 2019 (COVID-19) could develop severe disease requiring admission to the intensive care unit (ICU). This article presents a novel method that predicts whether a patient will need admission to the ICU and assesses the risk of in-hospital mortality by training a deep-learning model that combines a set of clinical variables and features in chest radiographs.

Methods : This was a prospective diagnostic test study. Patients with confirmed severe acute respiratory syndrome coronavirus 2 infection between March 2020 and January 2021 were included. This study was designed to build predictive models obtained by training convolutional neural networks for chest radiograph images using an artificial intelligence (AI) tool and a random forest analysis to identify critical clinical variables. Then, both architectures were connected and fine-tuned to provide combined models.

Results : 2552 patients were included in the clinical cohort. The variables independently associated with ICU admission were age, fraction of inspired oxygen (F _iO2 ) on admission, dyspnoea on admission and obesity. Moreover, the variables associated with hospital mortality were age, F _iO2 on admission and dyspnoea. When implementing the AI model to interpret the chest radiographs and the clinical variables identified by random forest, we developed a model that accurately predicts ICU admission (area under the curve (AUC) 0.92±0.04) and hospital mortality (AUC 0.81±0.06) in patients with confirmed COVID-19.

Conclusions : This automated chest radiograph interpretation algorithm, along with clinical variables, is a reliable alternative to identify patients at risk of developing severe COVID-19 who might require admission to the ICU.

Munera Nicolás, Garcia-Gallo Esteban, Gonzalez Álvaro, Zea José, Fuentes Yuli V, Serrano Cristian, Ruiz-Cuartas Alejandra, Rodriguez Alejandro, Reyes Luis F

2022-Apr

In Critical care explorations

** : There is only low-certainty evidence on the use of predictive models to assist COVID-19 patient's ICU admission decision-making process. Accumulative evidence suggests that lung ultrasound (LUS) assessment of COVID-19 patients allows accurate bedside evaluation of lung integrity, with the added advantage of repeatability, absence of radiation exposure, reduced risk of virus dissemination, and low cost. Our goal is to assess the performance of a quantified indicator resulting from LUS data compared with standard clinical practice model to predict critical respiratory illness in the 24 hours following hospital admission.

DESIGN : Prospective cohort study.

SETTING : Critical Care Unit from University Hospital Purpan (Toulouse, France) between July 2020 and March 2021.

PATIENTS : Adult patients for COVID-19 who were in acute respiratory failure (ARF), defined as blood oxygen saturation as measured by pulse oximetry less than 90% while breathing room air or respiratory rate greater than or equal to 30 breaths/min at hospital admission. Linear multivariate models were used to identify factors associated with critical respiratory illness, defined as death or mild/severe acute respiratory distress syndrome (Pao₂/Fio₂ < 200) in the 24 hours after patient's hospital admission.

INTERVENTION : LUS assessment.

MEASUREMENTS AND MAIN RESULTS : One hundred and forty COVID-19 patients with ARF were studied. This cohort was split into two independent groups: learning sample (first 70 patients) and validation sample (last 70 patients). Interstitial lung water, thickening of the pleural line, and alveolar consolidation detection were strongly associated with patient's outcome. The LUS model predicted more accurately patient's outcomes than the standard clinical practice model (DeLong test: Testing: z score = 2.50, p value = 0.01; Validation: z score = 2.11, p value = 0.03).

CONCLUSIONS : LUS assessment of COVID-19 patients with ARF at hospital admission allows a more accurate prediction of the risk of critical respiratory illness than standard clinical practice. These results hold the promise of improving ICU resource allocation process, particularly in the case of massive influx of patients or limited resources, both now and in future anticipated pandemics.

Aguersif Amazigh, Sarton Benjamine, Bouharaoua Sihem, Gaillard Lucien, Standarovski Denis, Faucoz Orphée, Martin Blondel Guillaume, Khallel Hatem, Thalamas Claire, Sommet Agnes, Riu Béatrice, Morand Eric, Bataille Benoit, Silva Stein

2022-Jun

COVID-19, acute respiratory distress syndrome, acute respiratory failure, intensive care unit admission decision-making, lung ultrasound, machine learning

ArXiv Preprint

Yuehao Wang, Yonghao Long, Siu Hin Fan, Qi Dou

2022-06-30

In International journal of computer assisted radiology and surgery

PURPOSE : The robot-assisted automated puncture system under ultrasound guidance can well improve the puncture accuracy in ablation surgery. The automated puncture system requires advanced definition of the puncture location, while the displacement of thoracic-abdominal tumors caused by respiratory motion makes it difficult for the system to locate the best puncture position. Predicting tumor motion is an effective way to help the automated puncture system output a more accurate puncture position.

