A Bayesian Framework for Estimating the Risk Ratio of Hospitalization for People with Comorbidity Infected by the SARS-CoV-2 Virus

• Activity Number: 46 - Statistical Challenges and Breakthroughs in Diabetes and Obesity Research in the Big Data Era
• Type: Topic-Contributed
• Date/Time: Sunday, August 8, 2021 : 3:30 PM to 5:20 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Qunfeng Dong* and Xiang Gao
• Companies: Loyola University Chicago and Loyola University Chicago
• Keywords: COVID-19; SARS-CoV-2; Bayesian; Comorbidity; Hospitalization; Risk Ratio

Abstract

Estimating the hospitalization risk for people with certain comorbidities infected by the SARS-CoV-2 virus is important for developing public health policies and guidance based on risk stratification. Traditional biostatistical methods require knowing both the number of infected people who were hospitalized and the number of infected people who were not hospitalized. However, the latter may be undercounted, as it is limited to only those who were tested for viral infection. In addition, comorbidity information for people not hospitalized may not always be readily available for traditional biostatistical analyses. To overcome these limitations, we developed a Bayesian approach that only requires the observed frequency of comorbidities in COVID-19 patients in hospitals and the prevalence of comorbidities in the general population. By applying our approach to two different large-scale datasets in the U.S., our results consistently indicated that cardiovascular diseases carried the highest hospitalization risk for COVID-19 patients, followed by diabetes, chronic respiratory disease, hypertension, and obesity, respectively.