EUVIMEDEUVIMED entdecken
Crossref

Risk prediction of depression- and anxiety-related psychological distress in a large multistage survey sample of Chinese adults: a multi-algorithm ensemble machine-learning model with SHAP

Wanli Zang, Na Liu, Jiarong Wu, Qiuxia Zhang, Junxiu Wang

Journal of Affective Disorders · 2026-10 · 410 · 121987

DOI: 10.1016/j.jad.2026.121987 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-10. Verfasst von Wanli Zang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Physical Education, Soochow University, Suzhou, Jiangsu, 215021, China. Electronic address: wanli19961218@163.com. Hauptthemen laut MEDLINE: Machine Learning, Psychological Distress, Depression, Anxiety. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: Soochow University, Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: To develop an interpretable ensemble machine-learning model to support risk stratification of elevated depression- and anxiety-related psychological distress in a large multistage survey sample of Chinese adults, and to examine nonlinear associations with key psychosocial factors. METHODS: We analysed an unweighted analytical sample of 10,294 adults from the China Social Mentality Survey. Psychological distress was measured with the Kessler-10 scale, and 13 psychosocial indicators were included as candidate predictors. The sample was split 7:3 into training and hold-out test sets. Six binary classifiers were trained and combined using a TOPSIS-weighted classifier fusion (TCF) ensemble. SHAP with LOWESS was used to examine feature importance and dose-response patterns. RESULTS: The TCF model showed the most balanced overall performance across metrics. SHAP analyses showed that loneliness and dehumanization experiences were the strongest risk features, whereas positive psychosocial resources were generally associated with lower predicted risk. SHAP-LOWESS curves indicated nonlinear dose-response relationships: predicted risk rose when key adverse psychosocial features exceeded specific thresholds, whereas several positive resources showed protective patterns within certain ranges. CONCLUSIONS: In a large unweighted multistage survey sample of Chinese adults, the TCF ensemble model provided an interpretable and balanced prediction framework for depression- and anxiety-related psychological distress and highlighted loneliness, dehumanization, and psychosocial resources as key correlates of elevated distress risk. These nonlinear patterns and thresholds may inform future risk assessment and prioritisation of psychosocial assessment, but require confirmation in longitudinal, externally validated, and design-weighted cohorts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningPsychological DistressDepressionAnxietyStress, PsychologicalHumansFemaleChinaAdultMaleMiddle AgedYoung AdultRisk AssessmentAdolescentLonelinessPrediction AlgorithmsRisk FactorsPredictive Learning ModelsEast Asian People

Stichwörter der Autor:innen

Depression and anxietyEnsemble modelMachine learningPsychological distressPsychosocial factorsShapley additive explanations

Autor:innen und Institutionen

  • School of Physical Education, Soochow University, Suzhou, Jiangsu, 215021, China. Electronic address: wanli19961218@163.com.
  • School of Sociology and Ethnology, University of Chinese Academy of Social Sciences, Beijing, 102488, China. Electronic address: dr_ziyan@163.com.
  • School of Physical Education, Soochow University, Suzhou, Jiangsu, 215021, China. Electronic address: wujiarong1117@163.com.
  • School of Physical Education, Soochow University, Suzhou, Jiangsu, 215021, China. Electronic address: qxzhang@suda.edu.cn.
  • School of Mental Health, Wenzhou Medical University, Wenzhou, Zhejiang, 325000, China. Electronic address: wang_jx@cass.org.cn.

Förderung

  • Soochow University
  • Major Project of Philosophy and Social Science Research in Colleges and Universities of Jiangsu Province

Zitieren

APA

Zang, W., Liu, N., Wu, J., Zhang, Q., & Wang, J. (2026). Risk prediction of depression- and anxiety-related psychological distress in a large multistage survey sample of Chinese adults: a multi-algorithm ensemble machine-learning model with SHAP. Journal of Affective Disorders, 410, 121987. https://doi.org/10.1016/j.jad.2026.121987

Vancouver

Zang W, Liu N, Wu J, Zhang Q, Wang J. Risk prediction of depression- and anxiety-related psychological distress in a large multistage survey sample of Chinese adults: a multi-algorithm ensemble machine-learning model with SHAP. Journal of Affective Disorders. 2026;410:121987. doi:10.1016/j.jad.2026.121987

BibTeX
@article{Zang2026,
  author = {Zang, Wanli and Liu, Na and Wu, Jiarong and Zhang, Qiuxia and Wang, Junxiu},
  title = {Risk prediction of depression- and anxiety-related psychological distress in a large multistage survey sample of Chinese adults: a multi-algorithm ensemble machine-learning model with SHAP},
  journal = {Journal of Affective Disorders},
  year = {2026},
  volume = {410},
  pages = {121987},
  doi = {10.1016/j.jad.2026.121987}
}
Kostenlos starten →