EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Transcultural prediction model for late-life depression based on multi-cohort machine learning and explainable AI

Lu Liu, Lei Tang, Menqin Dai, Xianghong Ding, Liling Wu, Xiong Ke, Jiaming Luo, Nian Liu

Journal of Affective Disorders · 2026

DOI: 10.1016/j.jad.2025.120169 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026. Verfasst von Lu Liu und 7 weiteren Autor:innen. Beteiligte Einrichtung: Mental Health Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China; School of Psychiatry, North Sichuan Medical College, Nan…. Hauptthemen laut MEDLINE: Machine Learning, Depression, Depressive Disorder, Cross-Cultural Comparison. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Province Science and Technology Support Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Late-life depression is a global health concern with heterogeneous risk factors across populations. This study aimed to develop and validate a machine learning model for depression prediction in older adults using harmonized data from the United States and China. METHODS: We harmonized data from the Health and Retirement Study (HRS, n = 6865) and China Health and Retirement Longitudinal Study (CHARLS, n = 4476) for adults aged ≥60 years. Depression was assessed using validated scales in both cohorts. The Boruta algorithm was used for feature selection. 17 machine learning algorithms were evaluated, with HRS data split into training (70 %) and internal validation (30 %), and CHARLS data used for external validation. Model performance was assessed using AUC, decision curve analysis, calibration plots, and SHapley Additive Explanations (SHAP). RESULTS: The Gradient Boosting Machine (GBM) model achieved the best performance, with AUCs of 0.752 (95 % CI: 0.735-0.768) in HRS training, 0.763 (95 % CI: 0.737-0.788) in HRS validation, and 0.717 (95 % CI: 0.702-0.732) in CHARLS validation. The model showed good calibration and positive net benefit across relevant clinical thresholds. SHAP analysis identified self-rated health, functional dependency, self-rated memory, arthritis, and ADL score as top predictors with consistent effects across populations. CONCLUSION: We developed a robust and interpretable machine learning model for predicting late-life depression that generalizes across culturally distinct populations. The results highlight both common predictive factors and the need for population-specific considerations in clinical application.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDepressionDepressive DisorderCross-Cultural ComparisonHumansAgedMaleFemaleMiddle AgedChinaLongitudinal StudiesUnited StatesAged, 80 and overRisk FactorsCohort Studies

Stichwörter der Autor:innen

DepressionExplainable artificial intelligenceMachine learningOlder adultsTranscultural psychiatry

Autor:innen und Institutionen

  • Mental Health Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China; School of Psychiatry, North Sichuan Medical College, Nanchong, China; Key Laboratory of Digital-Intelligent Disease Surveillan…
  • Mental Health Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China; School of Psychiatry, North Sichuan Medical College, Nanchong, China; Department of Psychiatry, Sleep Medicine Centre, First A…
  • Mental Health Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, China; School of Psychiatry, North Sichuan Medical College, Nanchong, China.
  • Key Laboratory of Digital-Intelligent Disease Surveillance and Health Governance, North Sichuan Medical College, Nanchong, China; Nanchong Key Laboratory of Individualized Drug Therapy, Department of Pharmacy, The Secon…
  • Key Laboratory of Digital-Intelligent Disease Surveillance and Health Governance, North Sichuan Medical College, Nanchong, China.
  • Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, China. Electronic address: liunian@nsmc.edu.cn.

Förderung

  • Sichuan Province Science and Technology Support Program

Zitieren

APA

Liu, L., Tang, L., Dai, M., Ding, X., Wu, L., Ke, X., Luo, J., & Liu, N. (2026). Transcultural prediction model for late-life depression based on multi-cohort machine learning and explainable AI. Journal of Affective Disorders. https://doi.org/10.1016/j.jad.2025.120169

Vancouver

Liu L, Tang L, Dai M, Ding X, Wu L, Ke X, et al. Transcultural prediction model for late-life depression based on multi-cohort machine learning and explainable AI. Journal of Affective Disorders. 2026. doi:10.1016/j.jad.2025.120169

BibTeX
@article{Liu2026,
  author = {Liu, Lu and Tang, Lei and Dai, Menqin and Ding, Xianghong and Wu, Liling and Ke, Xiong and Luo, Jiaming and Liu, Nian},
  title = {Transcultural prediction model for late-life depression based on multi-cohort machine learning and explainable AI},
  journal = {Journal of Affective Disorders},
  year = {2026},
  doi = {10.1016/j.jad.2025.120169}
}
Kostenlos starten →