Unknown

Dataset Information

0

Symptom clusters in COVID-19: A potential clinical prediction tool from the COVID Symptom Study app.


ABSTRACT: 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.

SUBMITTER: Sudre CH 

PROVIDER: S-EPMC7978420 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

altmetric image

Publications

Symptom clusters in COVID-19: A potential clinical prediction tool from the COVID Symptom Study app.

Sudre Carole H CH   Lee Karla A KA   Lochlainn Mary Ni MN   Varsavsky Thomas T   Murray Benjamin B   Graham Mark S MS   Menni Cristina C   Modat Marc M   Bowyer Ruth C E RCE   Nguyen Long H LH   Drew David A DA   Joshi Amit D AD   Ma Wenjie W   Guo Chuan-Guo CG   Lo Chun-Han CH   Ganesh Sajaysurya S   Buwe Abubakar A   Pujol Joan Capdevila JC   du Cadet Julien Lavigne JL   Visconti Alessia A   Freidin Maxim B MB   El-Sayed Moustafa Julia S JS   Falchi Mario M   Davies Richard R   Gomez Maria F MF   Fall Tove T   Cardoso M Jorge MJ   Wolf Jonathan J   Franks Paul W PW   Chan Andrew T AT   Spector Tim D TD   Steves Claire J CJ   Ourselin Sébastien S  

Science advances 20210319 12


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  ...[more]

Similar Datasets

| S-EPMC9023535 | biostudies-literature
| S-EPMC8282115 | biostudies-literature
| S-EPMC9811485 | biostudies-literature
| S-EPMC9663188 | biostudies-literature
| S-EPMC10880228 | biostudies-literature
| PRJEB43387 | ENA
| S-EPMC10410382 | biostudies-literature
| S-EPMC11409358 | biostudies-literature
| S-EPMC7340163 | biostudies-literature
| S-EPMC8262614 | biostudies-literature