Research has shown that substance use disorders may have distinct pathologies requiring different treatment approaches. Recently, there has been a growing interest in personalized medicine, which aims to tailor treatment to a patient’s unique characteristics. One strategy for implementing a personalized approach in heterogeneous clinical settings is to identify patients exhibiting common clusters of symptoms. However, these methods are infrequently implemented in psychiatry and addiction care. The primary goal of the proposed projects is to characterize the underlying heterogeneity in psychiatric and substance use symptoms in addiction and mental health treatment populations. More specifically, to examine how latent clusters of patients emerge in terms of presenting psychiatric (i.e., depression, anxiety, PTSD, trauma) and substance use symptoms in admission data and then explore how the resulting clusters differ on mechanisms of behavior change (i.e., craving, impulsivity, and future discounting). Overall, these studies will better identify and characterize individual treatment needs, to allow for more targeted interventions. These will ultimately improve treatment outcomes and lower healthcare costs.