PERFORMANCE EVALUATION OF VARIOUS SUPERVISED MACHINE LEARNING ALGORITHMS FOR DIABETES PREDICTION
European Journal of Molecular & Clinical Medicine,
2020, Volume 7, Issue 8, Pages 4921-4925
Abstract- Diabetes is a chronic disease, causes due to increasing high level of sugar in blood and it directly impact on human body organs. When level of sugar increase in blood, body doesn’t produce required amount of insulin or sometimes it does not use sufficient available insulin that impact on too much glucose are present in blood. This can cause various health issues that may be dangerous to the human life. Every time person visits to diagnosis center and they spent money for diagnosis of disease. Various Machine Learning algorithms with help of data mining techniques can solve this problem. The data mining techniques play important role in healthcare industries to prediction of disease such as diabetes disease, heart disease, kidney disease etc. The goal of this paper is three machine learning algorithms namely K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF) is used to for early prediction of diabetes disease. Also, all these three algorithms are compared based on performance metrics.
- Article View: 107
- PDF Download: 353