The primary focus of the proposed work is to develop a model that exploits the rich data collected from numerous CGM (Continuous Glucose Monitors) and the associated time stamped meal disturbance input, exercise metrics and psychological stress estimates (from wearable sensor), and serum ketones levels (Tidepool data). Machine learning and Deep learning have matured to a level which permits the teasing out of subtle dynamics from large data sets. The PIs propose a coupled solution consisting of a machine learning based big data model and a first principled approach, such that the two components inform each other. The goal of this project is to develop models that can be used to drive the safety and efficacy of artificial pancreas technology for patients with Type 1 diabetes.The Research Foundation of SUNY on behalf of University at Buffalo is a recipient of JDRF's research grant — Identification of Areas of Artificial Pancreas Algorithm Enhancements Through Big-Data Analysis — supported by Tidepool Big Data Donation Project.