Can predicting COVID-19 mortality in a European cohort using only demographic and comorbidity data surpass age-based prediction: An externally validated study.

Avishek ChatterjeeGuangyao WuSergey PrimakovCary OberijeHenry WoodruffPieter L KubbenRonald HenryMarcel J H AriesMartijn BeudelPeter G NoordzijTom DormansNiels C Gritters van den OeverJoop P van den BerghCaroline E Wyers Suat SimsekRenée DoumaAuke C ReidingaMartijn D de KruifJulien GuiotAnne-Noelle FrixRenaud LouisMichel MoutschenPierre LovinfossePhilippe Lambin

Published in: PloS one (2021)

When applied to an external validation set, we found that an age-only mortality model outperformed all modeling attempts (curated on www.covid19risk.ai) using three feature selection methods on 22 demographic and comorbid features.

Keyphrases

coronavirus disease
sars cov
cardiovascular events
risk factors
artificial intelligence
electronic health record
respiratory syndrome coronavirus
big data
deep learning