Scientific Reports (Mar 2022)
Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study
- Ashley E. Mason,
- Frederick M. Hecht,
- Shakti K. Davis,
- Joseph L. Natale,
- Wendy Hartogensis,
- Natalie Damaso,
- Kajal T. Claypool,
- Stephan Dilchert,
- Subhasis Dasgupta,
- Shweta Purawat,
- Varun K. Viswanath,
- Amit Klein,
- Anoushka Chowdhary,
- Sarah M. Fisher,
- Claudine Anglo,
- Karena Y. Puldon,
- Danou Veasna,
- Jenifer G. Prather,
- Leena S. Pandya,
- Lindsey M. Fox,
- Michael Busch,
- Casey Giordano,
- Brittany K. Mercado,
- Jining Song,
- Rafael Jaimes,
- Brian S. Baum,
- Brian A. Telfer,
- Casandra W. Philipson,
- Paula P. Collins,
- Adam A. Rao,
- Edward J. Wang,
- Rachel H. Bandi,
- Bianca J. Choe,
- Elissa S. Epel,
- Stephen K. Epstein,
- Joanne B. Krasnoff,
- Marco B. Lee,
- Shi-Wen Lee,
- Gina M. Lopez,
- Arpan Mehta,
- Laura D. Melville,
- Tiffany S. Moon,
- Lilianne R. Mujica-Parodi,
- Kimberly M. Noel,
- Michael A. Orosco,
- Jesse M. Rideout,
- Janet D. Robishaw,
- Robert M. Rodriguez,
- Kaushal H. Shah,
- Jonathan H. Siegal,
- Amarnath Gupta,
- Ilkay Altintas,
- Benjamin L. Smarr
Affiliations
- Ashley E. Mason
- Osher Center for Integrative Health, University of California San Francisco
- Frederick M. Hecht
- Osher Center for Integrative Health, University of California San Francisco
- Shakti K. Davis
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Joseph L. Natale
- Halıcıoğlu Data Science Institute, University of California San Diego
- Wendy Hartogensis
- Osher Center for Integrative Health, University of California San Francisco
- Natalie Damaso
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Kajal T. Claypool
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Stephan Dilchert
- Department of Management, Zicklin School of Business, Baruch College, The City University of New York
- Subhasis Dasgupta
- San Diego Supercomputer Center, University of California San Diego
- Shweta Purawat
- San Diego Supercomputer Center, University of California San Diego
- Varun K. Viswanath
- Department of Electrical and Computer Engineering, University of California San Diego
- Amit Klein
- Department of Bioengineering: Bioinformatics, University of California San Diego
- Anoushka Chowdhary
- Osher Center for Integrative Health, University of California San Francisco
- Sarah M. Fisher
- Department of Psychology, Drexel University
- Claudine Anglo
- Osher Center for Integrative Health, University of California San Francisco
- Karena Y. Puldon
- Osher Center for Integrative Health, University of California San Francisco
- Danou Veasna
- Osher Center for Integrative Health, University of California San Francisco
- Jenifer G. Prather
- Osher Center for Integrative Health, University of California San Francisco
- Leena S. Pandya
- Osher Center for Integrative Health, University of California San Francisco
- Lindsey M. Fox
- Osher Center for Integrative Health, University of California San Francisco
- Michael Busch
- Vitalant Research Institute, University of California San Francisco
- Casey Giordano
- Department of Psychology, University of Minnesota - Twin Cities
- Brittany K. Mercado
- Love School of Business, Elon University
- Jining Song
- San Diego Supercomputer Center, University of California San Diego
- Rafael Jaimes
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Brian S. Baum
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Brian A. Telfer
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Casandra W. Philipson
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Paula P. Collins
- MIT Lincoln Laboratory, Massachusetts Institute of Technology
- Adam A. Rao
- School of Medicine, University of California San Francisco
- Edward J. Wang
- Department of Electrical and Computer Engineering, University of California San Diego
- Rachel H. Bandi
- Department of Anesthesiology, Northwestern McGaw Medical Center, Feinberg School of Medicine
