Multi-task multi-modality SVM for early COVID-19 Diagnosis using chest CT data.

In the early diagnosis of the Coronavirus disease (COVID-19), it is of great importance for either distinguishing severe cases from mild cases or predicting the conversion time that mild cases would possibly convert to severe cases. This study investigates both of them in a unified framework by exploring the problems such as slight appearance difference between mild cases and severe cases, the interpretability, the High Dimension and Low Sample Size (HDLSS) data, and the class imbalance. To this end, the proposed framework includes three steps: (1) feature extraction which first conducts the hierarchical segmentation on the chest Computed Tomography (CT) image data and then extracts multi-modality handcrafted features for each segment, aiming at capturing the slight appearance difference from different perspectives; (2) data augmentation which employs the over-sampling technique to augment the number of samples corresponding to the minority classes, aiming at investigating the class imbalance problem; and (3) joint construction of classification and regression by proposing a novel Multi-task Multi-modality Support Vector Machine (MM-SVM) method to solve the issue of the HDLSS data and achieve the interpretability. Experimental analysis on two synthetic and one real COVID-19 data set demonstrated that our proposed framework outperformed six state-of-the-art methods in terms of binary classification and regression performance.

Single-center experience of organ transplant practice during the COVID-19 epidemic.

In order to safely carry out organ donation transplants during the outbreak of coronavirus disease 2019 (COVID-19), we have formulated strict procedures in place for organ donation and transplantation. We retrospectively analyzed our transplantation work from January 20 to May 5, 2020, to discuss whether organ transplantation can be carried out safely during the epidemic period. From January 20 to May 5, 43 cases of donation were carried out in our hospital, and the utilization rate of liver, kidney, heart, lung, and pancreas donations was more than 90%. Forty-one cases of liver transplantation and 84 cases of kidney transplantation were performed. No graft loss or recipient death occurred within one month after kidney transplantation, and one patient (2.4%) died after liver transplantation. There was no significant difference in the length of hospital stay compared with that during the same period in the previous three years. More importantly, COVID-19 infection did not occur among healthcare providers, donors, patients, or their accompanying families in our center. Under the premise of correct protection, it is safe and feasible to carry out organ transplantation during the epidemic period. Our experience during the outbreak might provide a clinical reference for countries facing COVID-19 worldwide.

Cardiometabolic risks of SARS-CoV-2 hospitalization using Mendelian Randomization.

Many cardiometabolic conditions have demonstrated associative evidence with COVID-19 hospitalization risk. However, the observational designs of the studies in which these associations are observed preclude causal inferences of hospitalization risk. Mendelian Randomization (MR) is an alternative risk estimation method more robust to these limitations that allows for causal inferences. We applied four MR methods (MRMix, IMRP, IVW, MREgger) to publicly available GWAS summary statistics from European (COVID-19 GWAS n = 2956) and multi-ethnic populations (COVID-19 GWAS n = 10,908) to better understand extant causal associations between Type II Diabetes (GWAS n = 659,316), BMI (n = 681,275), diastolic and systolic blood pressure, and pulse pressure (n = 757,601 for each) and COVID-19 hospitalization risk across populations. Although no significant causal effect evidence was observed, our data suggested a trend of increasing hospitalization risk for Type II diabetes (IMRP OR, 95% CI 1.67, 0.96-2.92) and pulse pressure (OR, 95% CI 1.27, 0.97-1.66) in the multi-ethnic sample. Type II diabetes and Pulse pressure demonstrates a potential causal association with COVID-19 hospitalization risk, the proper treatment of which may work to reduce the risk of a severe COVID-19 illness requiring hospitalization. However, GWAS of COVID-19 with large sample size is warranted to confirm the causality.

Joint prediction and time estimation of COVID-19 developing severe symptoms using chest CT scan.

With the rapidly worldwide spread of Coronavirus disease (COVID-19), it is of great importance to conduct early diagnosis of COVID-19 and predict the conversion time that patients possibly convert to the severe stage, for designing effective treatment plans and reducing the clinicians' workloads. In this study, we propose a joint classification and regression method to determine whether the patient would develop severe symptoms in the later time formulated as a classification task, and if yes, the conversion time will be predicted formulated as a classification task. To do this, the proposed method takes into account 1) the weight for each sample to reduce the outliers' influence and explore the problem of imbalance classification, and 2) the weight for each feature via a sparsity regularization term to remove the redundant features of the high-dimensional data and learn the shared information across two tasks, i.e., the classification and the regression. To our knowledge, this study is the first work to jointly predict the disease progression and the conversion time, which could help clinicians to deal with the potential severe cases in time or even save the patients' lives. Experimental analysis was conducted on a real data set from two hospitals with 408 chest computed tomography (CT) scans. Results show that our method achieves the best classification (e.g., 85.91% of accuracy) and regression (e.g., 0.462 of the correlation coefficient) performance, compared to all comparison methods. Moreover, our proposed method yields 76.97% of accuracy for predicting the severe cases, 0.524 of the correlation coefficient, and 0.55 days difference for the conversion time.