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

General General

Deep Survival Analysis With Clinical Variables for COVID-19.

In IEEE journal of translational engineering in health and medicine

OBJECTIVE : Millions of people have been affected by coronavirus disease 2019 (COVID-19), which has caused millions of deaths around the world. Artificial intelligence (AI) plays an increasing role in all areas of patient care, including prognostics. This paper proposes a novel predictive model based on one dimensional convolutional neural networks (1D CNN) to use clinical variables in predicting the survival outcome of COVID-19 patients.

METHODS AND PROCEDURES : We have considered two scenarios for survival analysis, 1) uni-variate analysis using the Log-rank test and Kaplan-Meier estimator and 2) combining all clinical variables ([Formula: see text]=44) for predicting the short-term from long-term survival. We considered the random forest (RF) model as a baseline model, comparing to our proposed 1D CNN in predicting survival groups.

RESULTS : Our experiments using the univariate analysis show that nine clinical variables are significantly associated with the survival outcome with corrected p < 0.05. Our approach of 1D CNN shows a significant improvement in performance metrics compared to the RF and the state-of-the-art techniques (i.e., 1D CNN) in predicting the survival group of patients with COVID-19.

CONCLUSION : Our model has been tested using clinical variables, where the performance is found promising. The 1D CNN model could be a useful tool for detecting the risk of mortality and developing treatment plans in a timely manner.

CLINICAL IMPACT : The findings indicate that using both Heparin and Exnox for treatment is typically the most useful factor in predicting a patient's chances of survival from COVID-19. Moreover, our predictive model shows that the combination of AI and clinical data can be applied to point-of-care services through fast-learning healthcare systems.

Chaddad Ahmad, Hassan Lama, Katib Yousef, Bouridane Ahmed

2023

CNN, COVID-19, clinical variables

Radiology Radiology

Deep-learning-based ensemble method for fully automated detection of renal masses on magnetic resonance images.

In Journal of medical imaging (Bellingham, Wash.)

PURPOSE : Accurate detection of small renal masses (SRM) is a fundamental step for automated classification of benign and malignant or indolent and aggressive renal tumors. Magnetic resonance image (MRI) may outperform computed tomography (CT) for SRM subtype differentiation due to improved tissue characterization, but is less explored compared to CT. The objective of this study is to autonomously detect SRM on contrast-enhanced magnetic resonance images (CE-MRI).

APPROACH : In this paper, we described a novel, fully automated methodology for accurate detection and localization of SRM on CE-MRI. We first determine the kidney boundaries using a U-Net convolutional neural network. We then search for SRM within the localized kidney regions using a mixture-of-experts ensemble model based on the U-Net architecture. Our dataset contained CE-MRI scans of 118 patients with different solid kidney tumor subtypes including renal cell carcinomas, oncocytomas, and fat-poor renal angiomyolipoma. We evaluated the proposed model on the entire CE-MRI dataset using 5-fold cross validation.

RESULTS : The developed algorithm reported a Dice similarity coefficient of 91.20 ± 5.41 % (mean ± standard deviation) for kidney segmentation from 118 volumes consisting of 25,025 slices. Our proposed ensemble model for SRM detection yielded a recall and precision of 86.2% and 83.3% on the entire CE-MRI dataset, respectively.

CONCLUSIONS : We described a deep-learning-based method for fully automated SRM detection using CE-MR images, which has not been studied previously. The results are clinically important as SRM localization is a pre-step for fully automated diagnosis of SRM subtypes.

Anush Agarwal, Rohini Gaikar, Nicola Schieda, WalaaEldin Elfaal Mohamed, Eranga Ukwatta

2023-Mar

U-Net, computer aided detection, deep learning, magnetic resonance imaging, renal masses

General General

Intelligent antepartum fetal monitoring via deep learning and fusion of cardiotocographic signals and clinical data.

In Health information science and systems

PURPOSE : Cardiotocography (CTG), which measures uterine contraction (UC) and fetal heart rate (FHR), is a crucial tool for assessing fetal health during pregnancy. However, traditional computerized cardiotocography (cCTG) approaches have non-negligible calibration errors in feature extraction and heavily rely on the expertise and prior experience to define diagnostic features from CTG or FHR signals. Although previous works have studied deep learning methods for extracting CTG or FHR features, these methods still neglect the clinical information of pregnant women.

METHODS : In this paper, we proposed a multimodal deep learning architecture (MMDLA) for intelligent antepartum fetal monitoring that is capable of performing automatic CTG feature extraction, fusion with clinical data and classification. The multimodal feature fusion was achieved by concatenating high-level CTG features, which were extracted from preprocessed CTG signals via a convolution neural network (CNN) with six convolution layers and five fully connected layers, and the clinical data of pregnant women. Eventually, light gradient boosting machine (LGBM) was implemented as fetal status assessment classifier. The effectiveness of MMDLA was evaluated using a dataset of 16,355 cases, each of which includes FHR signal, UC signal and pertinent clinical data like maternal age and gestational age.

RESULTS : With an accuracy of 90.77% and an area under the curve (AUC) value of 0.9201, the multimodal features performed admirably. The data imbalance issue was also effectively resolved by the LGBM classifier, with a normal-F1 value of 0.9376 and an abnormal-F1 value of 0.8223.

CONCLUSION : In summary, the proposed MMDLA is conducive to the realization of intelligent antepartum fetal monitoring.

