Speaker: Dr. Yinfei Kong is an Associate Professor at the Department of Information Systems and Decision Sciences, College of Business and Economics, California State University, Fullerton. He received his Ph.D. degree from the University of Southern California in 2016. He is particularly interested in deep learning, big data analytics, and applications in business and health care. (Web-page: https://sites.google.com/site/yinfeikong/; Email: firstname.lastname@example.org)
Abstract: We operationalize an intersectionality conceptual framework using a novel statistical approach and with these efforts improve estimation of disparities in access to treatment beyond race. We analyzed a sample of 941,286 treatment episodes collected in 2015, 2016, and 2017 in the United States from the Treatment Episodes Data Survey (TEDS-A). We also analyzed a subset of TEDS data from California (N=188,637) and Maryland (N=184,276), states with the largest sample of episodes. We conducted a retrospective subgroup analysis using a two-step approach called virtual twins. In step 1, we trained a classification model that gives the probability of waiting (one day or more). In step 2, we identified the subgroups with higher probability difference of waiting due to race. We tested three classification models for step 1 and identified that random forest was the classification model for step 1. Findings suggested that the following factors can define the subgroup more vulnerable to racial disparities: services setting, referral source, living arrangement, prior episodes, medication-assisted opioid treatment, and frequency of using the primary drug.