K-Nearest Neighbor Learning based Diabetes Mellitus Prediction and Analysis for eHealth Services

Abstract

Nowadays, eHealth service has become a booming area, which refers to computer-based health care andinformation delivery to improve health service locally, regionally and worldwide. An effective disease riskprediction model by analyzing electronic health data benefits not only to care a patient but also to provideservices through the corresponding data-driven eHealth systems. In this paper, we particularly focus onpredicting and analysing diabetes mellitus, an increasingly prevalent chronic disease that refers to a groupof metabolic disorders characterized by a high blood sugar level over a prolonged period of time. K-NearestNeighbor (KNN) is one of the most popular and simplest machine learning techniques to build such a diseaserisk prediction model utilizing relevant health data. In order to achieve our goal, we present an optimal KNearest Neighbor (Opt-KNN) learning based prediction model based on patient’s habitual attributes in variousdimensions. This approach determines the optimal number of neighbors with low error rate for providingbetter prediction outcome in the resultant model. The effectiveness of this machine learning eHealth modelis examined by conducting experiments on the real-world diabetes mellitus data collected from medicalhospitals.

Keywords

• health data analytics
• diabetes mellitus
• data science
• machine learning
• k-nearest neighbor
• predictive analytics
• classification
• intelligent systems
• ehealth
• iot services