Actionable companion · Learning design & outcomes
Learning with agency: Machine learning–based prediction of suicide attempts among adolescents: a national study using explainable artificial intelligence
AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.
Evidence and context
Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Secondary school. Verify the participant population and task before transferring the findings.
Original authors’ abstract, reproduced under the linked source license:
Abstract Objectives To develop and evaluate machine learning models for predicting adolescent suicide attempts and to examine predictor contributions using explainable artificial intelligence. Methods A repeated cross-sectional study used pooled data from the 2017–2024 Korea Youth Risk Behavior Web-Based Survey (n=448, 798). Models including logistic regression, random forest, and XGBoost were developed to classify suicide attempts. Performance was evaluated using AUC, F1 score, and sensitivity-oriented screening thresholds to reflect population-level screening purposes. SHapley Additive exPlanations (SHAP) quantified predictor contributions. Results The models showed moderate predictive performance, with XGBoost achieving the highest F1 score and random forest showing the highest sensitivity under the screening condition. SHAP analysis indicated that hopelessness contributed most strongly to prediction, followed by school violence and perceived stress. Additional contributors included self-rated health, household economic status, sleep satisfaction, and behavioral indicators. Under the screening condition, sensitivity improved, although positive predictive values remained low. Conclusion Machine learning models demonstrated moderate performance in predicting adolescent suicide attempts. Psychological and social variables contributed most strongly to prediction, and SHAP improved the interpretability of model outputs, supporting their potential utility for population-level screening support. Keywords: adolescent, machine learning, prediction model, SHAP, suicide attempts
What kind of evidence is this?
Supporting AI learning science · Survey / observational study
Stage: Secondary school. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.
Study methods · source passage
This study was a repeated cross-sectional study using pooled data from the 2017–2024 Korea Youth Risk Behavior Web-Based Survey (KYRBS) (21). The KYRBS is an annual, anonymous, self-administered online survey conducted by the Korea Disease Control and Prevention Agency in collaboration with the Ministry of Health and Welfare and the Ministry of Education of Korea. The survey targets middle and high school students (grades 7–12) and is designed to assess health-risk behaviors among Korean adolescents. The KYRBS uses a stratified, multistage cluster sampling design to obtain a nationally representative sample, with stratification based on geographic region and school type, followed by random selection of schools and classes. For the present study, data from the 2017–2024 survey cycles were pooled, resulting in a final analytic sample of 448, 798 adolescents.
Limitations and uncertainty · source passage
This study has several strengths. First, it used large-scale, nationally representative data, enhancing the generalizability of the findings to Korean adolescents. Second, it integrated conventional statistical analysis with machine learning approaches, allowing both the identification of associated factors and the evaluation of predictive performance within a single framework. Third, the application of SHapley Additive exPlanations (SHAP) enabled the interpretation of machine learning models, providing insight into the relative contribution of multiple domains of risk.
Design the system before the pilot
Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.
- Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.
A 90-day district pilot
- Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
- Days 16–30 · Design. Ask learners to attempt a problem unaided, compare an agent hint, explain a revision and verify the final reasoning against a trusted source. Make the permitted use explicit for each assignment. Name an accountable owner and set the baseline, success threshold and budget before implementation.
- Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
- Days 61–90 · Decide. Measure unaided transfer and delayed retention, calibration of confidence and the ability to identify an incorrect AI explanation. Record whether help-seeking becomes answer copying. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.
The board decision brief
Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.
Attribution and reuse
Eun Sun So; Ji-Young Yeo. Machine learning–based prediction of suicide attempts among adolescents: a national study using explainable artificial intelligence. Frontiers in Psychiatry (2026-07-08). https://doi.org/10.3389/fpsyt.2026.1868329
Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.