Factors associated with resistance to SARS-CoV-2 infection discovered using large-scale medical record data and machine learning

Abstract

There have been over 621 million cases of COVID-19 worldwide with over 6.5 million deaths. Despite the high secondary attack rate of COVID-19 in shared households, some exposed individuals do not contract the virus. In addition, little is known about whether the occurrence of COVID-19 resistance differs among people by health characteristics as stored in the electronic health records (EHR). In this retrospective analysis, we develop a statistical model to predict COVID-19 resistance in 8,536 individuals with prior COVID-19 exposure using demographics, diagnostic codes, outpatient medication orders, and count of Elixhauser comorbidities in EHR data from the COVID-19 Precision Medicine Platform Registry. Cluster analyses identified 5 patterns of diagnostic codes that distinguished resistant from non-resistant patients in our study population. In addition, our models showed modest performance in predicting COVID-19 resistance (best performing model AUROC = 0.61). Monte Carlo simulations conducted indicated that the AUROC results are statistically significant (p < 0.001) for the testing set. We hope to validate the features found to be associated with resistance/non-resistance through more advanced association studies.

Automated responses to the coronavirus disease-19 pandemic: An overview

“…Further strategies of pre-emption included the attempt to determine who, if exposed, would be likely to become both contagious and symptomatic by applying machine learning to databases of health records (Yang et al, 2023). Taken to the limit of pre-emptive logic, such a system might identify the most vulnerable to take them out of circulation.…”