A machine learning approach identifies distinct early-symptom cluster phenotypes which correlate with hospitalization, failure to return to activities, and prolonged COVID-19 symptoms.

Nusrat J EpsiJohn H PowersDavid A LindholmKatrin MendeAllison MalloyAnuradha GanesanNikhil HuprikarTahaniyat LalaniAlfred SmithRupal M ModyMilissa U JonesSamantha E BazanRhonda E ColomboChristopher J ColomboEvan C EwersDerek T LarsonCatherine M Berjohn Carlos J MaldonadoPaul W BlairJosh ChenowethDavid L SaundersJeffrey LivezeyRyan C MavesMargaret Sanchez EdwardsJulia S RozmanMark P SimonsDavid R TribbleBrian K AganTimothy H BurgessSimon D Pollettnull null

Published in: PloS one (2023)

We identified early symptom profiles potentially associated with hospitalization, return-to-activities, long-term symptoms, and inflammatory profiles. These findings may assist in patient prognosis, including prediction of long COVID risk.

Keyphrases

coronavirus disease
sars cov
machine learning
oxidative stress
sleep quality
genome wide
artificial intelligence
patient reported
gene expression
big data
physical activity
dna methylation