ISE Seminar - Hyojung Kang

Title: Modeling Complex Healthcare and Public Health Systems: From Prediction to Decision Support

Abstract: Healthcare and public health systems are complex, dynamic, and influenced by multiple interacting factors across individual, organizational, and population levels. This talk will highlight how industrial engineering and analytics methods can be used to better understand these systems, identify meaningful patterns, predict outcomes, and support decision-making at both the individual and population levels. At the patient level, the talk will present how machine learning and longitudinal modeling using large-scale insurance claims and electronic medical record data can support proactive and personalized diabetes management by characterizing treatment trajectories and predicting medication adherence to support earlier identification of patients who may benefit from intervention. At the population level, the talk will illustrate applications of spatiotemporal analytics, association rule mining, and trend analysis to identify geographic, combinatorial, and temporal patterns in substance use and overdose outcomes and inform targeted public health strategies. The talk will conclude by discussing opportunities and challenges in translating analytical models into decision-support tools that can guide clinical and public health action.

Bio

Hyojung Kang is an Associate Professor in the Department of Health and Kinesiology at the University of Illinois Urbana-Champaign. She is also affiliated with the Health Care Engineering Systems Center, Informatics Program, and Interdisciplinary Health Sciences Institute at UIUC. She received her Ph.D. in Industrial Engineering and Operations Research from The Pennsylvania State University and her M.S. in Industrial and Systems Engineering from Georgia Tech. Her research develops and applies advanced computational and analytical methods to complex, data-driven problems in healthcare and public health. Her methodological expertise includes machine learning and predictive modeling, discrete-event simulation, statistical modeling and spatial analytics. She integrates large-scale administrative, clinical, public health, and geospatial data to develop models that characterize complex systems, identify patterns and relationships, predict outcomes, and support decision-making under uncertainty. Her research has been supported by the NSF and NIH, as well as the Illinois Department of Public Health.