MétaCan
Menu
← Back to cohort
Record W4411015566 · doi:10.2196/71375

Measuring Psychological Well-Being and Behaviors Using Smartphone-Based Digital Phenotyping: An Intensive Longitudinal Observational mHealth Pilot Study Embedded in a Prospective Cohort of Women

2025· article· en· W4411015566 on OpenAlexaffvenue
Li Yi, Claudia Trudel‐Fitzgerald, Cindy Hu, Grete E. Wilt, Jorge E. Chavarro, Jukka‐Pekka Onnela, Francine Grodstein, Laura D. Kubzansky, Peter James

Bibliographic record

VenueJMIR mhealth and uhealth · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsUniversité du Québec à Trois-RivièresInstitut Universitaire en Santé Mentale de Québec
FundersNational Cancer InstituteNational Heart, Lung, and Blood InstituteNational Institute on AgingNational Institutes of HealthHarvard T.H. Chan School of Public Health
KeywordsmHealthPreprintObservational studySmartphone applicationLongitudinal studyPsychologyCohort studyProspective cohort studyMedicineClinical psychologyGerontologyPsychological interventionComputer scienceMultimediaPsychiatryWorld Wide WebInternal medicine

Abstract

fetched live from OpenAlex

Background: Intensive measures of well-being and behaviors in large epidemiologic cohorts have the potential to enhance health research in these areas. Yet, little is known regarding the feasibility of using mobile technology to collect intensive data in the "natural" environment in the context of ongoing large cohort studies. Objective: We examined the feasibility of using smartphone digital phenotyping to collect highly resolved psychological and behavioral data from participants in a pilot study with participants in Nurses' Health Study II, a nationwide prospective cohort of women. Methods: In this pilot study, an 8-day intensive smartphone protocol was implemented using the "Beiwe" smartphone app. Participants (n=181) completed a baseline survey on day 1 and answered ecological momentary assessment (EMA) surveys twice daily (days 2-8; early afternoon and evening) using their smartphone and provided minute-level accelerometer and GPS data. A feedback survey at the end of Substudy queried participants' experience with the app and data collection process. We assessed adherence to the protocol by examining completion on EMA surveys and completeness of accelerometer and GPS data at the participant, participant day, and prompt levels. Results: Our pilot study demonstrated modest overall compliance with smartphone-based surveys: the baseline survey completion rate was high (156/181, 86.2%), but average daily EMA response rates during the 7-day period were lower with 55.6% (SD 3.9%) for early afternoon and 54.7% (SD 3.2%) for evening. We also observed good average daily completeness of smartphone accelerometer (mean 62.0%, SD 4.5%) data and GPS data (mean 57.7%, SD 3.1%). The feedback survey revealed that the participants found "the app easy to use" (median 85.0 on a scale of 1-100) and were "willing to repeat similar studies" (median 85.0 on a scale of 1-100). Although participants reported feeling their participation was a positive experience (median 64.0 on a scale of 1-100), they also identified some important issues, including user fatigue due to repetitive daily surveys. Conclusions: We observed modest compliance with smartphone surveys and completeness of smartphone passive sensing data in this pilot study compared with similar studies in the past. However, this was not unexpected, given our participants were older (aged 57-75 years, with more than 3 decades of follow-up at the time of the substudy) and may encounter more technological barriers, not to mention that the indication of willingness to participate in such studies again was fairly high. Our findings also highlight that the success and data quality of efforts to obtain daily measures may vary depending on data type and emphasize the need to improve the design of the EMA survey to improve or sustain participant engagement over the study period. Overall, our findings suggest smartphone-based digital phenotyping as a promising technology when embedding in large epidemiological cohorts to collect intensive longitudinal observation data.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.004
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.005
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.004
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0000.000
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.179
GPT teacher head0.460
Teacher spread0.280 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same venueJMIR mhealth and uhealth→Same topicDigital Mental Health Interventions→French-language works237,207→