Explainable AI for Mental Health Prediction in Drug-Affected Populations with Dragonfly Algorithm and GAN Oversampling

2026-06-21

AI Summary

This study addresses the challenges of early mental health issue detection in individuals with substance use disorders, particularly in the presence of imbalanced data and limited model interpretability. To this end, the authors propose an interpretable multiclass prediction framework that uniquely integrates GAN-based oversampling with a Dragonfly Algorithm-optimized XGBoost classifier. The approach further incorporates a hybrid feature selection strategy combining PCA and information gain, alongside SHAP-based interpretability analysis. Experimental results demonstrate that the model achieves 94.17% accuracy and a 93.80% weighted F1-score on high-dimensional imbalanced datasets, significantly outperforming baseline methods. Importantly, the SHAP analysis identifies sleep quality, physical health, and emotion regulation as key predictive factors, highlighting the model’s clinical potential for supporting early intervention strategies.

Abstract

Mental illnesses among drug users are an increasing international issue, particularly in regions where early detection cannot be easily undertaken. The current literature tends to ignore the use of AI-based mental health analysis in drug users, and low quality of the class imbalance treatment, low interpretability, and optimal hyperparameter optimization can lower predictive quality and clinical utility. This study present a detailed, explainable machine learning (ML) model of multiclass mental health prediction, using a multidimensional data set of drug-affected persons. We combine hybrid PCA-Information Gain (PCA-IG) feature selection, Generative Adversarial Network (GAN)-based oversampling, and Dragonfly Algorithm (DA)-optimized XGBoost to address some of the limitations of existing methods. The suggested framework is effective to work with high-dimensional categorical data, address the issue of class imbalance, and improve predictive performance due to intelligent hyperparameter tuning. The experimental findings show that the XGBoost model optimized using the DA, in combination with GAN-based oversampling, has an accuracy of 94.17% and a weighted F1-score of 93.80%, which is better than the traditional and baseline models. The behavioral, lifestyle, and health factors, particularly sleep quality, physical health, and emotional regulation, are strongly predictive of mental health, with demographic factors having little impact, as seen through feature analysis. SHAP-based explainable AI provides easy-to-understand, instance-level information, enhancing interpretability and trust in models to be used in clinical settings. The results indicate that this framework has the potential to generate valid mental health forecasting tools, which would facilitate early intervention and enhance the treatment of drug-influenced people.

Problem

• Mental Health Prediction
• Drug-Affected Populations
• Class Imbalance
• Explainable AI
• Early Detection

Innovation

• Explainable AI
• Dragonfly Algorithm
• GAN Oversampling
• Mental Health Prediction
• Class Imbalance