Abstract
Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR.
Abstract (translated)
糖尿病是一种至今没有永久治愈的方法,是全球死亡人数的主要原因之一。糖尿病的急剧增长需要采取预防性措施来避免或预测其发生。本文提出了HealthEdge,一个基于机器学习的智能医疗保健框架,用于预测二型糖尿病。在集成的物联网边缘云计算系统中,使用了两个真实的糖尿病数据集,进行了数值实验和比较分析,使用了随机森林(RF)和Logistic Regression(LR)两种最常用的机器学习算法。结果表明,RF平均比LR预测糖尿病准确率高出6%。
URL
https://arxiv.org/abs/2301.10450