Feasibility and Acceptability of Collecting Passive Phone Usage and Sensor Data Via Apple SensorKit: Randomized Pilot Study
Funk, C.; Fang, Y.; Zhao, Z.; Horwitz, A.; Sen, S.; Frank, E.
2023-11-10
Abstract
Apple SensorKit provides a novel technological framework for health researchers to capture passive participant data. It is unclear whether implementing an e-Cohort study that collects these potentially more sensitive sensor data can achieve successful participation and retention rates. The objective of this study was to assess the feasibility and acceptability of collecting passive phone usage and sensor data utilizing Apple SensorKit in a longitudinal e-Cohort study of medical trainees. iPhone users enrolled in the Intern Health Study 2022 cohort were invited to participate in the Apple SensorKit pilot study in the last quarter of the internship year. Participants were randomized into 1 of 2 arms: 1) invitation to supply data from all sensors of interest (Ambient Light, Device Usage, Keyboard Metrics, Messages Usage, Phone Usage, Speech Metrics, Visits), 2) invitation to supply data only from less sensitive sensors (Ambient Light, Keyboard Metrics, Messages Usage, Phone Usage). Participants received an email with instructions for enabling Apple SensorKit, followed by a reminder push notification four days later. Based on the results of the pilot study, potential 2023 cohort participants were invited to opt into 5 sensor types (Ambient Light, Keyboard Metrics, Message Usage, Phone Usage, Visits) upon initial study enrollment. Device data were tracked for the first 2 months of the internship year. In the 2022 cohort, participants in the less "invasive" study arm (4 sensors) were significantly more likely to opt in to SensorKit data collection in comparison with those in the full 7 sensor arm. Participants in the less "invasive" arm were also significantly more likely to opt into each of the 4 individual sensor types presented in both arms. There were no significant differences in opt-in rates between the sensor types presented within each arm. In the 2023 cohort, there were no significant differences in opt-in rates or retention after 2 months based on sensor type. Our pilot study demonstrated that successful enrollment and retention rates can be achieved for the collection of Apple SensorKit data in an e-Cohort, however inclusion of additional sensor types that may be perceived as more "invasive" or "sensitive" can reduce overall enrollment.Deep Blue DOI
Subjects
Apple SensorKit; SensorKit; iPhone; i-phone; Smartphone; Smart-phone; Phone sensor; Mobile Tech; Mobile Health
Description
Presented at the MeTRIC 2023 Symposium
Types
Poster
Metadata
Show full item recordShowing items related by title, author, creator and subject.
-
Torres, Chioma; Radesky, Jenny; Levitt, Kimberley J.; McDaniel, Brandon T. (Common Sense MediaWiley Periodicals, Inc., 2021-09)
-
Must, Britni; Ludewig, Kathleen (Goldman School of Public Policy, University of California at Berkeley, 2010)
-
Maslowsky, Julie; Frost, Sara; Hendrick, C. Emily; Trujillo Cruz, Freddy O.; Merajver, Sofia D. (Wiley Periodicals, Inc., 2016-07)
Remediation of Harmful Language
The University of Michigan Library aims to describe its collections in a way that respects the people and communities who create, use, and are represented in them. We encourage you to Contact Us anonymously if you encounter harmful or problematic language in catalog records or finding aids. More information about our policies and practices is available at Remediation of Harmful Language.
Accessibility
If you are unable to use this file in its current format, please select the Contact Us link and we can modify it to make it more accessible to you.