METHODS : In this paper, we propose a self-attention-based feature pyramid algorithm FPSANet for time-series forecasting, which can extract both linear and nonlinear dependencies of time series. Firstly, we use the temporal convolutional network as the backbone to extract different scale time-series features, and the self-attention module is followed to weigh more significant features to improve nonlinear prediction. Secondly, we use autoregressive models to perform linear prediction. Finally, we directly combine the above two kinds of predictions as the final prediction.

RESULTS : FPSANet is trained and tested on our private datasets captured from clinical individuals, and we predict the target position after 50 ms, 150 ms, 300 ms and 400 ms. The result shows the evaluation criteria of the MAE is less than 1 mm at 50 ms and 150 ms, and less than 2 mm at 300 ms. Compared with the AR model, bidirectional LSTM and RVM, our method not only outperforms both models in accuracy (AR: ~ 7.7%; bidirectional LSTM: ~ 75.9%; RVM: ~ 76.5%) but is also more stable on different types of respiratory curves.

CONCLUSION : Respiratory motion in the liver in actual clinical practice vary widely from person to person, while sometimes having less distinct periodic patterns. Under these conditions, our algorithm has the advantage of excellent stability for prediction on various sequences, and its running time of performing single sequence prediction can meet clinical requirements.

Yao Chen, He Jishuai, Che Hui, Huang Yibin, Wu Jian

2022-Jun-29

AR, Deep learning, Respiratory motion prediction, Self-attention, Temporal convolutional network

In Interdisciplinary sciences, computational life sciences

Asif Sohaib, Amjad Kamran

2022-Jun-29

Computer-aided detection and diagnosis, Deep learning, Optical coherence tomography, Residual network, Transfer learning

In Herz

Heinzel Frank R, Shah Sanjiv J

2022-Jun-29

Cardiovascular disease, Classification, Machine learning, Phenomapping, Phenotype

In European archives of oto-rhino-laryngology : official journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS) : affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery

BACKGROUND : Thyroid nodules are common. Ultrasonography (US) is the first investigation for thyroid nodules. Artificial Intelligence (AI) is widely integrated into medical diagnosis to provide additional information. The primary objective of this study was to accumulate the pooled sensitivity and specificity between all available AI and radiologists using thyroid US imaging. The secondary objective was to compare AI's diagnostic performance to that of radiologists.

MATERIALS AND METHODS : A systematic review meta-analysis. PubMed, Scopus, Web of Science, and Cochrane Library data were searched for studies from inception until June 11, 2020.

RESULTS : Twenty five studies were included in this meta-analysis. The pooled sensitivity and specificity of AI were 0.86 (95% CI 0.81-0.91) and 0.78 (95% CI 0.73-0.83), respectively. The pooled sensitivity and specificity of radiologists were 0.85 (95% CI 0.80-0.89) and 0.82 (95% CI 0.77-0.86), respectively. The accuracy of AI and radiologists is equivalent in terms of AUC [AI 0.89 (95% CI 0.86-0.92), radiologist 0.91 (95% CI 0.88-0.93)]. The diagnostic odd ratio (DOR) between AI 23.10 (95% CI 14.20-37.58) and radiologists 27.12 (95% CI 17.45-42.16) had no statistically significant difference (P = 0.56). Meta-regression analysis revealed that Deep Learning AI had significantly greater sensitivity and specificity than classic machine learning AI (P < 0.001).

CONCLUSION : AI demonstrated comparable performance to radiologists in diagnosing benign and malignant thyroid nodules using ultrasonography. Additional research to establish its equivalency should be conducted.

