PITA Fiscal Year 2007 Projects

Biomedical and Health Engineering

Automating Information Collection for Diabetes Management
Our hypothesis is that near automatic data acquisition to support management of diabetes is possible. The proposed system will gather information on exercise (calories burned), food intake (calories consumed) and readings of sugar concentration. We will develop an image-recognition system to determine a diabetes patient’s calories consumption. We will also implement a tear-based glucometer, which changes color based on the amount of glucose and use an image–recognition system to determine color and corresponding tear glucose level. In our prior work, we have built DiMA, the Diabetes Management Assistant, that facilitates self-monitoring, training, and patient/doctor communication with individuals who have diabetes. Pilot studies with nurses and patients at UPMC have shown that DiMA effectively assists patients and care providers with monitoring diabetes. Our monitoring platform will be a camera-equipped cell phone augmented with accelerometers. A cell-phone camera can take a picture of the contact lens to determine the blood sugar level without having to draw blood. Blood Glucose Determination will comprise detecting the eye location, locating the glucose indicator, and analyzing the indicator’s color to determine the patient’s blood glucose level. For food caloric intake determination, we will detect food items in an image and classify food items by comparison with training samples. We will use a picture of a meal to determine the food and serving size, derive the calories consumed from the image, and create a diabetic management system that records almost all data automatically. Unsupervised machine learning algorithms will monitor accelerometer data to determine type and intensity of user activity.