TY - JOUR
T1 - Developing a COVID-19 mortality risk prediction model when individual-level data are not available
AU - Barda, Noam
AU - Riesel, Dan
AU - Akriv, Amichay
AU - Levy, Joseph
AU - Finkel, Uriah
AU - Yona, Gal
AU - Greenfeld, Daniel
AU - Sheiba, Shimon
AU - Somer, Jonathan
AU - Bachmat, Eitan
AU - Rothblum, Guy N.
AU - Shalit, Uri
AU - Netzer, Doron
AU - Balicer, Ran
AU - Dagan, Noa
N1 - Funding Information:
We want to thank Adi Berliner, Shay Ben-Shahar, Anna Kuperberg, Reut Ohana, Nurit Man, Irena Livshitz, Alon Schwartz, Nir Shahar, and Ilana Roitman for contributing to the model’s implementation. We want to thank Mark Katz, Anna Kuperberg, Morton Leibowitz, and Oren Oster for helping with the outcome definition. We want to thank Shay Perchik, Michael Lischinsky, and Galit Shaham for helping with Quality Assurance. We want to thank Ilan Gofer for organizing the data. G.N.R. reports grants from Israel Science Foundation, grants from Israel-US Binational Science Foundation, grants from European Research Council, and grants from Amazon Research Award during the conduct of the study. U.S. reports personal fees from K-health, grants from Israel Science Foundation, and grants from Yad Hanadiv, outside the submitted work.
Publisher Copyright:
© 2020, The Author(s).
PY - 2020
Y1 - 2020
N2 - At the COVID-19 pandemic onset, when individual-level data of COVID-19 patients were not yet available, there was already a need for risk predictors to support prevention and treatment decisions. Here, we report a hybrid strategy to create such a predictor, combining the development of a baseline severe respiratory infection risk predictor and a post-processing method to calibrate the predictions to reported COVID-19 case-fatality rates. With the accumulation of a COVID-19 patient cohort, this predictor is validated to have good discrimination (area under the receiver-operating characteristics curve of 0.943) and calibration (markedly improved compared to that of the baseline predictor). At a 5% risk threshold, 15% of patients are marked as high-risk, achieving a sensitivity of 88%. We thus demonstrate that even at the onset of a pandemic, shrouded in epidemiologic fog of war, it is possible to provide a useful risk predictor, now widely used in a large healthcare organization.
AB - At the COVID-19 pandemic onset, when individual-level data of COVID-19 patients were not yet available, there was already a need for risk predictors to support prevention and treatment decisions. Here, we report a hybrid strategy to create such a predictor, combining the development of a baseline severe respiratory infection risk predictor and a post-processing method to calibrate the predictions to reported COVID-19 case-fatality rates. With the accumulation of a COVID-19 patient cohort, this predictor is validated to have good discrimination (area under the receiver-operating characteristics curve of 0.943) and calibration (markedly improved compared to that of the baseline predictor). At a 5% risk threshold, 15% of patients are marked as high-risk, achieving a sensitivity of 88%. We thus demonstrate that even at the onset of a pandemic, shrouded in epidemiologic fog of war, it is possible to provide a useful risk predictor, now widely used in a large healthcare organization.
KW - epidemiology
UR - http://www.scopus.com/inward/record.url?scp=85090324118&partnerID=8YFLogxK
U2 - 10.1038/s41467-020-18297-9
DO - 10.1038/s41467-020-18297-9
M3 - Article
C2 - 32895375
AN - SCOPUS:85090324118
VL - 11
JO - Nature Communications
JF - Nature Communications
SN - 2041-1723
IS - 1
M1 - 4439
ER -