A Predictive Model for Severe Covid-19 in the Medicare Population: A Tool for Prioritizing Scarce Vaccine Supply

Abstract

ABSTRACTBackgroundRecommendations for prioritizing populations for COVID-19 vaccination have focused on front-line health care personnel and residents in long term care, followed by other individuals at higher risk for severe disease. Existing models for identifying higher risk individuals including those over age 65 lack the needed integration of socio-demographic and clinical risk factors to ensure equitable vaccine allocation.MethodsWe developed a predictive model for severe COVID-19 using clinical data from de-identified Medicare claims for 16 million Medicare fee-for-service beneficiaries, including 1 million COVID-19 cases, and socio-economic data from the CDC Social Vulnerability Index. To identify risk factors for severe COVID-19, we used multivariate logistic regression and random forest modeling. Predicted individual probabilities of COVID-19 hospitalization were then calculated for population risk stratification and COVID-19 vaccine prioritization, and for mapping of population risk levels at the county and zip code levels on a nationwide dashboard.ResultsThe leading Covid-19 hospitalization risk factors driving the risk model were: Non-white ethnicity (particularly North American Native, Black, and Hispanic), end-stage renal disease, advanced age (particularly age over 85), prior hospitalization, leukemia, morbid obesity, chronic kidney disease, lung cancer, chronic liver disease, pulmonary fibrosis or pulmonary hypertension, and chemotherapy. However, previously reported risk factors such as chronic obstructive pulmonary disease and diabetes conferred modest hospitalization risk. Among all social vulnerability factors analyzed, residence in a low-income zip code was the only risk factor independently predicting Covid-19 hospitalization. The mapped hospitalization risk levels showed significant correlations with the cumulative COVID-19 case hospitalization rates at the zip code level in the fifteen most populous U.S. major metropolitan areas.ConclusionThis multi-factor risk model which predicts severe Covid-19and its population risk dashboard can be used to optimize Covid-19 vaccine allocation in the higher risk Medicare population where socio-demographic and comorbidity risk factors need to be considered concurrently.