Investigation of the use of a sensor bracelet for the presymptomatic detection of changes in physiological parameters related to COVID-19: an interim analysis of a prospective cohort study (COVI-GAPP). Issue 6 (21st June 2022)

• Record Type: Journal Article
• Authors: Risch, Martin; Grossmann, Kirsten; Aeschbacher, Stefanie; Weideli, Ornella C; Kovac, Marc; Pereira, Fiona; Wohlwend, Nadia; Risch, Corina; Hillmann, Dorothea; Lung, Thomas; Renz, Harald; Twerenbold, Raphael; Rothenbühler, Martina; Leibovitz, Daniel; Kovacevic, Vladimir; Markovic, Andjela; Klaver, Paul; Brakenhoff, Timo B; Franks, Billy; Mitratza, Marianna; Downward, George S; Dowling, Ariel; Montes, Santiago; Grobbee, Diederick E; Cronin, Maureen; Conen, David; Goodale, Brianna M; Risch, Lorenz
• Other Names: author non-byline.; Cronin Maureen author non-byline.; Goodale Brianna author non-byline.; Kovacevic Vladimir author non-byline.; Grossmann Kirsten author non-byline.; Risch Lorenz author non-byline.; Risch Martin author non-byline.; Weideli Ornella author non-byline.; Conen David author non-byline.; Stokman Regien author non-byline.; Franks Billy author non-byline.; Dijk Hans Van author non-byline.; Klaver Paul author non-byline.; Houtman Eric author non-byline.; Bouwman Jon author non-byline.; Hage Kay author non-byline.; Smets Lotte author non-byline.; Willigen Marcel van author non-byline.; Chodura Maui author non-byline.; Vink Niki de author non-byline.; Heikamp Tessa author non-byline.; Brakenhoff Timo author non-byline.; Leurink Titia author non-byline.; Scherpenzeel Wendy van author non-byline.; Aarts Wout author non-byline.; Montes Santiago author non-byline.; Kuchta Alison author non-byline.; Simon Christian author non-byline.; Rispens Theo author non-byline.; Chiucchiuini Antonella author non-byline.; Dowling Ariel author non-byline.; Emby Steve author non-byline.; Douwes Annemarijn author non-byline.; Downward George author non-byline.; Vigot Nathalie author non-byline.; Stolk Pieter author non-byline.; Grobbee Diederick author non-byline.; Veen Duco author non-byline.; Reitsma Hans author non-byline.; Wijgert Janneke author non-byline.; Mitratza Marianna author non-byline.; Bruijning Patricia author non-byline.; Hehakaya Charisma author non-byline.; Oberski Daniel author non-byline.; Folarin Amos author non-byline.; Dobson Richard author non-byline.; Denaxas Spiros author non-byline.; Medina Pablo Fernandez author non-byline.; Fredslund Eskild author non-byline.; Kjellberg Jakob author non-byline.;
• Is Part Of: BMJ open. Volume 12:Issue 6(2022)
• Publication Date: 2022-06-21
• Subjects: COVID-19 -- Health informatics -- VIROLOGY -- Public health -- Infection control -- Health & safety; Medicine -- Research -- Periodicals; 610.72
• DOI: 10.1136/bmjopen-2021-058274
• Languages: English
• ISSNs: 2044-6055

Abstract

Abstract : Objectives: We investigated machinelearningbased identification of presymptomatic COVID-19 and detection of infection-related changes in physiology using a wearable device. Design: Interim analysis of a prospective cohort study. Setting, participants and interventions: Participants from a national cohort study in Liechtenstein were included. Nightly they wore the Ava-bracelet that measured respiratory rate (RR), heart rate (HR), HR variability (HRV), wrist-skin temperature (WST) and skin perfusion. SARS-CoV-2 infection was diagnosed by molecular and/or serological assays. Results: A total of 1.5 million hours of physiological data were recorded from 1163 participants (mean age 44±5.5 years). COVID-19 was confirmed in 127 participants of which, 66 (52%) had worn their device from baseline to symptom onset (SO) and were included in this analysis. Multi-level modelling revealed significant changes in five (RR, HR, HRV, HRV ratio and WST) device-measured physiological parameters during the incubation, presymptomatic, symptomatic and recovery periods of COVID-19 compared with baseline. The training set represented an 8-day long instance extracted from day 10 to day 2 before SO. The training set consisted of 40 days measurements from 66 participants. Based on a random split, the test set included 30% of participants and 70% were selected for the training set. The developed long short-term memory (LSTM) based recurrent neural network (RNN) algorithm had a recall (sensitivity) of 0.73 in the training set and 0.68 in the testing set when detecting COVID-19 up to 2 days prior to SO. Conclusion: Wearable sensor technology can enable COVID-19 detection during the presymptomatic period. Our proposed RNN algorithm identified 68% of COVID-19 positive participants 2 days prior to SO and will be further trained and validated in a randomised, single-blinded, two-period, two-sequence crossover trial. Trial registration number ISRCTN51255782; Pre-results.