Machine learning-based predictive factor analysis of depression among Chinese adolescents
Machine-Learning-basierte Analyse prädiktiver Faktoren für Depression bei chinesischen Jugendlichen
Frontiers in Psychiatry · 19.05.2026 · 17
DOI: 10.3389/fpsyt.2026.1801560 ↗Auf einen Blick
Bei 559 chinesischen Jugendlichen sagte LightGBM Depression am besten voraus (AUC 0,834). Besonders wichtig waren Neurotizismus und Merkmale der personal growth initiative.
Fragestellung
Wie gut klassifizieren sieben ML-Algorithmen niedriges vs. hohes Depressionsrisiko bei chinesischen Jugendlichen, und welche Faktoren sind am wichtigsten?
Methode
559 chinesische Jugendliche; 7 ML-Algorithmen mit 5-fold cross-validation; Vergleich per Friedman- und Nemenyi-Tests; Feature-Importance, SHAP, Interaktionstests und Youden-J-Threshold-Analyse.
Ergebnisse
LightGBM erzielte die beste Performance mit AUC 0,834 sowie balancierter Genauigkeit, Sensitivität und Spezifität. Neurotizismus war der robusteste Prädiktor, gefolgt von proaktiver Veränderung, Verträglichkeit, Extraversion und growth resilience.
Einschränkungen
Querschnittsdesign; keine externe Validierung; allgemeine Cut-offs und kausale Schlüsse sollten vorsichtig interpretiert werden.
Schlussfolgerung der Autor:innen
ML-Algorithmen, besonders LightGBM, identifizieren Depressionsrisiko bei Jugendlichen wirksam; Persönlichkeitsmerkmale und PGI sind Kernprädiktoren.
Kernaussagen
- LightGBM war das beste Modell mit AUC 0,834
- Neurotizismus war der stärkste Prädiktor
- Keine externe Validierung; Querschnittsdaten
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Psychiatry, online erschienen am 19.05.2026. Verfasst von Jichang Guo und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Education Science, Minzu Normal University of Xingyi, Xingyi, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Adolescent depression has emerged as a critical global public health concern, with rising prevalence in China posing severe threats to psychological development and social adaptation. Traditional statistical methods face limitations in capturing complex non-linear relationships and interactions among influencing factors, while machine learning algorithms offer advantages in predictive modeling of mental health disorders.
Objective
This study aimed to: (1) compare the performance of seven ML algorithms in classifying low and high depression risk groups among Chinese adolescents; (2) identify key predictive factors from demographic, personality, and PGI-related variables; (3) explore non-linear relationships and interactive effects between critical factors; and (4) explore preliminary threshold values for key factors as potential references for risk identification.
Methods
A total of 559 Chinese adolescents completed assessments of demographic characteristics, Big Five personality traits, personal growth initiative, and depression symptoms. Model performance was compared using Friedman tests and Nemenyi post-hoc tests appropriate for correlated cross-validation data. Seven ML algorithms were trained and optimized using 5-fold cross-validation. Feature importance was analyzed via traditional metrics and SHAP values, and SHAP interaction effects were tested using permutation tests. Threshold analysis was conducted using the Youden’s J statistic.
Results
LightGBM outperformed other models with an AUC of 0.834, achieving balanced accuracy, sensitivity, and specificity. Neuroticism emerged as the most robust predictor across all models, followed by proactive change, agreeableness, extraversion, and growth resilience. Demographic factors showed minimal predictive power. SHAP permutation tests confirmed significant interactions between neuroticism and proactive change and between proactive change and agreeableness, whereas no significant interaction was found between neuroticism and agreeableness. Preliminary thresholds were identified for key factors within this sample.
Conclusion
ML algorithms, particularly lightGBM, effectively identify adolescent depression risk, with personality traits and PGI serving as core predictive factors. The findings highlight the value of integrating multi-dimensional variables in depression prediction and provide preliminary references for early intervention. Given the cross-sectional design and lack of external validation, conclusions regarding generalizable cutoffs and causal inference should be made with caution. Targeted strategies focusing on reducing neuroticism and enhancing proactive growth behaviors may mitigate depression vulnerability in Chinese adolescents.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Education Science, Minzu Normal University of Xingyi, Xingyi, China.
- School of Literature and Journalism, Minzu Normal University of Xingyi, Xingyi, China.
Zitieren
APA
Guo, J., Pan, Y., & Fan, T. (2026). Machine learning-based predictive factor analysis of depression among Chinese adolescents. Frontiers in Psychiatry, 17. https://doi.org/10.3389/fpsyt.2026.1801560
Vancouver
Guo J, Pan Y, Fan T. Machine learning-based predictive factor analysis of depression among Chinese adolescents. Frontiers in Psychiatry. 2026;17. doi:10.3389/fpsyt.2026.1801560
BibTeX
@article{Guo2026,
author = {Guo, Jichang and Pan, Yanpei and Fan, Tingting},
title = {Machine learning-based predictive factor analysis of depression among Chinese adolescents},
journal = {Frontiers in Psychiatry},
year = {2026},
volume = {17},
doi = {10.3389/fpsyt.2026.1801560}
}
EUVIMED