Abstract:
Glycaemic Variability is one of the main complication diabetes patients’ face frequently. Even though smart equipment has been invented for blood glucose levels management, majority of the diabetes patients rely on Glucometer and other manual methods to measure and record their blood glucose levels in Sri Lanka. This research focuses on providing a solution for people in need, for predicting their blood glucose levels to benefit them in managing their Glycaemic levels. This study further focuses on the prediction ability of a sparser dataset (only 3 recordings per day) and proposes a methodology for predicting the blood glucose values for new patients. Entire study is divided into four broader categories as, personalized prediction with carb, personalized prediction without carb, non-personalized prediction with carb, and non-personalized prediction without carb. Out of the above four modules, personalized prediction with carb obtained the maximum prediction accuracy of mean rate of 85.3% for 8 patients. non-personalized prediction module obtained the maximum Glycaemic prediction accuracy mean rate of 79%.
