JMERC
Owner
Janbazan Medical and Engineering Research Center (JMERC) is the owner of IJWPH.
1.0
Cite Score 2025
SJR: 0.129 / SNIP: 0.140
Volume 18, Issue 3 (2026)
Iran J War Public Health 2026, 18(3): 291-297 |
Back to browse issues page
Article Type:
Subject:
Ethics code: IR.AJAUMS.REC.1403.111
History
Received: 2026/07/16 | Accepted: 2026/09/2 | Published: 2026/09/8
Received: 2026/07/16 | Accepted: 2026/09/2 | Published: 2026/09/8
How to cite this article
Goodarzi N, Imani M, Mohsenabadi H, Shabani M. Machine Learning Classification of Lifetime Suicide Attempts Among Iranian Military Conscripts Using a Gradient Boosting Approach. , Iran J War Public Health. 2026; 18 (3) :291-297
URL: http://ijwph.ir/article-1-1817-en.html
URL: http://ijwph.ir/article-1-1817-en.html
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Rights and permissions
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
1- Department of Clinical Psychology, Faculty of Medicine, Aja University of Medical Sciences, Tehran, Iran
2- Liver and Pancreatobiliary Diseases Research Center, Digestive Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
3- Department of Clinical Psychology, Faculty of Behavioral Sciences and Mental Health (Tehran Institute of Psychiatry), Iran University of Medical Sciences, Tehran, Iran
4- Department of Clinical Psychology, School of Behavioral Sciences and Mental Health (Tehran Institute of Psychiatry), Iran University of Medical Sciences, Tehran, Iran
2- Liver and Pancreatobiliary Diseases Research Center, Digestive Diseases Research Institute, Tehran University of Medical Sciences, Tehran, Iran
3- Department of Clinical Psychology, Faculty of Behavioral Sciences and Mental Health (Tehran Institute of Psychiatry), Iran University of Medical Sciences, Tehran, Iran
4- Department of Clinical Psychology, School of Behavioral Sciences and Mental Health (Tehran Institute of Psychiatry), Iran University of Medical Sciences, Tehran, Iran
Abstract (805 Views)
Aims: This study evaluated the utility of machine learning, specifically a gradient boosting model, for classifying lifetime suicide attempts among Iranian military conscripts and addressing the limitations of traditional linear assessments.
Instrument & Methods: In this cross-sectional study of 338 conscripts, psychological data were collected using the Beck Hopelessness Scale–Short Form, the Suicide Capacity Scale–Version 3, Psychache Scale, the Acquired Capability for Suicide Scale–Fearlessness About Death, Suicidal Behaviors Questionnaire-Revised, and the Interpersonal Needs Questionnaire. A gradient boosting model was trained to classify participants according to their history of lifetime suicide attempts and was benchmarked against Logistic Regression. Feature importance was interpreted using SHapley Additive exPlanations to ensure clinical transparency.
Findings: The gradient boosting model achieved high classification accuracy (area under the curve=0.9344), outperforming the logistic regression model (area under the curve=0.9180). SHapley Additive exPlanations analysis identified the Suicide Scale–Fearlessness About Death and Suicidal Behaviors Questionnaire-Revised as the most significant features distinguishing attempters from non-attempters. Furthermore, intense psychological pain (psychache) emerged as a key discriminative factor in identifying the high-risk group. The gradient boosting model effectively captured complex, nonlinear risk patterns.
Conclusion: Suicide-attempt history is associated with elevated psychological risk, while acquired capability, suicidal behavior, and psychological pain are key predictors for identifying at-risk individuals in military populations.
Instrument & Methods: In this cross-sectional study of 338 conscripts, psychological data were collected using the Beck Hopelessness Scale–Short Form, the Suicide Capacity Scale–Version 3, Psychache Scale, the Acquired Capability for Suicide Scale–Fearlessness About Death, Suicidal Behaviors Questionnaire-Revised, and the Interpersonal Needs Questionnaire. A gradient boosting model was trained to classify participants according to their history of lifetime suicide attempts and was benchmarked against Logistic Regression. Feature importance was interpreted using SHapley Additive exPlanations to ensure clinical transparency.
Findings: The gradient boosting model achieved high classification accuracy (area under the curve=0.9344), outperforming the logistic regression model (area under the curve=0.9180). SHapley Additive exPlanations analysis identified the Suicide Scale–Fearlessness About Death and Suicidal Behaviors Questionnaire-Revised as the most significant features distinguishing attempters from non-attempters. Furthermore, intense psychological pain (psychache) emerged as a key discriminative factor in identifying the high-risk group. The gradient boosting model effectively captured complex, nonlinear risk patterns.
Conclusion: Suicide-attempt history is associated with elevated psychological risk, while acquired capability, suicidal behavior, and psychological pain are key predictors for identifying at-risk individuals in military populations.