313 Data-Driven Evaluation of Community Health Worker Program

Abstract

OBJECTIVES/GOALS: Thiswork is an evidential study that demonstrates the positive impactof integrating Community Health Workers (CHWs) and SocialDeterminants of Health on an important health outcome, notably in decreasing the 30-day unplanned hospital ED readmissions at Sinai Health Systems. METHODS/STUDY POPULATION: Using datafrom the Sinai Urban Health Institute (SUHI), we compare predictingthe readmissions of patients with and without data pertainingto Social Determinants of Health (SDoH). We thoroughly describe the data cleaning and data pre-processing, done in collaboration with experts in community health. We use a fundamental and ubiquitous classifier in Random Forest for its feature characterization capability in order to translate models results into insights and recommendations for the CHW program. RESULTS/ANTICIPATED RESULTS: We show that when patients are simply engaged byCHWs, regardless of the content of those conversations, we canincrease the predictive accuracy of our classifier by 5%. We usethis result to make recommendations for improving patient careand discuss limitations and future work. Importantly our workpoints directly to the human connection between patients andCHWs as an important feature in the readmission rate. DISCUSSION/SIGNIFICANCE: Our work shows that the predictive capabilities of the classifier increases with CHW logs and SDoH survey data, highlighting the benefit of collecting this information. This is the first step in early identification of such patients so that CHWs are focusing on and providing resources to patients who will most benefit from the program.