Cao Zhen, Wang Guoqiang, Xu Ling, Li Chaowei, Hao Yuexing, Chen Qinqun, Li Xia, Liu Guiqing, Wei Hang

2023-Dec

Antepartum fetal monitoring, Cardiotocographic signal, Clinical data, Convolutional neural network, Multimodal feature fusion

Pathology Pathology

USC-ENet: a high-efficiency model for the diagnosis of liver tumors combining B-mode ultrasound and clinical data.

In Health information science and systems

PURPOSE : Ultrasound image acquisition has the advantages of being low cost, rapid, and non-invasive, and it does not produce radiation. Currently, ultrasound is widely used in the diagnosis of liver tumors. However, owing to the complex presentation and diverse features of benign and malignant liver tumors, accurate diagnosis of liver tumors using ultrasound is difficult even for experienced radiologists. In recent years, artificial intelligence-assisted diagnosis has proven to provide effective support to radiologists. However, there is room for further improvement in the existing ultrasound artificial intelligence diagnostic model of liver tumor. First, the image diagnostic model may not fully consider relevant clinical data in the decision-making process. Second, owing to the difficulty in collecting biopsy pathology and physician-labeled ultrasound data of liver tumors, training datasets are usually small, and commonly used large neural networks tend to overfit on small datasets, which seriously affects the generalization of the model.

METHODS : In this study, we propose a deep learning-assisted diagnosis model called USC-ENet, which integrates B-mode ultrasound features of liver tumors and clinical data of patients, and we design a small neural network specifically for small-scale medical images combined with an attention mechanism.

RESULTS AND CONCLUSION : Real data from 542 patients with liver tumors (N = 2168 images) are used during model training and validation. Experiments show that USC-ENet can achieve a good classification effect (area under the curve = 0.956, sensitivity = 0.915, and specificity = 0.880) after small-scale data training, and it has certain interpretability, showing good potential for clinical adoption. In conclusion, our model provides not only a reliable second opinion for radiologists but also a reference for junior radiologists who lack clinical experience.

Zhao Tingting, Zeng Zhiyong, Li Tong, Tao Wenjing, Yu Xing, Feng Tao, Bu Rui

2023-Dec

B-mode ultrasound, EfficientNet, Feature fusion, Liver tumor

Public Health Public Health

COVID-19Base v3: Update of the knowledgebase for drugs and biomedical entities linked to COVID-19.

In Frontiers in public health

COVID-19 has taken a huge toll on our lives over the last 3 years. Global initiatives put forward by all stakeholders are still in place to combat this pandemic and help us learn lessons for future ones. While the vaccine rollout was not able to curb the spread of the disease for all strains, the research community is still trying to develop effective therapeutics for COVID-19. Although Paxlovid and remdesivir have been approved by the FDA against COVID-19, they are not free of side effects. Therefore, the search for a therapeutic solution with high efficacy continues in the research community. To support this effort, in this latest version (v3) of COVID-19Base, we have summarized the biomedical entities linked to COVID-19 that have been highlighted in the scientific literature after the vaccine rollout. Eight different topic-specific dictionaries, i.e., gene, miRNA, lncRNA, PDB entries, disease, alternative medicines registered under clinical trials, drugs, and the side effects of drugs, were used to build this knowledgebase. We have introduced a BLSTM-based deep-learning model to predict the drug-disease associations that outperforms the existing model for the same purpose proposed in the earlier version of COVID-19Base. For the very first time, we have incorporated disease-gene, disease-miRNA, disease-lncRNA, and drug-PDB associations covering the largest number of biomedical entities related to COVID-19. We have provided examples of and insights into different biomedical entities covered in COVID-19Base to support the research community by incorporating all of these entities under a single platform to provide evidence-based support from the literature. COVID-19Base v3 can be accessed from: https://covidbase-v3.vercel.app/. The GitHub repository for the source code and data dictionaries is available to the community from: https://github.com/91Abdullah/covidbasev3.0.

Basit Syed Abdullah, Qureshi Rizwan, Musleh Saleh, Guler Reto, Rahman M Sohel, Biswas Kabir H, Alam Tanvir

2023

CORD-19, COVID-19, SARS-CoV-2, deep learning, machine learning

General General

Structures, band gaps, and formation energies of highly stable phases of inorganic ABX3 halides: A = Li, Na, K, Rb, Cs, Tl; B = Be, Mg, Ca, Ge, Sr, Sn, Pb; and X = F, Cl, Br, I.

In RSC advances

Recently, halide perovskites have attracted a substantial attention. Although the focus was mostly on hybrid ones with organic polyatomic cations and with inadequate stability, there is a sizable inorganic halide space that is not well explored and may be more stable than hybrid perovskites. In this work, a robust automated framework is used to calculate the essential properties of the highly stable phases of 168 inorganic halide perovskites. The considered space of ABX3 compounds consists of A = Li, Na, K, Rb, Cs, Tl, B = Be, Mg, Ca, Ge, Sr, Sn, Pb, and X = F, Cl, Br, I. The targeted properties are the structure, the formation energy to assess stability, and the energy gap for potential applicability. The calculations are carried out using the density functional theory (DFT) integrated with the precision library of Standard Solid-State Pseudopotentials (SSSP) for structure relaxation and PseudoDojo for energy gap calculation. Furthermore, we adopted a very sufficient and robust random sampling to identify the highly stable phases. The results illustrated that only 118 of the possible 168 compounds are formidable and have reliable results. The remaining 50 compounds are either not formidable or suffer from computational inconsistencies.

Alqahtani Saad M, Alsayoud Abduljabar Q, Alharbi Fahhad H

2023-Mar-14