Applying machine learning to identify unrecognized COVID-19 deaths recorded as other causes of death in the United States
Authors:
- Mathew V. KiangMKMathew V. Kiang
- Zehang Richard LiZLZehang Richard Li
- Elizabeth Wrigley-FieldEWElizabeth Wrigley-Field
- Rafeya V. RaquibRRRafeya V. Raquib
- Dielle J. LundbergDLDielle J. Lundberg
- Eugenio PaglinoEPEugenio Paglino
- Benjamin HuynhBHBenjamin Huynh
- Kirsten Bibbins-DomingoKBKirsten Bibbins-Domingo
- M. Maria GlymourMGM. Maria Glymour
- Andrew C. StokesASAndrew C. Stokes
Top Cited Papers
Open Access
- 20 March 2026
- journal article
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 12 (12) , eaef5697
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.Keywords
Funding Information
- W.K. Kellogg Foundation
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (P2C HD041023)
This publication has 97 references indexed in Scilit:
- Certifying Death in the United StatesJournal of Forensic Sciences, 2018
- Death Certification Errors and the Effect on Mortality StatisticsPublic Health Reports®, 2017
- Quantifying underreporting of law-enforcement-related deaths in United States vital statistics and news-media-based data sources: A capture–recapture analysisPLOS Medicine, 2017
- The Validity of Race and Hispanic-origin Reporting on Death Certificates in the United States: An Update.2016
- Prediction Policy ProblemsAmerican Economic Review, 2015
- Methods for Constructing and Assessing Propensity ScoresHealth Services Research, 2014
- Education reporting and classification on death certificates in the United States.2010
- Regularization Paths for Generalized Linear Models via Coordinate Descent2010
- The validity of race and Hispanic origin reporting on death certificates in the United States.2008
- Medicolegal Death Investigation System2003