|
Activity Number:
|
191
- Statistical Research in Rapid Response to COVID-19 Pandemic: Forecasts, Risk Factors, Therapeutics, and Vaccine Trials
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 10, 2021 : 1:30 PM to 3:20 PM
|
|
Sponsor:
|
Health Policy Statistics Section
|
|
Abstract #316653
|
|
|
Title:
|
Dynamic Risk Assessment of COVID-19 Hospitalization from Electronic Health Records (EHRs)
|
|
Author(s):
|
Yuanjia Wang*
|
|
Companies:
|
Columbia University
|
|
Keywords:
|
COVID-19;
spatial temporal modeling;
infectious disease;
risk prediction;
confounding
|
|
Abstract:
|
Identifying individuals at greater risk of COVID-19 infection and severe illness is crucial for prioritizing diagnostic testing, providing best care, and managing healthcare resources. In this talk, we present statistical methods to construct patient-level predictive model and identify patients at high risk of severe progression using electronic health records (EHRs). We first propose a spatial-temporal model to examine the socioeconomic heterogeneity and spatial correlation of COVID-19 transmission at the community level from reported daily new cases. From the model, we extract latent infection density as a measure of community-level risk factor. Next, we assess the individual risk of severe COVID-19 outcomes after a positive diagnosis by a varying-coefficient model that integrates individual-level risk factors from EHRs with community-level risk factors. We analyze COVID transmission data in New York City (NYC) and EHRs from NYC hospitals, where time-varying effects of community risk factors and significant interactions between individual- and community-level risk factors are detected.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2021 program
|
