Speakers: Sudeepa Bhattacharyya, PhD

Sudeepa Bhattacharyya, PhD

Professor of Biomedical and Health Informatics
University of Missouri-Kansas City
Department of Biomedical Informatics
University of Arkansas for Medical Sciences

 

Dr. Sudeepa Bhattacharyya is a Professor of Biomedical and Health Informatics at the University of Missouri-Kansas City, with a secondary appointment in the Department of Biomedical Informatics at the University of Arkansas for Medical Sciences. She holds a Ph.D. in Bioinformatics, specializing in advanced statistical modeling and AI/ML algorithms. Her research spans multi-omics and multi-modal data integration for disease pathobiology, deep learning applications in healthcare, and spatial machine learning for disease risk assessment. Her work also addresses bias in healthcare, missing value imputation in electronic health records, and social and behavioral determinants of health.

Dr. Bhattacharyya’s lab develops AI-driven predictive models for colorectal cancer risk, maternal-child health disparities, and precision medicine applications. She actively collaborates with NIH-funded consortia on precision medicine and gut microbiome research in neurological diseases. She holds leadership roles in premier societies such as the American Public Health Association and the American Statistical Association. She has participated in NIH, NSF, and OAH (Office of Adolescent Health) review panels, she has co-facilitated NIH think-tank sessions, serves on multiple journal editorial boards, and has filed two U.S./international patent applications. She has consistently received funding through NIH, NSF, and USDA grants.

 

Uncovering Geographic Disparities in Colorectal Cancer: A Spatial Modeling Approach to Multidimensional Risk Factor Analysis

Colorectal cancer (CRC) is one of the most common and preventable cancers, yet significant disparities in screening, incidence, and late-stage diagnosis persist across different geographic locations and socioeconomic contexts. We have developed a spatial modeling framework to identify multidimensional risk factors influencing CRC outcomes at county and census-tract levels. By integrating demographic, socioeconomic, environmental, built environment, and behavioral data, our framework employs Geographically Weighted Regression (GWR) and Geographically Weighted Random Forest (GW-RF) to capture spatial heterogeneity in disease prevalence and outcomes. Results reveal geographic clusters of high and low CRC burden, emphasizing the need for spatially explicit approaches to identify localized risk factors. These insights can guide targeted public health interventions and policies to reduce disparities and improve CRC prevention and early detection.