Led by our wonderful UG researcher Sahana, our abstract on data-driven insights on physical activity and hypoglycemia in type 1 diabetes has been accepted as an ORAL presentation at the prestigious American Diabetes Association (ADA) annual meeting to be held in New Orleans in June 2022. In this work, we build computation models from multi-modal data (CGM, insulin, physical activity metrics) to identify the key predictors of exercise-induced hypoglycemia. We propose a novel CGM-based measure that is independently associated with extent of hypoglycemia 2 hours after exercise. More details may be found here.

We are grateful to the Tidepool Big Data Donation project for providing the physical activity data for anlaysis. Huge thanks to the awesome Dr. Dan DeSalvo and Dr. Alex Siller for their clinical guidance, to my mentor Dr. Ashu Sabharwal for his inputs on the analysis, and to my UG mentees Sahana and Jeremiah Johnson for their fantastic work!

Multi-modal data showing glucose, physical activity, insulin, and carb intake in a study participant. Sharp glucose drop post-exercise can be observed. Image may not be reused or reshared without written permission of the authors of the abstract in the link above.