Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Surgery Surgery

Predicting transient ischemic attack risk in patients with mild carotid stenosis using machine learning and CT radiomics.

In Frontiers in neurology

OBJECTIVE : This study aims to establish a radiomics-based machine learning model that predicts the risk of transient ischemic attack in patients with mild carotid stenosis (30-50% North American Symptomatic Carotid Endarterectomy Trial) using extracted computed tomography radiomics features and clinical information.

METHODS : A total of 179 patients underwent carotid computed tomography angiography (CTA), and 219 carotid arteries with a plaque at the carotid bifurcation or proximal to the internal carotid artery were selected. The patients were divided into two groups; patients with symptoms of transient ischemic attack after CTA and patients without symptoms of transient ischemic attack after CTA. Then we performed random sampling methods stratified by the predictive outcome to obtain the training set (N = 165) and testing set (N = 66). 3D Slicer was employed to select the site of plaque on the computed tomography image as the volume of interest. An open-source package PyRadiomics in Python was used to extract radiomics features from the volume of interests. The random forest and logistic regression models were used to screen feature variables, and five classification algorithms were used, including random forest, eXtreme Gradient Boosting, logistic regression, support vector machine, and k-nearest neighbors. Data on radiomic feature information, clinical information, and the combination of these pieces of information were used to generate the model that predicts the risk of transient ischemic attack in patients with mild carotid artery stenosis (30-50% North American Symptomatic Carotid Endarterectomy Trial).

RESULTS : The random forest model that was built based on the radiomics and clinical feature information had the highest accuracy (area under curve = 0.879; 95% confidence interval, 0.787-0.979). The combined model outperformed the clinical model, whereas the combined model showed no significant difference from the radiomics model.

CONCLUSION : The random forest model constructed with both radiomics and clinical information can accurately predict and improve discriminative power of computed tomography angiography in identifying ischemic symptoms in patients with carotid atherosclerosis. This model can aid in guiding the follow-up treatment of patients at high risk.

Xia Hai, Yuan Lei, Zhao Wei, Zhang Chenglei, Zhao Lingfeng, Hou Jialin, Luan Yancheng, Bi Yuxin, Feng Yaoyu

2023

CT angiography, carotid artery, machine learning, prediction model, transient ischemic attack

oncology Oncology

Risk factor identification and prediction models for prolonged length of stay in hospital after acute ischemic stroke using artificial neural networks.

In Frontiers in neurology

BACKGROUND : Accurate estimation of prolonged length of hospital stay after acute ischemic stroke provides crucial information on medical expenditure and subsequent disposition. This study used artificial neural networks to identify risk factors and build prediction models for a prolonged length of stay based on parameters at the time of hospitalization.

METHODS : We retrieved the medical records of patients who received acute ischemic stroke diagnoses and were treated at a stroke center between January 2016 and June 2020, and a retrospective analysis of these data was performed. Prolonged length of stay was defined as a hospital stay longer than the median number of days. We applied artificial neural networks to derive prediction models using parameters associated with the length of stay that was collected at admission, and a sensitivity analysis was performed to assess the effect of each predictor. We applied 5-fold cross-validation and used the validation set to evaluate the classification performance of the artificial neural network models.

RESULTS : Overall, 2,240 patients were enrolled in this study. The median length of hospital stay was 9 days. A total of 1,101 patients (49.2%) had a prolonged hospital stay. A prolonged length of stay is associated with worse neurological outcomes at discharge. Univariate analysis identified 14 baseline parameters associated with prolonged length of stay, and with these parameters as input, the artificial neural network model achieved training and validation areas under the curve of 0.808 and 0.788, respectively. The mean accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of prediction models were 74.5, 74.9, 74.2, 75.2, and 73.9%, respectively. The key factors associated with prolonged length of stay were National Institutes of Health Stroke Scale scores at admission, atrial fibrillation, receiving thrombolytic therapy, history of hypertension, diabetes, and previous stroke.

CONCLUSION : The artificial neural network model achieved adequate discriminative power for predicting prolonged length of stay after acute ischemic stroke and identified crucial factors associated with a prolonged hospital stay. The proposed model can assist in clinically assessing the risk of prolonged hospitalization, informing decision-making, and developing individualized medical care plans for patients with acute ischemic stroke.