- Bianca J. Choe
- Department of Emergency Medicine, University of California Los Angeles Health
- Elissa S. Epel
- Center for Health and Community, University of California San Francisco
- Stephen K. Epstein
- Department of Emergency Medicine, Beth Israel Deaconess Medical Center Boston
- Joanne B. Krasnoff
- Schmidt College of Medicine, Florida Atlantic University
- Marco B. Lee
- Department of Neurosurgery, Santa Clara Valley Medical Center, Stanford University
- Shi-Wen Lee
- Department of Emergency Medicine, Jamaica Hospital Medical Center
- Gina M. Lopez
- Department of Emergency Medicine, Boston Medical Center
- Arpan Mehta
- Department of Anesthesiology: Pain Management and Perioperative Medicine, University of Miami
- Laura D. Melville
- Department of Emergency Medicine, New York Presbyterian Brooklyn Methodist Hospital
- Tiffany S. Moon
- Department of Anesthesiology and Pain Management, University of Texas Southwestern
- Lilianne R. Mujica-Parodi
- Department of Biomedical Engineering, Renaissance School of Medicine, Stony Brook University
- Kimberly M. Noel
- Stony Brook Medicine, Stony Brook University Renaissance School of Medicine
- Michael A. Orosco
- Department of Anesthesia: Perioperative and Pain Medicine, Kaiser Permanente San Diego
- Jesse M. Rideout
- Department of Emergency Medicine, Tufts Medical Center
- Janet D. Robishaw
- Schmidt College of Medicine, Florida Atlantic University
- Robert M. Rodriguez
- Department of Emergency Medicine, University of California San Francisco
- Kaushal H. Shah
- Weill Cornell Medical Center, Weill Cornell Medical School
- Jonathan H. Siegal
- New York Presbyterian Queens, Weill-Cornell Medical College
- Amarnath Gupta
- Halıcıoğlu Data Science Institute, University of California San Diego
- Ilkay Altintas
- Halıcıoğlu Data Science Institute, University of California San Diego
- Benjamin L. Smarr
- Halıcıoğlu Data Science Institute, University of California San Diego
- DOI
- https://doi.org/10.1038/s41598-022-07314-0
- Journal volume & issue
-
Vol. 12,
no. 1
pp. 1 – 15
Abstract
Abstract Early detection of diseases such as COVID-19 could be a critical tool in reducing disease transmission by helping individuals recognize when they should self-isolate, seek testing, and obtain early medical intervention. Consumer wearable devices that continuously measure physiological metrics hold promise as tools for early illness detection. We gathered daily questionnaire data and physiological data using a consumer wearable (Oura Ring) from 63,153 participants, of whom 704 self-reported possible COVID-19 disease. We selected 73 of these 704 participants with reliable confirmation of COVID-19 by PCR testing and high-quality physiological data for algorithm training to identify onset of COVID-19 using machine learning classification. The algorithm identified COVID-19 an average of 2.75 days before participants sought diagnostic testing with a sensitivity of 82% and specificity of 63%. The receiving operating characteristic (ROC) area under the curve (AUC) was 0.819 (95% CI [0.809, 0.830]). Including continuous temperature yielded an AUC 4.9% higher than without this feature. For further validation, we obtained SARS CoV-2 antibody in a subset of participants and identified 10 additional participants who self-reported COVID-19 disease with antibody confirmation. The algorithm had an overall ROC AUC of 0.819 (95% CI [0.809, 0.830]), with a sensitivity of 90% and specificity of 80% in these additional participants. Finally, we observed substantial variation in accuracy based on age and biological sex. Findings highlight the importance of including temperature assessment, using continuous physiological features for alignment, and including diverse populations in algorithm development to optimize accuracy in COVID-19 detection from wearables.
