TY - JOUR
T1 - App-based COVID-19 syndromic surveillance and prediction of hospital admissions in COVID Symptom Study Sweden
AU - Kennedy, Beatrice
AU - Fitipaldi, Hugo
AU - Hammar, Ulf
AU - Maziarz, Marlena
AU - Tsereteli, Neli
AU - Oskolkov, Nikolay
AU - Varotsis, Georgios
AU - Franks, Camilla A.
AU - Nguyen, Diem
AU - Spiliopoulos, Lampros
AU - Adami, Hans Olov
AU - Björk, Jonas
AU - Engblom, Stefan
AU - Fall, Katja
AU - Grimby-Ekman, Anna
AU - Litton, Jan Eric
AU - Martinell, Mats
AU - Oudin, Anna
AU - Sjöström, Torbjörn
AU - Timpka, Toomas
AU - Sudre, Carole H.
AU - Graham, Mark S.
AU - du Cadet, Julien Lavigne
AU - Chan, Andrew T.
AU - Davies, Richard
AU - Ganesh, Sajaysurya
AU - May, Anna
AU - Ourselin, Sébastien
AU - Pujol, Joan Capdevila
AU - Selvachandran, Somesh
AU - Wolf, Jonathan
AU - Spector, Tim D.
AU - Steves, Claire J.
AU - Gomez, Maria F.
AU - Franks, Paul W.
AU - Fall, Tove
N1 - Publisher Copyright:
© 2022, The Author(s).
PY - 2022/12
Y1 - 2022/12
N2 - The app-based COVID Symptom Study was launched in Sweden in April 2020 to contribute to real-time COVID-19 surveillance. We enrolled 143,531 study participants (≥18 years) who contributed 10.6 million daily symptom reports between April 29, 2020 and February 10, 2021. Here, we include data from 19,161 self-reported PCR tests to create a symptom-based model to estimate the individual probability of symptomatic COVID-19, with an AUC of 0.78 (95% CI 0.74–0.83) in an external dataset. These individual probabilities are employed to estimate daily regional COVID-19 prevalence, which are in turn used together with current hospital data to predict next week COVID-19 hospital admissions. We show that this hospital prediction model demonstrates a lower median absolute percentage error (MdAPE: 25.9%) across the five most populated regions in Sweden during the first pandemic wave than a model based on case notifications (MdAPE: 30.3%). During the second wave, the error rates are similar. When we apply the same model to an English dataset, not including local COVID-19 test data, we observe MdAPEs of 22.3% and 19.0% during the first and second pandemic waves, respectively, highlighting the transferability of the prediction model.
AB - The app-based COVID Symptom Study was launched in Sweden in April 2020 to contribute to real-time COVID-19 surveillance. We enrolled 143,531 study participants (≥18 years) who contributed 10.6 million daily symptom reports between April 29, 2020 and February 10, 2021. Here, we include data from 19,161 self-reported PCR tests to create a symptom-based model to estimate the individual probability of symptomatic COVID-19, with an AUC of 0.78 (95% CI 0.74–0.83) in an external dataset. These individual probabilities are employed to estimate daily regional COVID-19 prevalence, which are in turn used together with current hospital data to predict next week COVID-19 hospital admissions. We show that this hospital prediction model demonstrates a lower median absolute percentage error (MdAPE: 25.9%) across the five most populated regions in Sweden during the first pandemic wave than a model based on case notifications (MdAPE: 30.3%). During the second wave, the error rates are similar. When we apply the same model to an English dataset, not including local COVID-19 test data, we observe MdAPEs of 22.3% and 19.0% during the first and second pandemic waves, respectively, highlighting the transferability of the prediction model.
UR - http://www.scopus.com/inward/record.url?scp=85128664211&partnerID=8YFLogxK
U2 - 10.1038/s41467-022-29608-7
DO - 10.1038/s41467-022-29608-7
M3 - Article
C2 - 35449172
AN - SCOPUS:85128664211
SN - 2041-1723
VL - 13
JO - Nature Communications
JF - Nature Communications
IS - 1
M1 - 2110
ER -