Peer-reviewed article
Development and validation of a machine learning-based screening tool for early detection of adolescent suicide risk.
Weijia Li, Yongtian Cheng, Zeming Zhang, Yingying Yang, Yanpeng Jin et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001Researchers in Southern China developed and tested two machine learning-based tools to identify adolescents at early risk of suicide before they attempt it. One tool uses 51 items and another uses 11 items for easier use in schools. Both tools showed good ability to predict which young people would develop suicide risk when tested on new groups of adolescents. The study suggests these screening tools could help schools detect at-risk teenagers early and provide timely support.
Key points
- Two versions of screening tools were developed: a 51-item full version and an 11-item abbreviated version
- The CatBoost machine learning algorithm performed best with an AUROC of 0.87 or higher
- The abbreviated 11-item tool showed only a 0.02 reduction in performance while being more practical
- Longitudinal validation with follow-up interviews confirmed the tools can predict actual suicide risk development
- The tools integrate multiple dimensions of vulnerability factors beyond just current suicidal thoughts
Limitations
The study provides preliminary validation in a Chinese school setting and the document does not report implementation outcomes, cost-effectiveness, or whether using these tools actually leads to better mental health outcomes when schools adopt them. Further research is needed to confirm effectiveness across different populations and settings.
Abstract
BACKGROUND: Adolescent suicide remains a significant public health concern, yet existing suicide screening instruments primarily focus on already manifested suicidal phenomena, underscoring the need for reliable and practical tools to enable early identification and intervention. METHODS: Based on a large-scale school-based cohort study conducted in Southern China in 2022, this study aimed to develop and preliminarily validate two machine learning-based tools (a 51-item full version and an 11-item abbreviated version) designed to help identify adolescents at risk of developing suicide risk. The dataset was divided into two samples for tool development and longitudinal interview validation. During the tool development phase, LASSO regression was employed to select items with optimal contributions for recent suicide attempts from a multidimensional set of risk factors, followed by model training with multiple machine learning algorithms. The developed models were subsequently evaluated for their ability to predict suicide risk as assessed by the follow-up interview in the longitudinal validation phase. RESULTS: Both versions of the screening tool demonstrated adequate discriminative ability, with the CatBoost algorithm outperforming others (AUROC ≥ 0.87). The abbreviated tool showed a slight trade-off between model precision and practicality, with a 0.02 reduction in AUROC, while still maintaining appropriate discrimination. Longitudinal validation using follow-up interview outcomes supported the predictive validity of both tools. These findings provide preliminary evidence for the utility of machine learning-based suicide risk screening tools among adolescents. CONCLUSIONS: This study provides evidence supporting the machine learning-based screening tools for early suicide risk detection in adolescents that integrates multidimensional vulnerabilities. The tools show promise in facilitating early identification and targeted interventions in school settings, addressing a critical need in adolescent mental health care. Nonetheless, further research is warranted to confirm their efficacy and support broader implementation.
Findings the Hub has extracted
Each claim below is labelled by its type of design and links back to this report.
- Intervention
- Machine learning-based screening tools (51-item full version and 11-item abbreviated version) to identify adolescents at risk of developing suicide risk
- Population
- Adolescents in schools in Southern China, based on large-scale school-based cohort study from 2022
Key finding
Both screening tools demonstrated adequate discriminative ability with CatBoost algorithm achieving AUROC ≥ 0.87
Li et al. · PubMed (US National Library of Medicine) · 3 May 2026