Back

Pre-existing health conditions and severe COVID-19 infection: Analysis of commercial health insurance data from 690,000 infected patients

Wineinger, N. E.; Li, V.; Waalen, J.; Topol, E. J.

2021-03-12 epidemiology
10.1101/2021.03.11.21252708 medRxiv
Show abstract

The development and distribution of new vaccines promises an end to the COVID-19 pandemic. With the elderly and front line workers first in line, the vaccination strategy for the general population remains unclear. In this study we identified 690,000 patients infected with COVID-19 with commercial health insurance coverage across the country between April 1, 2020 and September 30, 2020. From prior health care claims, we determined each persons pre-existing diseases among 26 common chronic diseases. Across age-sex strata we determined the relationships between these conditions and severe COVID-19 infections: ICU admission and extended in-patient stay. We classify disease according to risk, develop multivariable models to predict infection outcomes, and created an online risk assessment tool to estimate risk of ICU admission based on pre-existing health conditions. Our results could be used to help guide risk, vaccination health policy, and personal decision-making as these become available to the general population.

Matching journals

The top 11 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.