Yang Cheng-Chang, Bamodu Oluwaseun Adebayo, Chan Lung, Chen Jia-Hung, Hong Chien-Tai, Huang Yi-Ting, Chung Chen-Chih

2023

artificial neural network - ANN, hospitalization, ischemic stroke, length of stay, machine learning, outcome, prediction, thrombolysis

General General

Spiral drawing analysis with a smart ink pen to identify Parkinson's disease fine motor deficits.

In Frontiers in neurology

INTRODUCTION : Since the uptake of digitizers, quantitative spiral drawing assessment allowed gaining insight into motor impairments related to Parkinson's disease. However, the reduced naturalness of the gesture and the poor user-friendliness of the data acquisition hamper the adoption of such technologies in the clinical practice. To overcome such limitations, we present a novel smart ink pen for spiral drawing assessment, intending to better characterize Parkinson's disease motor symptoms. The device, used on paper as a normal pen, is enriched with motion and force sensors.

METHODS : Forty-five indicators were computed from spirals acquired from 29 Parkinsonian patients and 29 age-matched controls. We investigated between-group differences and correlations with clinical scores. We applied machine learning classification models to test the indicators ability to discriminate between groups, with a focus on model interpretability.

RESULTS : Compared to control, patients' drawings were characterized by reduced fluency and lower but more variable applied force, while tremor occurrence was reflected in kinematic spectral peaks selectively concentrated in the 4-7 Hz band. The indicators revealed aspects of the disease not captured by simple trace inspection, nor by the clinical scales, which, indeed, correlate moderately. The classification achieved 94.38% accuracy, with indicators related to fluency and power distribution emerging as the most important.

CONCLUSION : Indicators were able to significantly identify Parkinson's disease motor symptoms. Our findings support the introduction of the smart ink pen as a time-efficient tool to juxtapose the clinical assessment with quantitative information, without changing the way the classical examination is performed.

Toffoli Simone, Lunardini Francesca, Parati Monica, Gallotta Matteo, De Maria Beatrice, Longoni Luca, Dell’Anna Maria Elisabetta, Ferrante Simona

2023

“Parkinsons disease”, eHealth, movement disorders, smart ink pen, spiral analysis

Ophthalmology Ophthalmology

Macular Telangiectasia Type 2: A Classification System Using MultiModal Imaging MacTel Project Report Number 10.

In Ophthalmology science

PURPOSE : To develop a severity classification for macular telangiectasia type 2 (MacTel) disease using multimodal imaging.

DESIGN : An algorithm was used on data from a prospective natural history study of MacTel for classification development.

SUBJECTS : A total of 1733 participants enrolled in an international natural history study of MacTel.

METHODS : The Classification and Regression Trees (CART), a predictive nonparametric algorithm used in machine learning, analyzed the features of the multimodal imaging important for the development of a classification, including reading center gradings of the following digital images: stereoscopic color and red-free fundus photographs, fluorescein angiographic images, fundus autofluorescence images, and spectral-domain (SD)-OCT images. Regression models that used least square method created a decision tree using features of the ocular images into different categories of disease severity.

MAIN OUTCOME MEASURES : The primary target of interest for the algorithm development by CART was the change in best-corrected visual acuity (BCVA) at baseline for the right and left eyes. These analyses using the algorithm were repeated for the BCVA obtained at the last study visit of the natural history study for the right and left eyes.

RESULTS : The CART analyses demonstrated 3 important features from the multimodal imaging for the classification: OCT hyper-reflectivity, pigment, and ellipsoid zone loss. By combining these 3 features (as absent, present, noncentral involvement, and central involvement of the macula), a 7-step scale was created, ranging from excellent to poor visual acuity. At grade 0, 3 features are not present. At the most severe grade, pigment and exudative neovascularization are present. To further validate the classification, using the Generalized Estimating Equation regression models, analyses for the annual relative risk of progression over a period of 5 years for vision loss and for progression along the scale were performed.

CONCLUSIONS : This analysis using the data from current imaging modalities in participants followed in the MacTel natural history study informed a classification for MacTel disease severity featuring variables from SD-OCT. This classification is designed to provide better communications to other clinicians, researchers, and patients.

FINANCIAL DISCLOSURES : Proprietary or commercial disclosure may be found after the references.

