Machine learning-based prediction and classification of psychiatric symptoms induced by drug and plants toxicity

Abstract

Psychiatric disorders induced by drug and plant toxicity represent a complex and underexplored area in medical research. Exposure to substances such as pharmaceuticals, illicit drugs, and environmental toxins can trigger a wide range of neuropsychiatric symptoms. This study proposes the development of a machine learning (ML) model to predict and classify these symptoms by analyzing open-access, de-identified datasets. Supervised and unsupervised learning techniques, including neural networks and algorithms like XGBoost, were applied to distinguish drug-induced psychiatric conditions from primary psychiatric disorders. The models were evaluated using metrics such as accuracy, precision, recall, and AUC-ROC. The XGBoost model demonstrated the best performance, achieving an AUC-ROC of 94.8%, making it a promising tool for clinical decision-support systems. This approach can improve early detection and intervention for psychiatric symptoms associated with drug toxicity, contributing to safer and more personalized healthcare.