GlucoGuide: An Intelligent Type-2 Diabetes Solution Using Data Mining and Mobile Computing

Type-2 Diabetes (T2D) is a dreadful disease affecting hundreds of millions of people worldwide, and is linked and worsen by unhealthy lifestyles. However, managing T2D effectively with lifestyle change remains highly challenging for both T2D patients and doctors. In this paper, we proposed, built, and evaluated a personalized diabetes recommendation system, called Gluco Guide for T2D patients. Gluco Guide conveniently aggregates a variety of lifestyle data via medical sensors and mobile devices, mines the data with a novel data-mining framework, and outputs personalized and timely recommendations to patients aimed to control their blood glucose level. To evaluate its clinical efficiency, we conducted a three-month clinical trial on human subjects. Due to the high cost and complexity of trials on human, a small but representative subject group was involved. Two standard laboratory blood tests for diabetes were used before and after the trial. The results are quite remarkable. Generally speaking, Gluco Guide amounted to turning an early diabetic patient to be pre-diabetic, and pre-diabetic to non-diabetic, in only 3-months.