logo
ResearchBunny Logo
Abstract
This study investigated the accuracy of a machine learning model in detecting COVID-19 infection using data from wearable devices and self-reported symptoms. A total of 38,911 individuals were enrolled, with 1118 testing positive and 7032 negative for COVID-19. An explainable gradient boosting prediction model achieved an AUC of 0.83 (symptomatic cohort) and 0.70 (all individuals, excluding self-reported symptoms). The model adapted to different sensor data and engagement levels, outperforming state-of-the-art algorithms in similar conditions. This approach enables scalable, passive monitoring of COVID-19 infection even in settings without self-reported symptoms.
Publisher
npj Digital Medicine
Published On
Dec 08, 2021
Authors
Matteo Gadaleta, Jennifer M. Radin, Katie Baca-Motes, Edward Ramos, Vik Khetarpal, Eric J. Topol, Steven R. Steinbulh, Giorgio Quer
Tags
COVID-19
machine learning
wearable devices
predictive model
passive monitoring
public health
sensor data

Related Publications

Explore these studies to deepen your understanding of the subject.

Prediction of mortality risk and duration of hospitalization of COVID-19 patients with chronic comorbidities based on machine learning algorithms
Medicine and Health

Prediction of mortality risk and duration of hospitalization of COVID-19 patients with chronic comorbidities based on machine learning algorithms

P. Amiri, M. Montazeri, et al.

Stylistic and linguistic variations in compliments: an empirical analysis of children's gender schema development with machine learning algorithms
Linguistics and Languages

Stylistic and linguistic variations in compliments: an empirical analysis of children's gender schema development with machine learning algorithms

X. Liao and Y. Zhang

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets
Medicine and Health

Design and Analysis of a Deep Learning Ensemble Framework Model for the Detection of COVID-19 and Pneumonia Using Large-Scale CT Scan and X-ray Image Datasets

X. Xue, S. Chinnaperumal, et al.

Unsupervised machine learning to investigate trajectory patterns of COVID-19 symptoms and physical activity measured via the MyHeart Counts App and smart devices
Medicine and Health

Unsupervised machine learning to investigate trajectory patterns of COVID-19 symptoms and physical activity measured via the MyHeart Counts App and smart devices

V. Gupta, S. Kariotis, et al.

Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny