Addressing the Mental Health Crisis: Understanding Suicidal Risk Factors in University Students Through Interpretable Machine Learning

DOI

10.2991/978-94-6239-664-7_30How to use a DOI?

Keywords

Mental health; Suicidal Risks; Bangladeshi university students; Machine learning; Explainable AI; StudentSafe dataset

Abstract

Mental health issues among college students have become a major worldwide issue, especially impacting young adults going through crucial transitional periods. This crisis particularly affects Bangladesh, a developing South Asian country. Students there experience high rates of anxiety, depression, and suicidal thoughts, but the country has very limited mental health support services. Despite this gravity, research on Bangladeshi students’ mental health is still scattered and limited by small sample sizes and a narrow demographic focus, making it challenging to develop effective intervention strategies. This study presents StudentSafe, an extensive dataset comprising 4,004 meticulously collected records from 99 Bangladeshi universities using structured questionnaires that have been verified by psychiatrists. The dataset contains demographic data, family background variables, academic performance indicators, and psychological health measures. We employed multiple machine learning algorithms to predict suicidal risk tendencies, with XGBoost achieving optimal performance at 75.36% F1-score, surpassing previous comparable studies. To ensure transparency and actionable insights, we integrated LIME and SHAP explainability frameworks, revealing that device usage patterns, institution type, academic achievement, and family environment constitute the primary determinants of suicide risk prediction among Bangladeshi students. We found that these factors are much stronger predictors than basic demographic information. This suggests we can develop specific, targeted interventions based on these key factors. This research provides Bangladeshi universities, policymakers, and mental health professionals with an evidence-based foundation for developing early warning systems and culturally appropriate support mechanisms in resource-constrained educational environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ashadul Islam
AU  - Aminur Rahman
AU  - Md. Joynal Abdin
AU  - Oliur Rahaman
AU  - Md. Nur Alam
PY  - 2026
DA  - 2026/06/08
TI  - Addressing the Mental Health Crisis: Understanding Suicidal Risk Factors in University Students Through Interpretable Machine Learning
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 427
EP  - 441
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_30
DO  - 10.2991/978-94-6239-664-7_30
ID  - Islam2026
ER  -