Pre-symptomatic detection of COVID-19 from smartwatch data

Area of Science:

• Digital Health
• Epidemiology
• Wearable Technology

Background:

• Consumer wearable devices offer continuous vital sign monitoring for infectious disease surveillance.
• Smartwatch data has the potential for early detection of various health conditions.

Purpose of the Study:

• To investigate the utility of consumer smartwatch data for pre-symptomatic detection of coronavirus disease 2019 (COVID-19).
• To assess the feasibility of using wearable technology for large-scale, real-time infectious disease monitoring.

Main Methods:

• Analysis of physiological (heart rate, sleep) and activity (steps) data from 32 individuals with COVID-19 within a cohort of ~5,300 participants.
• Retrospective analysis of smartwatch data to evaluate a two-tiered warning system based on resting heart rate deviations.

Main Results:

• 81% of COVID-19 cases showed alterations in heart rate, steps, or sleep.
• Pre-symptomatic detection was achieved in 22 out of 25 cases (88%), with some detected up to nine days prior to symptom onset.
• A warning system could have detected 63% of COVID-19 cases pre-symptomatically based on resting heart rate changes.

Conclusions:

• Consumer smartwatch data can facilitate pre-symptomatic detection of COVID-19.
• Wearable devices show promise for large-scale, real-time surveillance of respiratory infections.
• Integrating wearable data into public health strategies may enhance early detection and response to epidemics.