Journal article · 2025 · Open access
Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data
Journal of Medical Internet Research, 28, e72501 · Published 5 December 2025 · DOI 10.2196/72501
In brief
“Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data” is a 2025 journal article by Balasundaram Kadirvelu and 5 co-authors, published in Journal of Medical Internet Research. OpenAlex counts 38 citations as of 17 November 2026, which puts it in the top 5% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Journal of Medical Internet Research.
- Citations
- 38
- Most cited in
- 2026 (35)
- Field-weighted impact
- 22.41
- References
- 107
- Authors
- 6
Abstract
Background: Adolescents are particularly vulnerable to mental disorders, with over 75% of lifetime cases emerging before the age of 25 years. Yet most young people with significant symptoms do not seek support. Digital phenotyping, leveraging active (self-reported) and passive (sensor-based) data from smartphones, offers a scalable, low-burden approach for early risk detection. Despite this potential, its application in school-going adolescents from general (nonclinical) populations remains limited, leaving a critical gap in community-based prevention efforts. Objective: This study evaluated the feasibility of using a smartphone app to predict mental health risks in nonclinical adolescents by integrating active and passive data streams within a machine learning (ML) framework. We examined the utility of this approach for identifying risks related to internalizing and externalizing difficulties, eating disorders, insomnia, and suicidal ideation. Methods: Participants (n=103; mean age 16.1 years, SD 1.0) from 3 UK secondary schools used the Mindcraft app (Brain and Behaviour Lab) for 14 days, providing daily self-reports (eg, mood, sleep, and loneliness) and continuous passive sensor data (eg, location, step count, and app usage). We developed a deep learning model incorporating contrastive pretraining with triplet margin loss to stabilize user-specific behavioral patterns, followed by supervised fine-tuning for binary classification of 4 mental health outcomes, namely, the Strengths and Difficulties Questionnaire (SDQ)-high risk, insomnia, suicidal ideation, and eating disorder. Performance was assessed using leave-one-subject-out cross-validation (LOSO-CV), with balanced accuracy as the primary metric. Comparative analyses were conducted using CatBoost (Yandex) and multilayer perceptron (MLP) models without pretraining. Feature importance was assessed using Shapley Additive Explanations (SHAP) values, and associations between key digital features and clinical scales were analyzed. Results: Integration of active and passive data outperformed single-modality models, achieving mean balanced accuracies of 0.71 (0.03) for SDQ-high risk, 0.67 (0.04) for insomnia, 0.77 (0.03) for suicidal ideation, and 0.70 (0.03) for eating disorder. The contrastive learning approach improved representation stability and predictive robustness. SHAP analysis highlighted clinically relevant features, such as negative thinking and location entropy, underscoring the complementary value of combining subjective and objective data. Correlation analyses confirmed meaningful associations between key digital features and mental health outcomes. Performance in an independent external validation cohort (n=45) achieved balanced accuracies of 0.63-0.72 across outcomes, suggesting generalizability to new settings. Conclusions: This study demonstrates the feasibility and utility of smartphone-based digital phenotyping for predicting mental health risks in nonclinical, school-going adolescents. By integrating active and passive data with advanced machine modeling techniques, this approach shows promise for early detection and scalable intervention strategies in community settings.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kadirvelu, B., Bel, T. B., Freccero, A., Di Simplicio, M. C., Nicholls, D., & Faisal, A. A. (2025). Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data. Journal of Medical Internet Research, 28, e72501. https://doi.org/10.2196/72501
MLA 9
Kadirvelu, Balasundaram, et al. “Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data.” Journal of Medical Internet Research, vol. 28, 2025, p. e72501. https://doi.org/10.2196/72501.
Chicago
Kadirvelu, Balasundaram, Teresa Bellido Bel, Aglaia Freccero, Martina C. Di Simplicio, Dasha Nicholls, and A. Aldo Faisal. 2025. “Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data.” Journal of Medical Internet Research 28: e72501. https://doi.org/10.2196/72501.
Harvard
Kadirvelu, B. et al. (2025) ‘Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data’, Journal of Medical Internet Research, 28, p. e72501. doi:10.2196/72501.
IEEE
B. Kadirvelu, T. B. Bel, A. Freccero, M. C. Di Simplicio, D. Nicholls, and A. A. Faisal, “Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data,” Journal of Medical Internet Research, vol. 28, p. e72501, 2025, doi: 10.2196/72501.
BibTeX
@article{kadirvelu2025digital,
title = {{Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data}},
author = {Kadirvelu, Balasundaram and Bel, Teresa Bellido and Freccero, Aglaia and Di Simplicio, Martina C. and Nicholls, Dasha and Faisal, A. Aldo},
journal = {Journal of Medical Internet Research},
year = {2025},
volume = {28},
pages = {e72501},
doi = {10.2196/72501},
url = {https://doi.org/10.2196/72501}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Social Sciences › Psychology › Applied Psychology › Digital Mental Health Interventions
- digital phenotyping
- adolescent mental health
- mental health risk prediction
- smartphone sensor data
- passive sensing
- contrastive learning
- Strengths and Difficulties Questionnaire
- insomnia
Work with this paper
Most-cited papers in Psychology
- Diagnostic and Statistical Manual of Mental DisordersAndrés Santiago González Moreno · American Psychiatric Association Publishing eBooks · 2013 · 123,932 citations
- The theory of planned behaviorIcek Ajzen · Organizational Behavior and Human Decision Processes · 1991 · 106,482 citations
- Self-efficacy: Toward a unifying theory of behavioral change.Albert Bandura · Psychological Review · 1977 · 61,923 citations
- Self-determination theory and the facilitation of intrinsic motivation, social development, and well-being.Richard M. Ryan, Edward L. Deci · American Psychologist · 2000 · 55,457 citations
- Mind in Society: The Development of Higher Psychological ProcessesL. S. Vygotsky · 기초학문자료센터(KRM) (Korea Research Foundation) · 1978 · 53,340 citations
Questions about this paper
How do I cite this paper in APA style?
Kadirvelu, B., Bel, T. B., Freccero, A., Di Simplicio, M. C., Nicholls, D., & Faisal, A. A. (2025). Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data. Journal of Medical Internet Research, 28, e72501. https://doi.org/10.2196/72501
How many times has this paper been cited?
38 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Journal of Medical Internet Research: sign in and open the full text from this page.
Who wrote this paper?
Balasundaram Kadirvelu, Teresa Bellido Bel, Aglaia Freccero, Martina C. Di Simplicio, Dasha Nicholls, A. Aldo Faisal.
What is the DOI of this paper?
10.2196/72501, permanently at https://doi.org/10.2196/72501. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.