A machine learning model for the prediction of unhealthy alcohol use among women of childbearing age in Alabama.

INTRODUCTION: This study utilizes a machine learning model to predict unhealthy alcohol use treatment levels among women of childbearing age. METHODS: In this cross-sectional study, women of childbearing age (n = 2397) were screened for alcohol use over a 2-year period as part of the AL-SBIRT (screening, brief intervention, and referral to treatment in Alabama) program in three healthcare settings across Alabama for unhealthy alcohol use severity and depression. A support vector machine learning model was estimated to predict unhealthy alcohol use scores based on depression score and age. RESULTS: The machine learning model was effective in predicting no intervention among patients with lower Patient Health Questionnaire (PHQ)-2 scores of any age, but a brief intervention among younger patients (aged 18-27 years) with PHQ-2 scores >3 and a referral to treatment for unhealthy alcohol use among older patients (between the ages of 25 and 50) with PHQ-2 scores >4. CONCLUSIONS: The machine learning model can be an effective tool in predicting unhealthy alcohol use treatment levels and approaches.

HIV/STI/HCV Risk Clusters and Hierarchies Experienced by Women Recently Released from Incarceration.

This study examines cross-sectional clusters and longitudinal predictions using an expanded SAVA syndemic conceptual framework-SAVA MH + H (substance use, intimate partner violence, mental health, and homelessness leading to HIV/STI/HCV risks)-among women recently released from incarceration (WRRI) (n = 206) participating in the WORTH Transitions (WT) intervention. WT combines two evidence-based interventions: the Women on the Road to Health HIV intervention, and Transitions Clinic. Cluster analytic and logistic regression methods were utilized. For the cluster analyses, baseline SAVA MH + H variables were categorized into presence/absence. For logistic regression, baseline SAVA MH + H variables were examined on a composite HIV/STI/HCV outcome collected at 6-month follow-up, controlling for lifetime trauma and sociodemographic characteristics. Three SAVA MH + H clusters were identified, the first of which had women with the highest overall levels of SAVA MH + H variables, 47% of whom were unhoused. Hard drug use (HDU) was the only significant predictor of HIV/STI/HCV risks in the regression analyses. HDUs had 4.32-fold higher odds of HIV/STI/HCV outcomes than non-HDUs (p = 0.002). Interventions such as WORTH Transitions must differently target identified SAVA MH + H syndemic risk clusters and HDU to prevent HIV/HCV/STI outcomes among WRRI.