ABSTRACT
COVID-19 causes significant morbidity and mortality and early intervention is key to minimizing deadly complications. Available treatments, such as monoclonal antibody therapy, may limit complications, but only when given soon after symptom onset. Unfortunately, these treatments are often expensive, in limited supply, require administration within a hospital setting, and should be given before the onset of severe symptoms. These challenges have created the need for early triage of patients likely to develop life-threatening complications. To meet this need, we developed an automated patient risk assessment model using a real-world hospital system dataset with over 17,000 COVID-positive patients. Specifically, for each COVID-positive patient, we generate a separate risk score for each of four clinical outcomes including death within 30 days, mechanical ventilator use, ICU admission, and any catastrophic event (a superset of dangerous outcomes). We hypothesized that a deep learning binary classification approach can generate these four risk scores from electronic healthcare records data at the time of diagnosis. Our approach achieves significant performance on the four tasks with an area under receiver operating curve (AUROC) for any catastrophic outcome, death within 30 days, ventilator use, and ICU admission of 86.7%, 88.2%, 86.2%, and 87.8%, respectively. In addition, we visualize the sensitivity and specificity of these risk scores to allow clinicians to customize their usage within different clinical outcomes. We believe this work fulfills a clear clinical need for early detection of objective clinical outcomes and can be used for early screening for treatment intervention. © 2021 IEEE
ABSTRACT
Objective: To screen inhibitors targeting SARS-CoV-2 S protein-ACE2 interaction by molecular docking. Methods: Candidate natural products were collected from Selleck China natural product library (Catalog No. L1400, 2 054 natural products). The structure of SARS-CoV-2 S protein-ACE2 had been determined by Qiang Zhou team (PDB: 6M17). The molecular docking was performed by Discovery Studio. Results: Based on the virtual amino acid mutation experiment which determined the key amino acids, the binding cavity was created. Then, 11 compounds were screened out from the natural compound library: digitonin, Lonicera grisea saponin A, forsythiaside B, L. grisea saponin B, Dipsacus asperges saponin B, hederacoside D, platycodon D, echinacoside, ginsenoside Rb2, ginsenoside Rc, and chlorogenic acid C. Conclusion: The 11 potential inhibitors targeting SARS-CoV-2 S protein-ACE2 interaction were screened out from natural products library, which provides a reference for the research of new anti SARS-CoV-2 drugs.
ABSTRACT
At the end of December, 2019, a novel coronavirus disease (COVID-19) outbreak was found in China. COVID-19 spreads all over 268 countries, and more than 70 000 people got infected till February 23th, 2020. COVID-19 can result in acute respiratory distress syndrome and multiple organ failure due to its strong infectivity and extensive spread. These severe complications are believed to be the consequence of cytokine storm caused by the virus infection. In the “Diagnosis and treatment of novel coronavirus pneumonia”, glucocorticoid is recommended as the immunosuppressive agents to prevent acute immune reaction in critical patients. However, the usage of glucocorticoid may bring severe residual effects such as superinfection risks, prolonged course of disease. Traditional Chinese medicine might have advantages in the moderation of immune system. Actually, TCM is now applied in the treatment of COVID-19 clinically, and exhibits excellent therapeutic effects. In this review, the potential usage of TCM or traditional prescriptions in inhibiting cytokine storm and treating in acute lung injury were analyzed, which would be an effective strategy for the treatment of COVID-19.