Applying machine learning to identify unrecognized COVID-19 deaths recorded as other causes of death in the United States

2026/03/18 by Mathew V. Kiang, Zehang Richard Li, Elizabeth Wrigley-Field +7 · 2 voices
Mathematics · Medicine · Social Sciences · #COVID-19 and healthcare impacts #COVID-19 epidemiological studies #Insurance, Mortality, Demography, Risk Management

paper · doi:10.1126/sciadv.aef5697

openalex publication_date 2026/03/18 · openalex created_date 2026/03/20 · openalex updated_date 2026/07/12

Abstract

The actual number of US deaths caused by severe acute respiratory syndrome coronavirus 2 infection has been investigated and debated since the start of the COVID-19 pandemic. Here, we use machine learning trained on US death certificates from March 2020 to December 2021 to predict 155,536 (95% uncertainty interval: 150,062 to 161,112) unrecognized COVID-19 deaths. This indicates that 19% more COVID-19 deaths occurred in the US than officially reported. Predicted unrecognized COVID-19 deaths occurred disproportionately among decedents with less than a high school education; decedents identified as Hispanic, American Indian, Alaska Native, Asian, and/or Black; counties with lower household incomes and worse preexisting health; and counties in the South. These findings suggest that the US death investigation system undercounted COVID-19 deaths unevenly, hiding the true extent of inequities.

Citations

• Evidence triangulation in health research
• Infectious disease surveillance needs for the United States: lessons from COVID-19
• The Evolution of Excess Deaths in the United States During the First 2 Years of the COVID-19 Pandemic
• Prediction-Powered Inference
• Elastic Net Regularization Paths for All Generalized Linear Models
• A Tutorial on Bayesian Optimization
• Death Certification Errors and the Effect on Mortality Statistics
• Methods for Constructing and Assessing Propensity Scores
• Prediction Policy Problems
• Covid-19 — Implications for the Health Care System
• Elastic Net Regularization Paths for All Generalized Linear Models
• COVID-19 Mortality Update — United States, 2022

Discussions

• Direct link to the paper: doi.org/10.1126/scia... [bsky, 4 points, 0 comments]
• Elizabeth Wrigley-Field, PhD, co-authored “Applying machine learning to identify unrecognized COVID-19 deaths recorded as other causes of death in the United States” in Sciences Advances. doi.org/10.1 [bsky, 0 points, 0 comments]

Related

• Ensemble Machine Learning Methods for Modeling COVID19 Deaths
• A machine learning analysis of the relationship between some underlying medical conditions and COVID-19 susceptibility
• COVID-19 Mortality Update — United States, 2022
• Machine Learning and Data Science approach towards trend and predictors analysis of CDC Mortality Data for the USA
• The Number of Confirmed Cases of Covid-19 by using Machine Learning: Methods and Challenges