Predictive modeling of adolescent suicidal behavior using machine learning: Key features and algorithmic insights
Suicidal ideation prevalence among students is a growing concern that requires urgent attention.This review systematically analyzes 28 studies on the application of machine learning techniques for the early detection of suicidal ideation. Among these, Random Forest and SVM emerged as the most common...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-12-01
|
| Series: | MethodsX |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2215016125002997 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Suicidal ideation prevalence among students is a growing concern that requires urgent attention.This review systematically analyzes 28 studies on the application of machine learning techniques for the early detection of suicidal ideation. Among these, Random Forest and SVM emerged as the most commonly used algorithms, featured in 35 % and 27 % of studies respectively. Reported model accuracies ranged from 70 % to 95 %, with deep learning approaches showing slightly higher average precision and recall values. Most studies relied on survey-based data (68 %) and employed PHQ-9 or GAD-7 scales for input features. This review highlights existing gaps in cross-cultural generalization and calls for the development of interpretable and hybrid models for improved risk prediction.This review aims to conduct a comprehensive examination of the etiological factors contributing to the development of suicidal thoughts in students, with the goal of enabling early detection through the application of AI and machine learning techniques.This paper aims to review the current state-of-the-art, highlight the limitations, and emphasizes the need to shift toward hybrid and ensemble deep learning models, which have shown early promise but lack extensive analysis in current literature. |
|---|---|
| ISSN: | 2215-0161 |