Speakers: Mark Clements, MD, PhD

Mark Clements, MD, PhD

Professor of Pediatrics
University of Missouri-Kansas City
Pediatric Endocrinologist
Children’s Mercy

 

Dr Mark Clements, MD, PhD is a Professor of Pediatrics at the University of Missouri-Kansas City, and Pediatric Endocrinologist at Children’s Mercy Hospital in Kansas City. He holds the Rick and Cathy Baier family endowed chair in endocrinology and has been supported by numerous grants from the National Institutes of Health, the Helmsley Charitable Trust and JDRF. He has authored or co-authored over 100 scientific manuscripts. From 2016-2019, he served as Pediatric Chair of the T1D Exchange Clinic Registry. He was a founding member of the T1D Exchange Quality Improvement Collaborative and served as the Data Science Co-Lead from 2016-2022. He was a member of the multi-national team responsible for the Exercise in Type 1 Diabetes (T1DEXI) study, having created the high-tech data integration system that allowed data collection from multiple wearable devices. He has pioneered the creation of the Rising T1DE Alliance, an initiative to use transformational approaches to improve type 1 diabetes care. His research interests include type 1 diabetes prevention, exercise in type 1 diabetes, behavioral interventions in youth and their parents, clinical trials of advanced technologies and digital therapeutics, and the use of big and small data alike to improve type 1 diabetes care via advanced machine learning and artificial intelligence.

The Rising T1DE Alliance: A Transformational Initiative to Improve Type 1 Diabetes Care

Diabetes centers and individuals with diabetes generate abundant data about diabetes-related outcomes and about self-management behaviors, comorbid medical conditions, and clinical care-related events. Yet few of these data are used by clinicians for decision making. Risk-based management protocols can help to improve both the quality and cost-efficiency of care. These protocols may be driven by biomarkers of risk extracted from electronic health records, diabetes self-management, and digital patient reported outcomes platforms; protocols may also be driven by forecasting of negative outcomes via Artificial Intelligence/Machine Learning approaches. Clinic participation in Learning Health Networks, with data sharing to a central data repository, can accelerate Big-Data-driven quality-improvement of care delivery. The presenter will 1) review examples of risk-based management approaches using each technique, including novel biomarker-based risk indices, and 2) further examine the current state of algorithms and AI/ML to manage population health in diabetes clinics. Many examples are derived from the work of the Rising T1DE Alliance, which seeks to implement multiple ML models to predict outcomes in clinical care, and to test remote patient monitoring along with multiple digital and behavorial health interventions to improve those predicted outcomes via a risk-based management approach.