Hyunju Kim
Principal Research Scientist
Hyunju Kim, PhD, is a Principal Research Scientist at the Institute for Experiential AI and the Department of Pharmaceutical Sciences in the Bouvé College of Health Sciences. Her research centers on brain, cognitive, and mental health across the lifespan. She focuses on building quantitative and mechanistic frameworks for understanding neuroplasticity, cognitive development, and cognitive resilience through physics-informed modeling and multimodal machine learning. Her current research program develops predictive models using machine learning to integrate physiological, neurological, behavioral, and environmental data. This work aims to identify bio-behavioral markers for early prediction and personalized intervention in cognitive decline, developmental delays, and mental health disorders.
She received her PhD in Physics from the University of Notre Dame, where she specialized in statistical physics and network theory, developing graph-theoretic algorithms and artificial neural networks with bio-inspired architectures. Her doctoral work created computational frameworks for analyzing multi-scale systems, including solving open problems in graph theory and creating tools for understanding emergent properties in complex systems ranging from gene regulatory systems to social networks.
Following postdoctoral positions at Virginia Tech and Arizona State University, she served as Assistant Research Professor at Arizona State University. Throughout this period, she developed novel computational frameworks combining graph theory, information theory, and statistical physics to analyze how network structure and functional constraints mutually influence each other in biological systems. She led research programs as Co-PI on NSF and Templeton World Charity Foundation projects focused on biological information processing. Her NASA-funded astrobiology research, where she served as Deputy Principal Investigator, applied these methods to characterize life at planetary scales and revealed universal scaling laws governing biological networks. Her work resulted in publications in Science Advances, PNAS, and Physical Review Letters, among others.
Prior to joining Northeastern, she worked as a Machine Learning Engineer at IQVIA, where she built end-to-end machine learning pipelines for healthcare applications using massive datasets covering over 100 million patients across multiple countries. Her work involved processing EMR and claims data, developing ML models, and deploying systems to predict disease onset, progression, and treatment adherence. This transitional research experience with real-world data applications, combined with her expertise in complex networks analysis, enables her novel approach of bridging computational modeling with practical clinical implementations for cognitive and mental health solutions.