Symptom clusters in COVID-19: A potential clinical prediction tool from the COVID Symptom Study app.
Carole Helene SudreKarla A LeeMary Ni LochlainnThomas VarsavskyBenjamin MurrayMark S GrahamCristina MenniMarc ModatRuth C E BowyerLong H NguyenDavid A DrewAmit D JoshiWenjie MaChuan-Guo GuoChun-Han LoSajaysurya GaneshAbubakar BuweJoan Capdevila PujolJulien Lavigne du CadetAlessia ViscontiMaxim B FreidinJulia El-Sayed MoustafaMario FalchiRichard DaviesMaria F GomezChristoph NowakM Jorge CardosoJonathan WolfPaul W FranksAndrew T ChanTimothy D SpectorClaire J StevesSébastien OurselinPublished in: Science advances (2021)
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.