Multimodal deep learning for detecting current depressive symptom status using wearable time-series data and structural brain MRI in high-risk occupational groups
Journal of Affective Disorders · 2026-12 · 414 · 122270
DOI: 10.1016/j.jad.2026.122270 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-12. Verfasst von Hakjin Lee und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Deep Learning, Depression, Wearable Electronic Devices. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
In high-risk occupational groups, current mental health status may be underreported because of stigma or concerns about disadvantage. Wearable data can capture short-term behavioral and physiological changes, but may be limited in capturing relatively stable biological characteristics. Structural brain magnetic resonance imaging (MRI) may reflect such individual differences and provide complementary information when combined with dynamic wearable signals. We evaluated whether a multimodal deep learning approach combining wearable-derived time-series data with structural brain MRI radiomics could help identify current depressive symptom status in firefighters and prosecution investigators. A total of 291 participants (184 firefighters and 107 prosecution investigators) were included, with a mean monitoring duration of 4.8 weeks. Elevated current depressive symptoms were defined as a Patient Health Questionnaire-9 (PHQ-9) score of 10 or higher at the final observation. Temporal deep learning models were evaluated under wearable-only and multimodal configurations. Multimodal models consistently outperformed wearable-only models, and the final multimodal LSTM model showed the best discriminative performance (AUROC = 0.867; 95% CI 0.814-0.914). In subgroup robustness analysis, performance was generally maintained across broader monitoring-duration categories and occupational groups. SHAP analysis identified the left paracentral lobule, right lateral ventricle, left amygdala, fragmented activity patterns, and minimum oxygen saturation during sleep as major contributors. These findings suggest that a multimodal approach integrating wearable-derived dynamic behavioral characteristics with relatively stable neuroanatomical information from structural brain MRI may serve as a supportive tool for more objectively identifying current depressive symptom status in high-risk occupational populations.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea.
- Ewha Brain Institute, Ewha Womans University, Seoul, Republic of Korea; Department of Brain and Cognitive Sciences, Ewha Womans University, Seoul, Republic of Korea. Electronic address: sujungjyoon@ewha.ac.kr.
- Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea. Electronic address: hwamin@korea.ac.kr.
Förderung
- National Research Foundation of Korea
Zitieren
APA
Lee, H., Jang, M., Jung, T., Byeon, J., Yoon, S., & Lee, H. (2026). Multimodal deep learning for detecting current depressive symptom status using wearable time-series data and structural brain MRI in high-risk occupational groups. Journal of Affective Disorders, 414, 122270. https://doi.org/10.1016/j.jad.2026.122270
Vancouver
Lee H, Jang M, Jung T, Byeon J, Yoon S, Lee H. Multimodal deep learning for detecting current depressive symptom status using wearable time-series data and structural brain MRI in high-risk occupational groups. Journal of Affective Disorders. 2026;414:122270. doi:10.1016/j.jad.2026.122270
BibTeX
@article{Lee2026,
author = {Lee, Hakjin and Jang, MyeongGyun and Jung, Taewon and Byeon, Jinmo and Yoon, Sujung and Lee, Hwamin},
title = {Multimodal deep learning for detecting current depressive symptom status using wearable time-series data and structural brain MRI in high-risk occupational groups},
journal = {Journal of Affective Disorders},
year = {2026},
volume = {414},
pages = {122270},
doi = {10.1016/j.jad.2026.122270}
}
EUVIMED