Back

Identifying At-Risk Communities and Key Vulnerability Indicators in the COVID-19 Pandemic

Thais, S.; Leibowitz, S.; Rios Gutierez, A.; Passarelli, A.; Santo, S.; Shipp, N.

2021-09-22 public and global health
10.1101/2021.09.19.21263805 medRxiv
Show abstract

Throughout the COVID-19 pandemic, certain communities have been disproportionately exposed to detrimental health outcomes and socioeconomic injuries. Quantifying community needs is crucial for identifying testing and service deserts, effectively allocating resources, and informing funding and decision making. We have constructed research-driven metrics measuring the public health and economic impacts of COVID-19 on vulnerable populations. In this work we further examine and validate these indices by training supervised models to predict proxy outcomes and analyzing the feature importances to identify gaps in our original metric design. The indices analyzed in this work are unique among COVID-19 risk assessments due to their robust integration of disparate data sources. Together, they enable more effective responses to COVID-19 driven health inequities.

Matching journals

The top 8 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.