Chew Emily Y, Peto Tunde, Clemons Traci E, Sallo Ferenc B, Pauleikhoff Daniel, Leung Irene, Jaffe Glenn J, Heeren Tjebo F C, Egan Catherine A, Charbel Issa Peter, Balaskas Konstantinos, Holz Frank G, Gaudric Alain, Bird Alan C, Friedlander Martin

2023-Jun

BCVA, best-corrected visual acuity, BLR, blue light reflectance, CART, Classification and Regression Trees, CF, color fundus, Classification, Classification and Regression Trees (CART), EZ, ellipsoid zone, FAF, fundus autoflorescence, FLIO, fluorescence lifetime imaging ophthalmoscopy, MacTel, macular telangiectasia type 2, Machine learning, Macular telangiectasia type 2, NHOR, natural history observation registry, NHOS, natural history observation study, Neurovascular degeneration, OCTA, OCT angiography, SD-OCT, spectral domain-OCT, VA, visual acuity

General General

Current status and trends of artificial intelligence research on the four traditional Chinese medicine diagnostic methods: a scientometric study.

In Annals of translational medicine

BACKGROUND : With the development of technology and the renewal of traditional Chinese medicine (TCM) diagnostic equipment, artificial intelligence (AI) has been widely applied in TCM. Numerous articles employing this technology have been published. This study aimed to outline the knowledge and themes trends of the four TCM diagnostic methods to help researchers quickly master the hotspots and trends in this field. Four TCM diagnostic methods is a TCM diagnostic method through inspection, listening, smelling, inquiring and palpation, the purpose of which is to collect the patient's medical history, symptoms and signs. Then, it provides an analytical basis for later disease diagnosis and treatment plans.

METHODS : Publications related to AI-based research on the four TCM diagnostic methods were selected from the Web of Science Core Collection, without any restriction on the year of publication. VOSviewer and Citespace were primarily used to create graphical bibliometric maps in this field.

RESULTS : China was the most productive country in this field, and Evidence-Based Complementary and Alternative Medicine published the largest number of related papers, and the Shanghai University of Traditional Chinese Medicine is the dominant research organization. The Chengdu University of Traditional Chinese Medicine had the highest average number of citations. Jinhong Guo was the most influential author and Artificial Intelligence in Medicine was the most authoritative journal. Six clusters separated by keywords association showed the range of AI-based research on the four TCM diagnostic methods. The hotspots of AI-based research on the four TCM diagnostic methods included the classification and diagnosis of tongue images in patients with diabetes and machine learning for TCM symptom differentiation.

CONCLUSIONS : This study demonstrated that AI-based research on the four TCM diagnostic methods is currently in the initial stage of rapid development and has bright prospects. Cross-country and regional cooperation should be strengthened in the future. It is foreseeable that more related research outputs will rely on the interdisciplinarity of TCM and the development of neural networks models.

Tian Zhikui, Wang Dongjun, Sun Xuan, Fan Yadong, Guan Yuanyuan, Zhang Naijin, Zhou Mi, Zeng Xianyue, Yuan Yin, Bu Huaien, Wang Hongwu

2023-Feb-15

Citespace, Scientometric analysis, VOSviewer, artificial intelligence (AI), four TCM diagnoses

General General

Statistical and machine learning methods for evaluating trends in air quality under changing meteorological conditions.

In Atmospheric chemistry and physics

Evaluating the influence of anthropogenic-emission changes on air quality requires accounting for the influence of meteorological variability. Statistical methods such as multiple linear regression (MLR) models with basic meteorological variables are often used to remove meteorological variability and estimate trends in measured pollutant concentrations attributable to emission changes. However, the ability of these widely used statistical approaches to correct for meteorological variability remains unknown, limiting their usefulness in the real-world policy evaluations. Here, we quantify the performance of MLR and other quantitative methods using simulations from a chemical transport model, GEOS-Chem, as a synthetic dataset. Focusing on the impacts of anthropogenic-emission changes in the US (2011 to 2017) and China (2013 to 2017) on PM2.5 and O3, we show that widely used regression methods do not perform well in correcting for meteorological variability and identifying long-term trends in ambient pollution related to changes in emissions. The estimation errors, characterized as the differences between meteorology-corrected trends and emission-driven trends under constant meteorology scenarios, can be reduced by 30%-42% using a random forest model that incorporates both local- and regional-scale meteorological features. We further design a correction method based on GEOS-Chem simulations with constant-emission input and quantify the degree to which anthropogenic emissions and meteorological influences are inseparable, due to their process-based interactions. We conclude by providing recommendations for evaluating the impacts of anthropogenic-emission changes on air quality using statistical approaches.

Qiu Minghao, Zigler Corwin, Selin Noelle E

2022