System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Epublish 2 citations

PubMed: 40750249 DOI: 10.1136/bmjment-2025-301761

Childhood trauma and recent stressors in predicting subclinical psychotic symptoms among Chinese university students in southwest China: a machine learning analysis within a gender-specific framework.

BMJ Ment Health 28(1)

Authors: Wanjie Tang, Zijian Deng, Zeyuan Sun, Qijun Zhao, Miguel Garcia-Argibay, Kadan Anoop, Tao Hu, Shuang Xue, Natali Bozhilova, Aldo Conti, Steve Lukito, Siqi Wu, Gang Wang, Chunhan Jin, Changjian Qiu, Qiaolan Liu, Jay Pan, Samuele Cortese, Katya Rubia

Affiliations

  • West China School of Public Health and West China Fourth Hospital, Sichuan University, Chengdu, China.
  • School of Computing Science, Sichuan University, Chengdu, China.
  • Department of Child and Adolescent Psychiatry, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, England, UK.
  • School of Medical Sciences, Örebro universitet, Orebro, Örebro, Sweden.
  • Department of Medical Epidemiology and Biostatistics, Karolinska Institute, Stockholm, Sweden.
  • University of Southampton, Southampton, England, UK.
  • Chengdu Normal University, Chengdu, Sichuan, China.
  • Norwegian University of Science and Technology, Trondheim, Trøndelag, Norway.
  • West China Hospital of Medicine, Chengdu, Sichuan, China.
  • Chengdu University, Chengdu, Sichuan, China.
  • Chongqing Jiaotong University, Chongqing, Chongqing, China.
  • West China School of Public Health and West China Fourth Hospital, Sichuan University, Chengdu, China.
  • University of Southampton, Southampton, UK. Academic Unit of Psychology and Clinical and Experimental Sciences (CNS and Psychiatry), University of Southampton, Southampton, UK.

Abstract

BACKGROUND

Subclinical psychotic symptoms (SPS) are common among college students and can lead to future mental health issues. However, it is still not clear which specific childhood trauma, stressors and health factors lead to SPSs, partly due to confounding factors and multicollinearity.

OBJECTIVE

To use machine learning to find the main predictors of SPS among university students, with special attention to gender differences.

METHODS

A total of 21 208 university students were surveyed regarding SPS and a wide range of stress-related factors, including academic pressure, interpersonal difficulties and abuse. Nine machine learning models were used to predict SPS. We examined the relationship between SPS and individual stressors using χ 2 tests, multicollinearity analysis and Pearson heatmaps. Feature engineering, t-distributed stochastic neighborhood embedding (t-SNE) and Shapley Additive Explanation values helped identify the most important predictors. We also assessed calibration with calibration curves and Brier scores, and evaluated clinical usefulness with decision curve analysis (DCA) to provide a thorough assessment of the models. In addition, we validated this model using independent external data.

FINDINGS

The Extreme Gradient Boosting (XGBoost) model had the best prediction results, with an Area Under the Curve (AUC) of 0.89, and validated with external data. It also showed good calibration, and DCA indicated clear clinical benefit. Interpersonal difficulties, academic pressure and emotional abuse emerged as the strongest predictors of SPS. Gender-stratified analyses revealed that academic pressure and emotional abuse affected males more, while health issues like chest pain and menstrual pain were stronger predictors for females.

CONCLUSIONS

Machine learning models effectively identified key stressors associated with SPS in university students. These findings highlight the importance of gender-sensitive approaches for the early detection and prevention of psychotic symptoms.

CLINICAL IMPLICATIONS

SPSs in college students can be predicted by interpersonal difficulties, academic stress and childhood emotional abuse. This information can help mental health professionals develop better ways to prevent and address SPSs.

MeSH

Pain, Stress, Physiological, Machine Learning, Signs And Symptoms, Learning, Wounds And Injuries, Mental Health, Universities