Abstract
BACKGROUND: Detoxification is frequently recommended as a treatment for moderate to severe Cocaine Use Disorder (CUD). However, the response to detoxification varies among patients, and previous studies have focused mostly on patterns of drug use behavior to test associations with treatment outcomes, overlooking the potential impact of psychosocial factors, other clinical variables, and individual life experiences. In this study we comprehensively examined several variables aiming to find the most relevant predictors to classify patients with severe versus non-severe cocaine withdrawal symptoms at the end of detoxification. METHODS: Data from 284 women with CUD who enrolled in a 3-week detoxification program was used in this longitudinal study. Psychosocial, clinical, and drug use behavior characteristics were evaluated, generating a dataset with 256 potential predictors. We tested six different machine learning classification algorithms. RESULTS: The best classification algorithm achieved an average accuracy and ROC-AUC of approximately 70%. The 16 features selected as best predictors were the severity of psychiatric, family, and social problems and the level of exposure to childhood maltreatment. Features associated with drug-use behavior included days consuming drugs and having craving symptoms in the last month before treatment, number of previous drug/alcohol-related treatments, and a composite score of addiction severity. The level of cocaine withdrawal syndrome at the beginning of detoxification was also a key feature for classification. A network analysis revealed the pattern of association between predictors. CONCLUSION: These variables can be assessed in real-world clinical settings, potentially helping clinicians to identify individuals with severe cocaine withdrawal that is likely to be sustained over the course of detoxification.