Symptom clusters in COVID-19: A potential clinical prediction tool from the COVID Symptom Study app.
JSON
Sudre CH, Lee KA, Lochlainn MN, Varsavsky T, Murray B, Graham MS, Menni C, Modat M, Bowyer RCE, Nguyen LH, Drew DA, Joshi AD, Ma W, Guo CG, Lo CH, Ganesh S, Buwe A, Pujol JC, du Cadet JL, Visconti A, Freidin MB, El-Sayed Moustafa JS, Falchi M, Davies R, Gomez MF, Fall T, Cardoso MJ, Wolf J, Franks PW, Chan AT, Spector TD, Steves CJ, Ourselin S
Sci Adv 7 (12) - [2021-03-00; online 2021-03-19]
As no one symptom can predict disease severity or the need for dedicated medical support in coronavirus disease 2019 (COVID-19), we asked whether documenting symptom time series over the first few days informs outcome. Unsupervised time series clustering over symptom presentation was performed on data collected from a training dataset of completed cases enlisted early from the COVID Symptom Study Smartphone application, yielding six distinct symptom presentations. Clustering was validated on an independent replication dataset between 1 and 28 May 2020. Using the first 5 days of symptom logging, the ROC-AUC (receiver operating characteristic - area under the curve) of need for respiratory support was 78.8%, substantially outperforming personal characteristics alone (ROC-AUC 69.5%). Such an approach could be used to monitor at-risk patients and predict medical resource requirements days before they are required.
PubMed 33741586
DOI 10.1126/sciadv.abd4177
Crossref 10.1126/sciadv.abd4177
pmc: PMC7978420
pii: 7/12/eabd4177