Bibliographic Details
| Title: |
Machine learning meets mental health: insights from over one million adolescents in China. |
| Authors: |
Li, Shangxuan (AUTHOR), Cheng, Weihao (AUTHOR), Yu, Zekai (AUTHOR) |
| Source: |
European Child & Adolescent Psychiatry. Apr2026, Vol. 35 Issue 4, p1347-1348. 2p. |
| Subjects: |
Mental depression risk factors, Self-injurious behavior, Risk assessment, Self-evaluation, Prediction models, Mental health, Psychological distress, Smartphones, Questionnaires, Behavior, Teenagers' conduct of life, Electronic equipment, Machine learning, Adolescence |
| Geographic Terms: |
China |
| Abstract: |
The article focuses on a large-scale study from Shanxi Province that used a combined Random Forest and LightGBM machine learning model to identify 13 key risk factors associated with comorbid depression and self-injury in adolescents, highlighting anxiety, parental emotional maltreatment, and cyber victimization as the strongest predictors. While the study demonstrates methodological innovation and offers valuable insights for early mental health screening, it primarily relies on self-reported data, which may be influenced by cultural factors such as emotional suppression and social desirability bias among Chinese adolescents. The authors suggest that incorporating Ecological Momentary Assessment, wearable device data, multi-informant reports, and longitudinal designs could improve the model’s accuracy and causal inference. Overall, the study represents a significant advancement toward data-driven, pattern-centered approaches in adolescent mental health research, with potential applications in personalized intervention development. [Extracted from the article] |
|
Copyright of European Child & Adolescent Psychiatry is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Psychology and Behavioral Sciences Collection |
