Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study
JMIR Formative Research · 2024
DOI: 10.2196/62725 ↗At a glance
Kohortenstudie in JMIR Formative Research, 2024. Written by Bridget Dwyer and 7 co-authors. Institution: Division of Digital Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, United States. Major MEDLINE topics: Mobile Applications. Cited 12 times so far (Crossref); 39 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Low engagement with mental health apps continues to limit their impact. New approaches to help match patients to the right app may increase engagement by ensuring the app they are using is best suited to their mental health needs.
Objective
This study aims to pilot how digital phenotyping, using data from smartphone sensors to infer symptom, behavioral, and functional outcomes, could be used to match people to mental health apps and potentially increase engagement Methods After 1 week of collecting digital phenotyping data with the mindLAMP app (Beth Israel Deaconess Medical Center), participants were randomly assigned to the digital phenotyping arm, receiving feedback and recommendations based on those data to select 1 of 4 predetermined mental health apps (related to mood, anxiety, sleep, and fitness), or the control arm, selecting the same apps but without any feedback or recommendations. All participants used their selected app for 4 weeks with numerous metrics of engagement recorded, including objective screentime measures, self-reported engagement measures, and Digital Working Alliance Inventory scores.
Results
A total of 82 participants enrolled in the study; 17 (21%) dropped out of the digital phenotyping arm and 18 (22%) dropped out from the control arm. Across both groups, few participants chose or were recommended the insomnia or fitness app. The majority (39/47, 83%) used a depression or anxiety app. Engagement as measured by objective screen time and Digital Working Alliance Inventory scores were higher in the digital phenotyping arm. There was no correlation between self-reported and objective metrics of app use. Qualitative results highlighted the importance of habit formation in sustained app use.
Conclusions
The results suggest that digital phenotyping app recommendation is feasible and may increase engagement. This approach is generalizable to other apps beyond the 4 apps selected for use in this pilot, and practical for real-world use given that the study was conducted without any compensation or external incentives that may have biased results. Advances in digital phenotyping will likely make this method of app recommendation more personalized and thus of even greater interest.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Division of Digital Psychiatry, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, United States.
ORCID profiles: Bridget Dwyer, Matthew Flathers, James Burns, Jane Mikkelson, Elana Perlmutter, Kelly Chen, Nanik Ram, John Torous
Cite
APA
Dwyer, B., Flathers, M., Burns, J., Mikkelson, J., Perlmutter, E., Chen, K., Ram, N., & Torous, J. (2024). Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study. JMIR Formative Research. https://doi.org/10.2196/62725
Vancouver
Dwyer B, Flathers M, Burns J, Mikkelson J, Perlmutter E, Chen K, et al. Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study. JMIR Formative Research. 2024. doi:10.2196/62725
BibTeX
@article{Dwyer2024,
author = {Dwyer, Bridget and Flathers, Matthew and Burns, James and Mikkelson, Jane and Perlmutter, Elana and Chen, Kelly and Ram, Nanik and Torous, John},
title = {Assessing Digital Phenotyping for App Recommendations and Sustained Engagement: Cohort Study},
journal = {JMIR Formative Research},
year = {2024},
doi = {10.2196/62725}
}
EUVIMED