Passive Sensing for Mental Health Monitoring: A Scoping Review of Machine Learning with Wearables and Smartphones (Preprint) DOI

S. Shen,

Wenhao Qi,

Jianwen Zeng

et al.

Published: May 7, 2025

BACKGROUND Mental health issues have become a significant global public challenge. Traditional assessments rely on subjective methods with limited ecological validity. Passive sensing via wearable devices and smartphones, combined machine learning (ML), enables objective, continuous, noninvasive mental monitoring. OBJECTIVE This study aims to provide comprehensive review of the current state passive sensing-based (ML) technologies for We summarize technical approaches, reveal association patterns between behavioral features disorders, explore potential directions future advancements. METHODS Following PRISMA-ScR guidelines, we searched seven major databases (Web Science, PubMed, IEEE Xplore, etc.) studies published 2015 2025. A total 42 were included. Information was extracted from dimensions such as data collection, preprocessing, feature engineering, ML methods, validation, integrating (e.g., sleep, activity, social interaction) disorders depression, anxiety). RESULTS The found that most commonly used digital biomarkers heart rate (n=28), movement index (n=25), step count (n=17), which significantly associated depression anxiety. Deep models CNN, LSTM) performed exceptionally well in processing time-series data. However, traditional random forest, XGBoost), due their higher interpretability, remain widely adopted. Current face challenges small sample sizes (median = 60.5 participants), short collection periods (45.24% had less than 7 days), device variety (76.19%). Additionally, only one conducted external limiting clinical generalizability models. On ethical front, few (14.29%) explicitly mentioned anonymization, highlighting need enhanced privacy protection algorithm fairness. CONCLUSIONS combination offers innovative solutions key challenges, including quality, model generalization, standards, be addressed before translation. Future research should focus large-scale longitudinal multimodal integration, optimization, interdisciplinary collaboration drive widespread adoption application these technologies.

Language: Английский

Community Therapeutic Space for Women with Schizophrenia: A New Innovative Approach for Health and Social Recovery DOI Creative Commons

M. Natividad,

Marcelo Chavez,

Ariadna Balagué

et al.

Women, Journal Year: 2025, Volume and Issue: 5(2), P. 13 - 13

Published: April 22, 2025

Women with schizophrenia have distinct health and social needs compared to men. The Mutua Terrassa Functional Unit for Schizophrenia has designed a new intervention called the Community Therapeutic Space (CTS), which is based on individual group interventions focused physical mental health, factors. We carried out narrative review focusing green blue spaces, climate change, light, digitalization gynecological screening in women schizophrenia, propose content seven topics of CTS. personalized space offers appointments professionals particular attention pharmacological issues. focuses mainly groups healthy habits, links community activities. interaction connections, connection nature. these three spaces been divided into colors: corners (related spaces), red corner (climate change), yellow (light health), white (mainly mindfulness), black (digitalization healthcare), purple screening). In future, peer-to-peer volunteer programs may help our healthcare unit ensure maintain positive effects interventions.

Language: Английский

Citations

0
Passive Sensing for Mental Health Monitoring: A Scoping Review of Machine Learning with Wearables and Smartphones (Preprint) DOI

S. Shen,

Wenhao Qi,

Jianwen Zeng

et al.

Published: May 7, 2025

BACKGROUND Mental health issues have become a significant global public challenge. Traditional assessments rely on subjective methods with limited ecological validity. Passive sensing via wearable devices and smartphones, combined machine learning (ML), enables objective, continuous, noninvasive mental monitoring. OBJECTIVE This study aims to provide comprehensive review of the current state passive sensing-based (ML) technologies for We summarize technical approaches, reveal association patterns between behavioral features disorders, explore potential directions future advancements. METHODS Following PRISMA-ScR guidelines, we searched seven major databases (Web Science, PubMed, IEEE Xplore, etc.) studies published 2015 2025. A total 42 were included. Information was extracted from dimensions such as data collection, preprocessing, feature engineering, ML methods, validation, integrating (e.g., sleep, activity, social interaction) disorders depression, anxiety). RESULTS The found that most commonly used digital biomarkers heart rate (n=28), movement index (n=25), step count (n=17), which significantly associated depression anxiety. Deep models CNN, LSTM) performed exceptionally well in processing time-series data. However, traditional random forest, XGBoost), due their higher interpretability, remain widely adopted. Current face challenges small sample sizes (median = 60.5 participants), short collection periods (45.24% had less than 7 days), device variety (76.19%). Additionally, only one conducted external limiting clinical generalizability models. On ethical front, few (14.29%) explicitly mentioned anonymization, highlighting need enhanced privacy protection algorithm fairness. CONCLUSIONS combination offers innovative solutions key challenges, including quality, model generalization, standards, be addressed before translation. Future research should focus large-scale longitudinal multimodal integration, optimization, interdisciplinary collaboration drive widespread adoption application these technologies.

Language: Английский

Citations

0