Improving Treatment Completion for Young Adults with Substance Use Disorder: Machine Learning-Based Prediction Algorithms

Abstract

Substance Use Disorder treatment completion has been associated with positive outcomes, such as reduced relapse rates and longer periods of abstinence. A study identified factors influencing SUD treatment completion among young adults (aged 18–25) receiving publicly funded outpatient services. This research brief describes how a machine learning decision tree model explored interactions between functional behavioral health needs and strengths, criminal justice system involvement, and completing treatment. A machine learning approach made it possible to identify complex relationships among many factors, improving our understanding on where to focus treatment.