RESEARCH
Diabetes Analytics and Recommendation Engine
Diabetes is a chronic disease affecting over 415 million people worldwide. Effectively managing glucose levels on a daily routine is crucial to maintaining a healthy and threat-free lifestyle. In this paper, we propose the Diabetes Analytic and Recommendation Engine (DARE) Architecture to harness personal technologies in assisting type two diabetic patients to manage their glucose levels through a rule-based system coupled with anomaly detection and threat forecasting in a context-driven environment. To this end, the proposed DARE Architecture takes a modular, cloud native approach in applying machine learning to predict glucose levels and provide context-driven recommendations effectively.
Key Takeaways
01. Context
Diabetes is a lifelong condition which occurs when the body does not produce enough insulin, or when the insulin produced is not used effectively. Insulin is a hormone that helps the body control the level of sugar in the blood. Consequently, glucose builds up in the blood instead of being used for energy. If this condition is left unmanaged, the excess sugar in the blood can eventually cause problems which may lead to reduced quality of life. Fortunately, good diabetes care and management can assist in the mitigation of these complications.
02. Problem
With the widespread use of ever-personal technologies such as smartwatches and voice assistants, new techniques need to explored to enable the management of an individual's glucose levels. In order to accomplish this, relevant health factors that contribute to an individual's glucose levels need to be determined.
03. Solution
This paper proposes the Diabetes Analytic and Recommendations Engine (DARE) Architecture developed to assist diabetic patients to harness personal technologies to intuitively manage their glucose levels and receive recommendations to ensure they maintain their glucose levels within their prescribed bounds. The DARE Architecture aims at taking a modular approach in applying machine learning techniques to effectively predict glucose levels and providing context-driven recommendations.
04. Impact
This paper presents DARE as a tool to assist diabetic patients in interactively managing their glucose levels, receive relevant health tips through correlations of their daily routines, and harness smart Internet of Things devices for more accurate input of their health data.