Proposal Number: 2037383 Principal Investigator: Xia Zhou, Gregory Forlenza, Qiang Liu, Temiloluwa Prioleau & Tam Vu Institutions: Dartmouth College, University of Colorado & University of Texas
Type-1 diabetes affects over 1.25 million people in the United States and its incidence is increasing every year. The majority of type 1 patients are not successful in achieving target blood glucose levels and control has actually been worsening in recent years despite expanded use of technologies. Inadequately controlled diabetes is the leading cause of blindness, kidney failure, heart attack and peripheral vascular disease possibly leading to amputation and in some cases death. Joint use of a continuous glucose monitor and insulin pump is considered the current gold standard for management of type-1 diabetes. Existing technologies, however, suffer from two well-established limitations: high user burden due to the need for manual ?meal announcements? to estimate insulin doses and low adherence to glucose monitoring devices due to the inconvenience of constantly breaking the skin for sensor insertion and irritation from the sensor adhesive. Thus, there is an urgent need in public health for fully automated, closed-loop glycemic control for type-1 diabetes patients, which will be the focus of the proposed research.
The proposed work aims to develop and pilot a joint multimodal sensing system that can provide continuous noninvasive glucose monitoring data in addition to automated meal detection with an estimate of meal intake. Both types of information are necessary to inform artificial pancreas algorithms for prediction of bolus (i.e. short-acting) insulin dose needs. More specifically, the proposed system is in the form of an ear-worn device, tackling key systems and algorithmic challenges to realize a fully closed-loop artificial pancreas system. The intellectual merits of the proposed work are following. First, it will develop novel system designs to realize fine-grained, robust dietary sensing by fusing three streams of signals (i.e., bio-electrical signals, motion, and acoustic signals); Second, it will advance existing optical-based noninvasive glucose monitoring by addressing challenges of skin scattering and mitigating the impact of confounding factors and user diversity; Third, it will present new energy-efficient machine learning models dedicated to enabling local execution at micro-controllers, dealing with the limited number of labeled training data, and ensuring data privacy and communication efficiency; Finally, it will characterize and validate biological and behavioral biomarkers most relevant to diabetes management for implementing an artificial pancreas systems and develop new approaches for adaptive sampling and noise handling to ensure accurate monitoring of target events.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
