An evolutionary prototype of a self-care application for type 2 diabetes

Abstract

Diabetes Mellitus or Diabetes is a chronic health condition. As there is no cure for both type 1 and 2 diabetes yet, the only solution is to manage the condition by improving lifestyle activities like eating and exercising and seeking medical advice. There are applications for diet planning, to analyze meals for nutrients, to suggest diabetic-friendly recipes and devices like blood glucose trackers to support type 2 diabetic patients. But there is no application or a device that can support a patient by addressing the diabetes condition. So, the plan is to conduct applied research on developing a mobile app for type 2 diabetes, capable of not only monitoring the patient’s physical activities but also for diet planning, monitoring diabetic peripheral neuropathy and diabetic foot ulcer (DFU) complications. This application provides point-of-care monitoring features that can help diabetic patients to understand their condition and to identify complication in advance and get necessary treatments. There are 3 main components focusing on patients’ diet, physical conditional, the possibility of diabetic peripheral neuropathy and DFUs. In order to implement these components, the intention is to use classification, clustering techniques in machine learning and CNN techniques for image processing. While the accuracies of the selected models built upon each feature (component) is more than 90%, the models have then been tested and concluded that each feature works accurately on patients.