Nicoleta Serban is Peterson Professor in the H. Milton Stewart School of Industrial and Systems Engineering at the Georgia Institute of Technology. Dr. Serban's research record is quite diverse, from statistical learning and mathematical modeling to data analysis using massive datasets, with recent contributions on drawing principled inferences on health services research, health policy, health population-based public health and health information dissemination. She had been the editor for physical sciences, engineering, and the environment for the Annals of Applied Statistics Journal from 2014 to 2021 and participated in multiple National Academy of Engineering (NAE) and Institute of Medicine (IOM) workshops and Frontiers of Engineering, and Science Symposiums organized by NAE and IOM. She is currently member of two state committees, the Georgia All-Payer Claims Database Advisory Committee (2011-present) and the Georgia Behavioral Health Reform & Innovation Commission (2020-present). She has reviewed for multiple funding agencies, including National Institutes of Health, Patient-Centered Outcomes Institute, National Science Foundation, California Tobacco-Related Disease Research Program among others. To date, she has published more than 75 peer-reviewed journal articles, a collaborative (with Dr. William B. Rouse) book titled Understanding and Managing the Complexity of Healthcare and single-authored book titled Healthcare System Access: Measurement, Inference and Intervention.

A substantive research leadership effort she has led since 2013 is the acquisition of the the Medicaid claims data from the Centers for Medicare and Medicaid Services. This data science initiative pertains to the acquisition of a massive database of trillions of medical records for 100+ million children and adults enrolled yearly in the Medicaid health insurance program each year. Her research in this area goes beyond implementation of computationally efficient modeling; it has brought to bear knowledge about important aspects of healthcare delivery and health policy for the Medicaid population. Examples include understanding the effectiveness of recommended care guidelines, cost-effectiveness and cost-savings analysis, evaluating interventions for improving population health, and comparing outcomes in terms of utilization and expenditure of different managed care systems and across multiple states and across multiple years. This research project has been a proof of concept at Georgia Tech on the implementation of data science for massive and highly sensitive data. The project required significant efforts towards safeguarding billions of patient identifiable health records in a very restrictive information technology (IT) infrastructure, establishing the data and computational environment to translate the claims records into meaningful data, and to analyze the data using rigorous analytics tools to derive knowledge toward improving decision making.