Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Mar 19;7(12):eabd4177.
doi: 10.1126/sciadv.abd4177. Print 2021 Mar.

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

Carole H Sudre  1   2   3 , Karla A Lee  4 , Mary Ni Lochlainn  4 , Thomas Varsavsky  5 , Benjamin Murray  5 , Mark S Graham  5 , Cristina Menni  4 , Marc Modat  5 , Ruth C E Bowyer  4 , Long H Nguyen  6 , David A Drew  6 , Amit D Joshi  6 , Wenjie Ma  6 , Chuan-Guo Guo  6 , Chun-Han Lo  6 , Sajaysurya Ganesh  7 , Abubakar Buwe  7 , Joan Capdevila Pujol  7 , Julien Lavigne du Cadet  7 , Alessia Visconti  4 , Maxim B Freidin  4 , Julia S El-Sayed Moustafa  4 , Mario Falchi  4 , Richard Davies  7 , Maria F Gomez  8 , Tove Fall  8 , M Jorge Cardoso  5 , Jonathan Wolf  7 , Paul W Franks  4   8 , Andrew T Chan  6 , Tim D Spector  4 , Claire J Steves  4 , Sébastien Ourselin  1
Affiliations

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

Carole H Sudre et al. Sci Adv. .

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.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1. Illustrative representation of the 6 clusters.
(Top) Frequency of positive answers per symptom across days for each cluster (darker, reported more frequently) and (bottom) associated Z-score of presentation of symptoms over overall symptom distribution (red, reported more than average; blue, reported less than average). The clusters are ordered from left to right by rates of reported hospital visit with associated rates of respiratory support of 1.5, 4.4, 3.7, 8.6, 9.9, and 19.8%, respectively.
Fig. 2
Fig. 2. Confusion matrix showing cluster prediction using projections based on 2 to 9 days after onset of symptoms.
By day 5 of COVID-19, the cluster in which a participant falls can be predicted with 72% weighted average precision.
Fig. 3
Fig. 3. Frequency of occurrence and duration of symptoms at 5 days.
(Left) Percentage of occurrence of symptoms at 5 days per cluster. (Right) Z-score in duration of symptom when occurring over the five first days.
Fig. 4
Fig. 4. Flowchart showing entry of participants into analysis.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Emanuel E. J., Persad G., Upshur R., Thome B., Parker M., Glickman A., Zhang C., Boyle C., Smith M., Phillips J. P., Fair allocation of scarce medical resources in the time of Covid-19. N. Engl. J. Med. 382, 2049–2055 (2020). - PubMed
    1. Phua J., Weng L., Ling L., Egi M., Lim C. M., Divatia J. V., Shrestha B. R., Arabi Y. M., Ng J., Gomersall C. D., Nishimura M., Koh Y., Du B.; Asian Critical Care Clinical Trials Group , Intensive care management of coronavirus disease 2019 (COVID-19): Challenges and recommendations. Lancet Respir. Med. 8, 506–517 (2020). - PMC - PubMed
    1. Drew D. A., Nguyen L. H., Steves C. J., Menni C., Freydin M., Varsavsky T., Sudre C. H., Cardoso M. J., Ourselin S., Wolf J., Spector T. D., Chan A. T.; COPE Consortium , Rapid implementation of mobile technology for real-time epidemiology of COVID-19. Science 368, 1362–1367 (2020). - PMC - PubMed
    1. Menni C., Valdes A. M., Freidin M. B., Sudre C. H., Nguyen L. H., Drew D. A., Ganesh S., Varsavsky T., Cardoso M. J., El-Sayed Moustafa J. S., Visconti A., Hysi P., Bowyer R. C. E., Mangino M., Falchi M., Wolf J., Ourselin S., Chan A. T., Steves C. J., Spector T. D., Real-time tracking of self-reported symptoms to predict potential COVID-19. Nat. Med. 26, 1037–1040 (2020). - PMC - PubMed
    1. Mackett A. J., Keevil V. L., COVID-19 and gastrointestinal symptoms—A case report. Geriatrics 5, 31 (2020). - PMC - PubMed

Publication types