Passive detection of COVID-19 with wearable sensors and explainable machine learning algorithms

  1. Matteo Gadaleta
  2. Jennifer M. Radin
  3. Katie Baca-Motes
  4. Edward Ramos
  5. Vik Kheterpal
  6. Eric J. Topol
  7. Steven R. Steinhubl
  8. Giorgio Quer

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Individual smartwatch or fitness band sensor data in the setting of COVID-19 has shown promise to identify symptomatic and pre-symptomatic infection or the need for hospitalization, correlations between peripheral temperature and self-reported fever, and an association between changes in heart-rate-variability and infection. In our study, a total of 38,911 individuals (61% female, 15% over 65) have been enrolled between March 25, 2020 and April 3, 2021, with 1118 reported testing positive and 7032 negative for COVID-19 by nasopharyngeal PCR swab test. We propose an explainable gradient boosting prediction model based on decision trees for the detection of COVID-19 infection that can adapt to the absence of self-reported symptoms and to the available sensor data, and that can explain the importance of each feature and the post-test-behavior for the individuals. We tested it in a cohort of symptomatic individuals who exhibited an AUC of 0.83 [0.81–0.85], or AUC = 0.78 [0.75–0.80] when considering only data before the test date, outperforming state-of-the-art algorithm in these conditions. The analysis of all individuals (including asymptomatic and pre-symptomatic) when self-reported symptoms were excluded provided an AUC of 0.78 [0.76–0.79], or AUC of 0.70 [0.69–0.72] when considering only data before the test date. Extending the use of predictive algorithms for detection of COVID-19 infection based only on passively monitored data from any device, we showed that it is possible to scale up this platform and apply the algorithm in other settings where self-reported symptoms can not be collected.

Article activity feed

  1. Version published to 10.1038/s41746-021-00533-1
  2. ScreenIT

    SciScore for 10.1101/2021.08.05.21261626: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:
    Limitations: In DETECT, all data is participant reported with no validation of the accuracy of self-reported symptoms, test dates or results. While we were able to collect continuous data, the amount of sensor data collected, or the accuracy of self-reported symptoms, depends entirely on the willingness of the participants to wear the sensor and accurately report how they feel. Despite the fact that the information collected may not be as accurate as in a controlled laboratory setting, previous work has demonstrated the value of participant-reported outcomes.28-30 In the data analysis, among the people who reported the COVID-19 test outcome (active participants), we separated participants who reported at least one symptom from those who did not report any symptoms. The app indeed did not have an explicit way to report the absence of symptoms, so potentially some symptomatic individual may have not reported their symptoms. Furthermore, this study is based on the aggregation of continuously monitored data into a finite number of daily features. A recent study has provided new insights about the analysis of intra-day changes for monitoring physiological variations,31 that may be used in future studies. Changes in more advanced metrics, like respiratory rate,17 peripheral temperature10 or HRV,12 may also prove to add to the prediction of a COVID-19 infection, even if they have been marginally considered in our work since only a small fraction of participants were providing this t...

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    Results from scite Reference Check: We found no unreliable references.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  3. Version published to 10.1101/2021.08.05.21261626v1 on medRxiv