AI for Good

Chapter 27Long-Term Effects of COVID-19

—Meghana Kshirsagar and Sumit Mukherjee

Executive Summary

While there is ample information on the risk factors of having complications or dying from SARS-CoV-2 (COVID), there is less information on the long-term effects of COVID and the risks of developing them. To address this knowledge gap, we analyzed a large U.S. medical billing claims dataset to identify common long-term diagnoses and symptoms following COVID infection as well as their associations with various social and medical risk factors. From Change Healthcare—a large insurance claims processor—we obtained a dataset that included healthcare claims (including diagnostic information encoded as International Classification of Diseases, 10th revision—ICD-10—codes) as well as various social determinants of health, such as race, income, education level, and veteran status of the individuals. To identify long-term effects associated with COVID infection, we used a self-controlled cohort design observational study to identify ICD-10 codes whose proportion was significantly increased in the outcome period compared to the control period. Further, we used logistic regression to identify statistically significant relationships between social determinants of health and long-term effects following COVID infection.

Among the over 1.37 million COVID patients analyzed, we found 36 out of 1,724 three-digit ICD-10 codes to be statistically significantly increased in the post-COVID period ( ...