Analysis and Evaluation of Explainable Artificial Intelligence on Suicide Risk Assessment

TL;DR

This paper evaluates the effectiveness of explainable AI techniques combined with machine learning models in predicting suicide risk and identifying key contributing factors, demonstrating high accuracy and interpretability for clinical use.

Contribution

It introduces an integrated framework using XAI and ML models for suicide risk assessment, highlighting the importance of explainability in clinical decision support.

Findings

Decision Tree achieved 95.23% accuracy and 0.95 AUC

SHAP identified anger, depression, and social isolation as key risk factors

Patients with higher income and education levels have lower suicide risk

Abstract

This study investigates the effectiveness of Explainable Artificial Intelligence (XAI) techniques in predicting suicide risks and identifying the dominant causes for such behaviours. Data augmentation techniques and ML models are utilized to predict the associated risk. Furthermore, SHapley Additive exPlanations (SHAP) and correlation analysis are used to rank the importance of variables in predictions. Experimental results indicate that Decision Tree (DT), Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) models achieve the best results while DT has the best performance with an accuracy of 95:23% and an Area Under Curve (AUC) of 0.95. As per SHAP results, anger problems, depression, and social isolation are the leading variables in predicting the risk of suicide, and patients with good incomes, respected occupations, and university education have the least risk. Results demonstrate the effectiveness of machine learning and XAI framework for suicide risk prediction, and they can assist psychiatrists in understanding complex human behaviours and can also assist in reliable clinical decision-making.