BMJ Open (Jun 2022)
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)
- ,
- Stefanie Aeschbacher,
- David Conen,
- Diederick E Grobbee,
- Raphael Twerenbold,
- Thomas Lung,
- Theo Rispens,
- Jakob Kjellberg,
- Lorenz Risch,
- Martin Risch,
- Marianna Mitratza,
- Harald Renz,
- Spiros Denaxas,
- Billy Franks,
- Diederick Grobbee,
- Martina Rothenbühler,
- Janneke Wijgert,
- Santiago Montes,
- Richard Dobson,
- Hans Reitsma,
- Christian Simon,
- Titia Leurink,
- Charisma Hehakaya,
- Patricia Bruijning,
- Kirsten Grossmann,
- Ornella C Weideli,
- Marc Kovac,
- Fiona Pereira,
- Nadia Wohlwend,
- Corina Risch,
- Dorothea Hillmann,
- Daniel Leibovitz,
- Vladimir Kovacevic,
- Andjela Markovic,
- Paul Klaver,
- Timo B Brakenhoff,
- George S Downward,
- Ariel Dowling,
- Maureen Cronin,
- Brianna M Goodale,
- Brianna Goodale,
- Ornella Weideli,
- Regien Stokman,
- Hans Van Dijk,
- Eric Houtman,
- Jon Bouwman,
- Kay Hage,
- Lotte Smets,
- Marcel van Willigen,
- Maui Chodura,
- Niki de Vink,
- Tessa Heikamp,
- Timo Brakenhoff,
- Wendy van Scherpenzeel,
- Wout Aarts,
- Alison Kuchta,
- Antonella Chiucchiuini,
- Steve Emby,
- Annemarijn Douwes,
- George Downward,
- Nathalie Vigot,
- Pieter Stolk,
- Duco Veen,
- Daniel Oberski,
- Amos Folarin,
- Pablo Fernandez Medina,
- Eskild Fredslund
Affiliations
- Stefanie Aeschbacher
- Cardiology Division, Department of Medicine, University Hospital Basel, Basel, Switzerland
- David Conen
- Department of Medicine, McMaster University, Hamilton, Ontario, Canada
- Diederick E Grobbee
- Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht (UMCU), Utrecht, The Netherlands
- Raphael Twerenbold
- 2 Department of Cardiology, University Hospital Basel, Basel, Switzerland
- Thomas Lung
- 3 Dr Risch Medical Laboratory, Buchs, Switzerland
- Theo Rispens
- Sanquin Research, Amsterdam, The Netherlands
- Jakob Kjellberg
- VIVE - The Danish Center for Social Science Research, Copenhagen, Denmark
- Lorenz Risch
- 1 Dr Risch Medical Laboratory, Vaduz, Liechtenstein
- Martin Risch
- 1 Dr Risch Medical Laboratory, Vaduz, Liechtenstein
- Marianna Mitratza
- Department of Public Health, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
- Harald Renz
- 24 Institute of Laboratory Medicine and Pathobiochemistry, Phillips University of Marburg, Marburg, Germany
- Spiros Denaxas
- 1 Institute of Health Informatics, University College London, London, UK
- Billy Franks
- 12 Julius Clinical, Zeist, The Netherlands
- Diederick Grobbee
- Martina Rothenbühler
- Department of Cardiology, University of Bern, Bern, Switzerland
- Janneke Wijgert
- Santiago Montes
- 16 Roche Diagnostics Nederland B.V, Almere, The Netherlands
- Richard Dobson
- 4Institute of Psychiatry, Psychology and Neuroscience, King’s College London
- Hans Reitsma
- Christian Simon
- Titia Leurink
- Charisma Hehakaya
- Patricia Bruijning
- 12 Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht, The Netherlands
- Kirsten Grossmann
- 1 Dr Risch Medical Laboratory, Vaduz, Liechtenstein
- Ornella C Weideli
- 1 Dr Risch Medical Laboratory, Vaduz, Liechtenstein
- Marc Kovac
- 3 Dr Risch Medical Laboratory, Buchs, Switzerland
- Fiona Pereira
- 6 Department of Metabolism, Digestive Diseases and Reproduction, Imperial College London, London, UK
- Nadia Wohlwend
- 3 Dr Risch Medical Laboratory, Buchs, Switzerland
- Corina Risch
- 3 Dr Risch Medical Laboratory, Buchs, Switzerland
- Dorothea Hillmann
- 3 Dr Risch Medical Laboratory, Buchs, Switzerland
- Daniel Leibovitz
- 9 Ava AG, Zurich, Switzerland
- Vladimir Kovacevic
- 9 Ava AG, Zurich, Switzerland
- Andjela Markovic
- 9 Ava AG, Zurich, Switzerland
- Paul Klaver
- 12 Julius Clinical, Zeist, The Netherlands
- Timo B Brakenhoff
- 12 Julius Clinical, Zeist, The Netherlands
- George S Downward
- 13 UMC Utrecht, Utrecht, The Netherlands
- Ariel Dowling
- 15 Takeda Pharmaceuticals, Digital Clinical Devices, Cambridge, UK
- Maureen Cronin
- industry representative
- Brianna M Goodale
- 9 Ava AG, Zurich, Switzerland
- Brianna Goodale
- Ornella Weideli
- Regien Stokman
- Hans Van Dijk
- Eric Houtman
- Jon Bouwman
- Kay Hage
- Lotte Smets
- Marcel van Willigen
- Maui Chodura
- Niki de Vink
- Tessa Heikamp
- Timo Brakenhoff
- Wendy van Scherpenzeel
- Wout Aarts
- Alison Kuchta
- Antonella Chiucchiuini
- Steve Emby
- Annemarijn Douwes
- George Downward
- Institute for Risk Assessment Sciences, Utrecht University, Utrecht, Netherlands
- Nathalie Vigot
- Pieter Stolk
- Duco Veen
- Daniel Oberski
- Amos Folarin
- Pablo Fernandez Medina
- Eskild Fredslund
- DOI
- https://doi.org/10.1136/bmjopen-2021-058274
- Journal volume & issue
-
Vol. 12,
no. 6
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 numberISRCTN51255782; Pre-results.
