Florida

University of Florida

Principal Investigator (UF/OneFlorida): Jiang Bian, PhD

Dr. Bian is an associate professor of Biomedical Informatics at the University of Florida, and Scientific Director of the Cancer Informatics Shared Resource for the University of Florida Health Cancer Center. Dr. Bian has a diverse yet strong multi-disciplinary background in data integration, semantic web and ontology, machine learning, natural language processing, social media analysis, network science, data privacy, and software engineering. Nevertheless, his expertise and background serve an overarching theme: data science with heterogeneous data, information and knowledge resources. Dr. Bian’s research areas can be divided into two sections under this overarching theme: (1) data-driven medicine—applications of informatics techniques, including machine learning methods in medicine on solving big and heterogeneous data problems; (2) mining the Internet, including the social web, to provide insights into health-related behavior and health outcomes of various populations and finding ways to develop interventions that promote public and consumer health; and (3) development of novel informatics methods, tools and systems to support clinical and clinical research activities. Relevant to this project, he led the effort on integrating and linking diverse data sources to create the data infrastructure for the OneFlorida—a key data resource for this project.

Co-Principal Investigator (UF/OneFlorida): Hui Shao, MD, PhD

Dr. Shao is currently an assistant professor at the University of Florida’s College of Pharmacy, within the Department of Pharmaceutical Outcomes and Policy. One of his core research areas is predictive modeling, using advanced machine learning, microsimulation, and econometrics method to build valid predictive models to resolve real-world issues. Dr. Shao is one of the original developer of the Building, Relating, Assessing, and Validating Outcomes (BRAVO) diabetes model, which is the first person-level microsimulation model predicting the progression of diabetes based on individuals’ characteristics and treatment regimen, in the U.S. Dr. Shao is currently working with the Centers for Disease Control and Prevention on multiple projects and oversees the development process of several national diabetes/prediabetes predictive models.

Co-Principal Investigator (UF/OneFlorida): Elizabeth Shenkman, PhD

Dr. Shenkman is the Chair of the Department of Health Outcomes and Biomedical Informatics, the Co-Director of the University of Florida Clinical and Translational Science Institute (CTSI), the lead PI for the OneFlorida Clinical Research Consortium, and te Director for the Family Data Center (FDC) at the Univerity of Florida. She is also a health outcomes researcher whose research focuses on: 1) determining which combinations of health care delivery, community, and patient factors influence quality and outcomes of care; and 2) developing and testing corresponding evidence-based strategies to reduce disparities in health outcomes among underserved populations.

Co-Principal Investigator (UF/OneFlorida): Yi Guo, PhD

Dr. Guo is an Assistant Professor in the Department of Health Outcomes & Biomedical Informatics in the College of Medicine at University of Florida. His research focuses on 1) reducing health disparities, 2) integrating heterogeneous data for health risk prediction, and 3) validating patient-reported outcome measures across subpopulations. With a unique combination of training in biostatistics, bioinformatics, and biochemistry, Dr. Guo has strong study design, data collection, and analytical skills. His expertise includes interventional study design, power and sample size analysis, analysis of multi-level and longitudinal designs, mediation and moderation analysis, and health risk, including risk of cardiovascular disease, prediction modeling. He has extensive experience collaborating with clinicians and biomedical researchers on study design, coordination, and analysis. In particular, he has extensive experience applying complex statistical models to analyze health outcomes.

About Our Center

As the third most populous state in the United States and a state with great racial-ethnic and geographic diversities, Florida will be an essential piece in the national diabetes surveillance system and provide important data for studying the epidemiology of diabetes among children and adolescents in the US southeast region where diabetes is most prevalent in the country. We will leverage our unique real-world data (RWD) source, the OneFlorida network, to build a surveillance system to monitor the prevalence and incidence of diabetes among children and adolescents in Florida in an accurate, cost-effective, and timely fashion. OneFlorida is the largest state-wide RWD repository that contains linked electronic health records (EHRs), claims, vital statistics, and birth records data, and covers a large portion of Floridians across all 67 Florida counties.


To provide more accurate estimations of T1DM and T2DM prevalence and incidence compared to prior EHRs-based systems, we will combine structured and unstructured data from patients’ EHRs to develop novel data-driven computable phenotyping algorithms through modern machine learning methods. This study will also generate important data on many risk factors that could contribute to the racial-ethnic and geographic disparities in diabetes, especially social and behavioral determinants of health, at both individual (e.g., individual health behaviors) and contextual levels (e.g., area-level access to metabolic control programs).