Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

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

Title: Symptom clusters in COVID-19: A potential clinical prediction tool from the COVID Symptom Study app
Authors: 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 WJ; Guo CG; Lo CH; Ganesh S; Buwe A; Pujol JC; du Cadet JL; Visconti A; Freidin MB; Moustafa JSES; Falchi M; Davies R; Gomez MF; Fall T; Cardoso MJ; Wolf J; Franks PW; Chan AT; Spector TD; Steves CJ; Ourselin S
Contributors: C. Sudre; K. Lee; M. Lochlainn; T. Varsavsky; B. Murray; M. Graham; C. Menni; M. Modat; R. Bowyer; L. Nguyen; D. Drew; A. Joshi; W. Ma; C. Guo; C. Lo; S. Ganesh; A. Buwe; J. Pujol; J. du Cadet; A. Visconti; M. Freidin; J. Moustafa; M. Falchi; R. Davie; M. Gomez; T. Fall; M. Cardoso; J. Wolf; P. Frank; A. Chan; T. Spector; C. Steve; S. Ourselin
Publication Year: 2021
Collection: The University of Milan: Archivio Istituzionale della Ricerca (AIR)
Subject Terms: Settore MEDS-24/A - Statistica medica
Description: 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.
Document Type: article in journal/newspaper
Language: English
Relation: info:eu-repo/semantics/altIdentifier/pmid/33741586; info:eu-repo/semantics/altIdentifier/wos/WOS:000633443000007; volume:7; issue:12; firstpage:1; lastpage:7; numberofpages:7; journal:SCIENCE ADVANCES; https://hdl.handle.net/2434/1097069
DOI: 10.1126/sciadv.abd4177
Availability: https://hdl.handle.net/2434/1097069; https://doi.org/10.1126/sciadv.abd4177
Rights: info:eu-repo/semantics/openAccess
Accession Number: edsbas.B44B1ECD
Database: BASE