Potipimpanon Pimrada, Charakorn Natamon, Hirunwiwatkul Prakobkiat

2022-Jun-29

Artificial intelligence, Deep learning, Machine learning, Neural network, Thyroid nodule, Ultrasonography

In Parasitology research ; h5-index 47.0

Zhou Xiaorong, Wang He, Xu Chuan, Peng Li, Xu Feng, Lian Lifei, Deng Gang, Ji Suqiong, Hu Mengyan, Zhu Hong, Xu Yi, Li Guo

2022-Jun-29

Advanced schistosomiasis, Predictive model, Support vector machine, k nearest neighbour

In Archives of orthopaedic and trauma surgery

BACKGROUND : Patient-reported outcome measures (PROMs) are increasingly used as quality benchmark in total hip and knee arthroplasty (THA; TKA) due to bundled payment systems that aim to provide a patient-centered, value-based treatment approach. However, there is a paucity of predictive tools for postoperative PROMs. Therefore, this study aimed to develop and validate machine learning models for the prediction of numerous patient-reported outcome measures following primary hip and knee total joint arthroplasty.

METHODS : A total of 4526 consecutive patients (2137 THA; 2389 TKA) who underwent primary hip and knee total joint arthroplasty and completed both pre- and postoperative PROM scores was evaluated in this study. The following PROM scores were included for analysis: HOOS-PS, KOOS-PS, Physical Function SF10A, PROMIS SF Physical and PROMIS SF Mental. Patient charts were manually reviewed to identify patient demographics and surgical variables associated with postoperative PROM scores. Four machine learning algorithms were developed to predict postoperative PROMs following hip and knee total joint arthroplasty. Model assessment was performed through discrimination, calibration and decision curve analysis.

RESULTS : The factors most significantly associated with the prediction of postoperative PROMs include preoperative PROM scores, Charlson Comorbidity Index, American Society of Anaesthesiology score, insurance status, age, length of hospital stay, body mass index and ethnicity. The four machine learning models all achieved excellent performance across discrimination (AUC > 0.83), calibration and decision curve analysis.

CONCLUSION : This study developed machine learning models for the prediction of patient-reported outcome measures at 1-year following primary hip and knee total joint arthroplasty. The study findings show excellent performance on discrimination, calibration and decision curve analysis for all four machine learning models, highlighting the potential of these models in clinical practice to inform patients prior to surgery regarding their expectations of postoperative functional outcomes following primary hip and knee total joint arthroplasty.

LEVEL OF EVIDENCE : Level III, case control retrospective analysis.

Klemt Christian, Uzosike Akachimere Cosmas, Esposito John G, Harvey Michael Joseph, Yeo Ingwon, Subih Murad, Kwon Young-Min

2022-Jun-29

Artificial intelligence, Hip and knee total joint arthroplasty, Machine learning, Patient-reported outcome measures, Risk factors

In Comprehensive Physiology ; h5-index 52.0

Kashou Anthony H, Adedinsewo Demilade A, Siontis Konstantinos C, Noseworthy Peter A

2022-Jun-29

In Genetics ; h5-index 66.0

Shah Pavak, Bao Zhirong, Zaidel-Bar Ronen

2022-Jun-29

Green fluorescent protein, activity sensors, confocal microscopy, fluorescence microscopy, image analysis, lightsheet microscopy, localization, molecular dynamics, spatiotemporal resolution, super resolution

In European journal of translational myology

Ciliberti Federica Kiyomi, Cesarelli Giuseppe, Guerrini Lorena, Gunnarsson Arnar Evgeni, Forni Riccardo, Aubonnet Romain, Recenti Marco, Jacob Deborah, Jónsson Halldór, Cangiano Vincenzo, Islind Anna Sigríður, Gambacorta Monica, Gargiulo Paolo

2022-Jun-28

In Expert review of neurotherapeutics

INTRODUCTION : Huntington's Disease as progressive neurological disorders associated with motor, behavioral, and cognitive impairment poses a therapeutic challenge in case of limited responsiveness to established therapeutics. Pallidal deep brain stimulation and neurorestorative strategies (brain grafts) scoping to modulate fronto-striatal circuits have gained increased recognition for the treatment of refractory Huntington's disease (HD).

