Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jun 3, 2025
Open Peer Review Period: Jun 4, 2025 - Jul 30, 2025
Date Accepted: Jul 21, 2025
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Predicting Engagement Patterns with Connected Wearable Devices in a Health System: A Survival Analysis
ABSTRACT
Background:
The rapid advancement and widespread adoption of wearable devices provides opportunities to collect longitudinal, objective activity and health data and integrate the information directly into a patient’s electronic health record (EHR). Patterns of engagement and factors associated with the use and non-use of wearable devices are currently not well-understood.
Objective:
We aim to quantify the number of individuals still engaged and using wearable devices at one year since each individual’s first day of usage, across a cohort collected over 6 years. We then aim to identify demographic and behavioral factors that statistically significantly predict the likelihood of staying engaged and using wearable devices within the same one-year-since-first-use timespan.
Methods:
We analyzed connected device data from a large, non-profit academic medical center, which began to incorporate wearable device data into the EHR system in April 2015. We conducted a survival analysis to evaluate time to early disengagement among connected device users and identify factors associated with long-term (one year) engagement in multivariable cox proportional hazard regression models.
Results:
The analysis included 8,616 individuals (median age 45 years, range 18-97, 52.1% male/47.9% female) with available connected device data (e.g., step counts) from the EHR between 2015 and 2021. A total of 5,870 (68.1%) patients were engaged, with active connected devices in the EHR, at one year. Multivariable cox regression models indicated no statistically significant differences between gender groups and race categories. Younger age categories (18-34 years) and lower median daily step counts (<5000) were associated with statistically significant increased hazards for early disengagement at one year.
Conclusions:
The ongoing development of new sensors and algorithms presents opportunities to expand the capabilities of wearable devices, making them even more integral to healthcare delivery. It is important to quantify and enhance engagement, in order to maximize the benefits of this technology and inform future use of the technologies to improve health outcomes.
Citation
The author of this paper has made a PDF available, but requires the user to login, or create an account.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.