02/15/2023
By Hsien-Yuan Hsu

From Data Science to Bayesian Spatiotemporal Modeling: A Journey Towards the Predict to Prevent (P2P) Overdose Study

Wednesday, Feb. 15
Noon to 1 p.m.
Coburn Hall 275
Lunch Provided

Speakers: Thomas Stopka and Cici Bauer

Thomas Stopka is an associate professor and epidemiologist with the Department of Public Health and Community Medicine at the Tufts University School of Medicine. In his NIH-funded interdisciplinary studies, he employs geographic information systems (GIS), spatiotemporal, biostatistical, and qualitative approaches. Throughout the past 24 years, his primary research interests have focused on the interconnectedness of opioid use, social and behavioral risk factors, infectious disease outcomes (HCV, HIV, STDs), and overdose among high-risk, and often hidden populations through community-engaged, epidemiological studies. He also tests public health and clinical interventions through randomized clinical trials to determine their impacts on opioid-related morbidity and mortality. In addition, Stopka is Co-PI of the Tufts research cluster focused on equity in health, wealth, and civic engagement. He teaches courses in GIS, spatial epidemiology, and research methods.

Cici Bauer is an associate professor of Biostatistics and Data Science at the University of Texas Health Science Center in Houston. She received her Ph.D. in Statistics from the University of Washington Seattle in 2012. Her research interests include Bayesian spatiotemporal modeling, small area estimation, hierarchical models for complex survey data, and statistical analysis of data from wearable devices. Her research has been funded by NIH and other federal and state agencies.

Abstract for the Presentation
Collaborative, community-engaged, and multidisciplinary research is increasingly valued by local communities, public health officials, and funders. Cici Bauer and Tom Stopka, a biostatistician and epidemiologist, respectively, will share their collaborative path towards successful extramurally funded research. They will highlight their complementary research and training backgrounds, as well as the early agencies, workgroups, funders, and collaborative opportunities that allowed them to build off of mutual interests in data science and geospatial research, and transition toward NIH funding to conduct Bayesian spatiotemporal modeling to predict to prevent opioid-related overdoses in order to inform preemptive public health responses.