期刊名称：International Journal of Computer Science and Network
印刷版ISSN：2277-5420
出版年度：2019
卷号：8
期号：4
页码：387-397
出版社：IJCSN publisher
摘要：Nowadays, Diabetes has become a constant chronic disease affecting the mankind. Various causes such as
bacterial or viral infection, toxic or chemical contents mix with the food, auto immune reaction, obesity, bad diet, change in
lifestyles, eating habit, environment pollution, etc. are responsible in increasing number of victims suffering from Diabetes.
Hence, It would be very helpful in predicting this disease at early stage and diagnosing the disease effectively. In health
care, this process is carried out using machine learning algorithms to analyze medical data to build to carry out medical
diagnoses. Diabetes Mellitus or Diabetes is a serious chronic disease which results in increase of blood sugar. It has always
been tedious to identify diabetes, but with emergence of machine learning the identification process has become simpler.
Three machine learning algorithms namely SVM, Decision Tree and Naive Bayes are used to detect Diabetes in earlier
stages. Algorithms are experimented and evaluated on measures like precision, Accuracy-measure and Recall. The results
obtained show Naive Bayes performs better with 76.30% compared to other algorithms. These results are verified using
Receiver Operating Characteristic (ROC) curves in a proper and systematic manner.