AREAS COVERED : A review (2000-2022) was performed in PubMed, Embase, and Cochrane Library covering clinical trials conceptualized to determine the efficacy and safety of invasive, stereotactic-guided deep-brain stimulation and intracranial brain-graft injection targeting the globus pallidus and adjunct structures (striatum).

EXPERT OPINION : Stereotactic brain-grafting strategies were performed in few HD patients with inconsistent findings and mild-to-moderate clinical responsiveness with a recently published large, randomized-controlled trial (NCT00190450) yielding negative results. We identified 19 in-human DBS trials (uncontrolled) targeting the globus pallidus internus/externus along with randomized-controlled trial pending report (NCT02535884). We did not detect any significant changes in the UHDRS total score after restorative injections, while in contrast, the use of deep-brain stimulation resulted in a significant reduction of chorea. GPi-DBS should be considered in cases where selective chorea is present. However, both invasive therapies remain experimental and are not ready for the implementation in clinical use.

Kinfe Thomas, Del Vecchio Alessandro, Nüssel Martin, Zhao Yining, Stadlbauer Andreas, Buchfelder Michael

2022-Jun-29

Huntington´s disease, brain grafts, chorea, deep-brain stimulation, dystonia, efficacy, fronto-striatal circuits, globus pallidus externus/internus, parkinsonism, quality of life, safety, striatum, unified Huntington´s disease rating scale (UHDRS)

In Acta radiologica (Stockholm, Sweden : 1987)

BACKGROUND : Dynamic myocardial computed tomography perfusion (CTP) is a novel technique able to depict cardiac ischemia.

PURPOSE : To evaluate the impact of a four-dimensional noise reduction filter (similarity filter [4D-SF]) on image quality in dynamic CTP imaging, allowing for substantial radiation dose reduction.

MATERIAL AND METHODS : Dynamic CTP datasets of 30 patients (16 women) with suspected coronary artery disease, acquired with a 320-slice CT system, were retrieved, reconstructed with the deep learning-based algorithm of the system (DLR), and filtered with the 4D-SF. For each case, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in six regions of interest (33-38mm²) were calculated before and after filtering, in four-chamber and short-axis views, and t-tested. Furthermore, six radiologists of different expertise evaluated subjective image preference by answering five visual grading analysis-type questions (regarding acceptable level of noise, absence of artifacts, natural appearance, cardiac contour sharpness, diagnostic acceptability) using a 5-point scale. The results were analyzed using visual grade characteristics (VGC) and intraclass correlation coefficient (ICC).

RESULTS : Mean SNR in four-chamber view (unfiltered vs. filtered) were: septum=4.1 ± 2.1 versus 7.6 ± 5.6; lateral wall=4.5 ± 2.0 versus 8.0 ± 4.9; CNRseptum=16.6 ± 8.9 versus 31.7 ± 28; lateral wall=16.2 ± 8.9 versus 31.3 ± 28.9. Similar results were obtained in short-axis view. The perceived filtered image quality indicated decreased noise (VGC_AUC=0.96) and artifacts (0.65), improved natural appearance (0.59), cardiac contour sharpness (0.74), and diagnostic acceptability (0.78). The inter-observer variability was excellent (ICC=0.79). All results were statistically significant (P < 0.05).

CONCLUSION : Similarity filtering after DLR improves image quality, possibly enabling dose reduction in dynamic CTP imaging in patient with suspected chronic coronary syndrome.

Sliwicka Olga, Swiderska-Chadaj Zaneta, Snoeren Miranda, Brink Monique, Salah Khibar, Peters-Bax Liesbeth, Stille Tip, van Amerongen Martinus Johannes, Sechopoulos Ioannis, Habets Jesse

2022-Jun-28

Computed tomography, dynamic myocardial computed tomography perfusion imaging, image quality, noise reduction filter

In Applied soft computing

Mar-Cupido Ricardo, García Vicente, Rivera Gilberto, Sánchez J Salvador

2022-Jun-23

COVID-19, Deep learning, Face mask, Recognition, Transfer learning

ArXiv Preprint

Elizabeth J Cross, Samuel J Gibson, Matthew R Jones, Daniel J Pitchforth, Sikai Zhang, Timothy J Rogers

2022-06-30

In eLife