The Risk Factors For Relapse Behavior In Individuals With Substance Use Disorders: Cross-sectional Study

PURPOSE: Substance abuse has become a serious public health problem worldwide, and finding effective prevention and treatment strategies is undoubtedly an urgent need. This study addresses the risk factors that lead to relapse behaviors among substance use disorders (SUDs) and provides a reference for developing appropriate prevention and treatment strategies for SUDs. METHODS: In this study, 5255 SUDs were collected by cluster-wide random sampling, including basic personal information, personal health, social relationships, drug abuse behaviors and characteristics, and other variables collected to predict the recurrence rate. Segmentation of datasets for training and evaluation of several widely used machine learning, using the best-performing eXtreme Gradient Boosting ( XGboost ) model is explained at different levels by SHapley Additive explanation ( SHAP ). RESULTS: A total of 5255 SUDs were included in the study, of which 63.62% felt that their physical health was seriously affected, but 92.29% of the patients did not receive any drug treatment. A total of 2023 (38.50%) SUDs had relapse behavior. The ROC curve of the constructed resorption prediction model showed the best effect of 0.76. The model ranking showed that substance use duration, type of drug, daily drug use time, age of first drug use, ways of taking drugs, and psychological and physiological factors were important in predicting relapse behavior. CONCLUSIONS: Interpretable machine learning not only performs well in predicting relapse but also helps clinical experts and healthcare workers to better understand each risk factor and each case. It also provides a new way of recognizing the risk factors that influence relapse. Supported by: This study was suppoted by the National Natural Science Foundation of ChinaGrant No.82472611 ), the Excellent Research Program of Sports Medicine andHealth College/Sports Medicine and Health Research Institute of Chengdu SportUniversity from 2024 to 2025 (Grant No. ZYGH2406), the "14th Five Year Plan'Scientific Research and Innovation Team of Chengdu Sport University (GrantNo.23CXID02).