tetano
Editor, Senior Moderator
Sci Adv
. 2026 Mar 20;12(12):eaef5697.
doi: 10.1126/sciadv.aef5697. Epub 2026 Mar 18.
Applying machine learning to identify unrecognized COVID-19 deaths recorded as other causes of death in the United States
Mathew V Kiang[SUP] 1 [/SUP], Zehang Richard Li[SUP] 2 [/SUP], Elizabeth Wrigley-Field[SUP] 3 [/SUP], Rafeya V Raquib[SUP] 4 [/SUP], Dielle J Lundberg[SUP] 4 [/SUP], Eugenio Paglino[SUP] 5 6 [/SUP], Benjamin Huynh[SUP] 7 [/SUP], Kirsten Bibbins-Domingo[SUP] 8 [/SUP], M Maria Glymour[SUP] 9 [/SUP], Andrew C Stokes[SUP] 4 [/SUP]
Affiliations
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.
. 2026 Mar 20;12(12):eaef5697.
doi: 10.1126/sciadv.aef5697. Epub 2026 Mar 18.
Applying machine learning to identify unrecognized COVID-19 deaths recorded as other causes of death in the United States
Mathew V Kiang[SUP] 1 [/SUP], Zehang Richard Li[SUP] 2 [/SUP], Elizabeth Wrigley-Field[SUP] 3 [/SUP], Rafeya V Raquib[SUP] 4 [/SUP], Dielle J Lundberg[SUP] 4 [/SUP], Eugenio Paglino[SUP] 5 6 [/SUP], Benjamin Huynh[SUP] 7 [/SUP], Kirsten Bibbins-Domingo[SUP] 8 [/SUP], M Maria Glymour[SUP] 9 [/SUP], Andrew C Stokes[SUP] 4 [/SUP]
Affiliations
- PMID: 41849604
- PMCID: PMC12998511
- DOI: 10.1126/sciadv.aef5697
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.