Using Machine Learning to Advance Disparities Research: Subgroup Analyses of Access to Opioid Treatment |
Opioid use disorder (OUD) and overdoses have become a national crisis, with more than 115 people dying from an opioid overdose in the U.S. every day. Improving access to treatment and recovery services, particularly for underserved groups, is a major priority for addressing the crisis. In a new paper supported by grant funding from the National Institute of Drug Abuse (NIDA) awarded to Jeanne Marsh (Director of CHAS and George Herbert Jones Distinguished Service Professor at the Crown Family School of Social Work, Policy, and Practice), researchers build on previous work that established racial and ethnic disparities in accessing treatment services by exploring other factors that can help health service researchers identify and understand additional sources of inequality in treatment access. The researchers conducted a study in which they operationalized an intersectionality framework using a novel statistical approach to improve the estimation of disparities in access to OUD treatment beyond race and ethnicity. The study used a sample of treatment episodes collected between 2015 and 2017 in the United States from the Treatment Episodes Data Survey (TEDS-A). Researchers found large variation across states in racial disparities, and their analysis of states with the largest samples showed critical factors that augmented disparities beyond race, including service setting, referral source, prior episodes, receipt of medication-assisted opioid treatment, primary drug use frequency, and homelessness. Visit our website to learn more about CHAS's involvement with the OpioidTx research group.
|
Building and Experimenting with An Agent-based Model to Study the Population-level Impact of CommunityRx, A Clinic-based Community Resource Referral Intervention |
Elbert Huang (CHAS Fellow and Professor of Medicine at the University of Chicago), Stacy Tessler Lindau (Professor of Obstetrics and Gynecology, Professor of Medicine-Geriatrics at UChicago Medicine), Jonathan Ozik (Michael M. Davis Presenter and Principal Computational Scientist at Argonne National Laboratory), and colleagues published a new paper on CommunityRx (CRx), an information technology intervention that provides patients with a personalized list of healthful community resources (HealtheRx). Their research builds on previous clinical trials that have shown that half of the participants who received clinical “doses” of the HealtheRx shared the information with others (“social does”) and seeks to capture the full impact of information diffusion. In order to study information diffusion from CRx under varying conditions, the researchers built an agent-based model (ABM) by constructing synthetic population (“agents”) using publicly-available data sources. The study demonstrates the process of building and experimenting with an ABM to study information diffusion from, and the population-level impact of, a clinical information-based intervention. Read the complete study linked below.
|
|
There are currently no upcoming Davis lectures. Stay tuned for the Spring 2022 lineup! |
Invisible Visits: Black Middle-Class Women in the American Healthcare System
Dr. Tina Sacks, AM ’98, PhD ’13 Assistant Professor
School of Social Welfare at the University of California, Berkeley
|
The Importance of Community Asset Mapping, Medical Integration with Social Sciences, and Youth Involvement
Dr. Stacy Lindau, PhD
Professor, Department of Medicine, UChicago Medicine and CIO/Founder of NowPow
|
Follow us on social media for news / updates |
|
