How Does the Novel Coronavirus Kill? A Machine Learning Approach

Background: Identifying patient characteristics associated with poor outcomes is vital to minimizing death due to COVID-19. Identification of features that predict mortality may improve triage and management of COVID-19 patients. Methods: A machine learning algorithm was applied to retrospective patient data to identify features correlated with mortality. Four populations were analyzed: 221 COVID-19 patients admitted to general isolated wards or ICU in Wuhan, China between January and February 2020; 230 COVID-19 inpatients admitted across four U.S. hospitals between January and April 2020; 99,224 inpatients admitted to a U.S. hospital; and 8,492 inpatients admitted to a U.S. hospital with viral infections other than SARS-CoV-2. Findings: Features associated with predicted mortality varied across populations. Among Chinese COVID-19 patients, creatinine was the top predictor of mortality, but was not among the most important features for the U.S. COVID-19 patients. Blood pressure was a more important predictor for U.S COVID-19 patients than for the U.S. viral or general hospitalized populations. Interpretation: The SARS-CoV-2 virus may affect different patient populations in different ways. This may be due to differences in treatment practice across populations, or to evolution of SARS-Cov-2 itself over time. The finding that creatinine was an important predictor only in the Chinese COVID-19 population may indicate that kidney-related complications due to SARS-CoV-2 are becoming less severe. Blood pressure was found to be an important feature in the U.S. COVID-19 population, suggesting an increased importance of cardiac and thrombotic complications of COVID-19. Funding Statement: None. Declaration of Interests: All authors who have affiliations listed with Dascena (Oakland, California, USA) are employees or contractors of Dascena. Ethics Approval Statement: All patient data was maintained in compliance with the Health Insurance Portability and Accountability Act (HIPAA). This study has been determined by the Pearl Institutional Review Board to be Exempt according to FDA 21 CFR 56.104 and 45CFR46.104(b)(4): (4) Secondary Research Uses of Data or Specimens under study number 20-DASC-119.