Mustafa Tosur, MD
Associate Professor,
Baylor College of Medicine / Texas Children’s Hospital
Featured in the Session: Rising Minds: AI Innovations in Diabetes—NIDDK Early-Career Investigator Symposium
When
Sunday, June 7
at 8:00 a.m. CT
Where
La Nouvelle Orleans C (Level 2)
Ernest N. Morial Convention Center
What is your presentation about?
Youth-onset type 2 diabetes is an aggressive and progressive disease that has increased markedly in incidence over the past two decades, posing a growing public health challenge. This presentation focuses on the use of artificial intelligence (AI) to address the marked clinical heterogeneity of youth-onset type 2 diabetes and to improve outcome prediction. Specifically, I will describe the development of an AI foundation model that integrates structured and unstructured electronic medical record (EMR) data to predict key clinical outcomes, including glycemic management and treatment response, within two to five years after diagnosis. These approaches aim to enable more precise, individualized care for affected youth.
How do you hope your presentation will impact diabetes research or care?
This work highlights a practical and scalable approach to leveraging rich EMR data, both structured and narrative, to generate clinically meaningful predictions in youth-onset type 2 diabetes. By improving early risk stratification and treatment selection, these methods have the potential to support more personalized and effective diabetes care.
How did you become involved with this area of diabetes research or care?
My clinical and research work has long focused on the heterogeneity of diabetes in youth, including type 2, atypical, and monogenic forms. An interest in applying advanced analytical methods to this problem led me to explore artificial intelligence approaches. This work was initiated through a National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)-supported dkNET AI Pilot award, in collaboration with the Texas Children’s Data Science Center, which provided the opportunity to develop and apply these methods in a clinical research setting.