Week-ahead prediction of depressive episodes using wearable-derived circadian biomarkers: A multicenter deep learning study with risk-based operating thresholds
Journal of Affective Disorders · 2026-11 · 412 · 122076
DOI: 10.1016/j.jad.2026.122076 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Journal of Affective Disorders, 2026-11. Verfasst von Byeongsu Kim und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Circadian Rhythm, Wearable Electronic Devices. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Science and ICT, South Korea.
Abstract (Originalsprache)
Early detection of depressive episodes is important because shorter duration of untreated illness is associated with better outcomes, yet routine care remains largely reactive and dependent on retrospective self-report. Wearables enable passive, continuous monitoring, and circadian disruptions in sleep-wake, activity, and diurnal heart rate (HR) patterns may precede mood episodes. However, prior wearable-based models often relied on short prediction horizons, simplistic circadian proxies, and limited clinical interpretability. We evaluated a deep learning approach that integrates two complementary circadian markers derived from a single wearable: an HR-derived cosine acrophase and a sleep-timing-based proxy measure of circadian phase related to dim-light melatonin onset (DLMO), since melatonin was not directly measured. Performance was summarized across risk-based operating thresholds. In a multicenter real-world mood disorder cohort (N = 144; 90,281 person-days), we trained a time-series model using 7-day wearable histories to predict the presence of a clinician-verified depressive episode one week ahead, with participant-level splits (6: 2:2) and discrimination consistency summarized across 10 repeated holdout runs. The combined circadian model achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.772 (95% confidence interval [CI], 0.750-0.794). On the held-out test set, the top 20% of risk-ranked patient-days captured 63.5% of depressive-episode days; at a base prevalence of 5.3%, positive predictive value (PPV) was 16.7% (3.2-fold prognostic lift), with a review burden of 20 per 100 patient-days. These findings support the feasibility of wearable-based week-ahead depressive-risk stratification in mood disorders, although external validation, probabilistic calibration, transportability assessment, and prospective episode-onset evaluation are required before clinical implementation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea.
- Department of Psychiatry, Korea University College of Medicine, Seoul, Republic of Korea.
- Department of Computer Science and Engineering, SunMoon University, Asan, Republic of Korea.
- 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
- Ministry of Science and ICT, South Korea
Zitieren
APA
Kim, B., Chae, M., Seo, H., Jeong, J., Park, S., Jeong, I., Kim, Y., Kim, Y., Jung, T., Lee, T., Cho, C. H., Yeom, J. W., Lee, T., Lee, H. J., & Lee, H. (2026). Week-ahead prediction of depressive episodes using wearable-derived circadian biomarkers: A multicenter deep learning study with risk-based operating thresholds. Journal of Affective Disorders, 412, 122076. https://doi.org/10.1016/j.jad.2026.122076
Vancouver
Kim B, Chae M, Seo H, Jeong J, Park S, Jeong I, et al. Week-ahead prediction of depressive episodes using wearable-derived circadian biomarkers: A multicenter deep learning study with risk-based operating thresholds. Journal of Affective Disorders. 2026;412:122076. doi:10.1016/j.jad.2026.122076
BibTeX
@article{Kim2026,
author = {Kim, Byeongsu and Chae, Minsu and Seo, Hyungjun and Jeong, Jaegwon and Park, Soohyun and Jeong, Inyong and Kim, Yihyun and Kim, Yeongmin and Jung, Taewon and Lee, Taeyeong and Cho, Chul-Hyun and Yeom, Ji Won and Lee, Taek and Lee, Heon-Jeong and Lee, Hwamin},
title = {Week-ahead prediction of depressive episodes using wearable-derived circadian biomarkers: A multicenter deep learning study with risk-based operating thresholds},
journal = {Journal of Affective Disorders},
year = {2026},
volume = {412},
pages = {122076},
doi = {10.1016/j.jad.2026.122076}
}
EUVIMED