Customer 360-degree Insights in Predicting Chronic Diabetes
This work addresses diabetes prediction for healthcare providers and patients, but it is incremental as it applies an existing classification model to new data.
The study tackled predicting chronic diabetes using a large dataset of 10 million customers with over 1,000 attributes, achieving an accuracy of 80% to enable proactive disease management and reduce healthcare costs.
Chronic diseases such as diabetes are quite prevalent in the world and are responsible for a significant number of deaths per year. In addition, treatments for such chronic diseases account for a high healthcare cost. However, research has shown that diabetes can be proactively managed and prevented while lowering these healthcare costs. We have mined a sample of ten million customers' 360-degree data representing the state of Texas, USA, with attributes current as of late 2018. The sample received from a market research data vendor has over 1000 customer attributes consisting of demography, lifestyle, and in some cases self-reported chronic conditions. In this study, we have developed a classification model to predict chronic diabetes with an accuracy of 80%. We demonstrate a use case where a large volume of 360-degree customer data can be useful to predict and hence proactively prevent chronic diseases such as diabetes.