Identifying Treatment Responders to Varenicline for Alcohol Use Disorder Using Two Machine-Learning Approaches

Varenicline has shown promise for treating alcohol use disorder (AUD); however, not everyone will respond to varenicline. Machine-learning methods are well suited identify treatment responders. In the present study, we examined data from National Institute on Alcohol Abuse and Alcoholism Clinical Intervention Group multisite clinical trial of varenicline using two machine-learning methods. Baseline characteristics taken a randomized were as potential moderators response qualitative interaction trees ( N = 199) group least absolute shrinkage selection operator nets 200). Results align with prior research, highlighting smoking status, AUD severity, medication adherence, drinking goal predictors response. Novel findings included between age cardiovascular health in predicting stronger effects among individuals lower craving. With increased integration methods, studies that effectively integrate development have high inform practice.