Detection of Type 2 Diabetes Using Clustering Methods – Balanced and Imbalanced Pima Indian Extended Dataset

TLDR: Large and small datasets have been taken for clustering using K-means approach, Farthest first method, Density based technique, Filtered clustering method and X-mean approach and the proposed method is Dimensionality reduction and clustering technique gives the highest accuracy.

Abstract: Diabetes mellitus is a metabolic illness that causes high blood sugar, which is widely known as diabetes. Insulin is a hormone produced by an organ situated behind the abdomen called the pancreas. This insulin agent moves glucose from your blood into the cells for energy and storage. With diabetic disorder, the body either will not create enough insulin or can’t effectively use the insulin it does create. Untreated high blood glucose or sugar from diabetic disorder will harm the nerves, eyes, kidneys, and different organs of the body. There are different data mining software tools to predict and analyze diabetes. Many attempts have been made by researchers to improve the efficiency of various models. The proposed method is Dimensionality reduction and clustering technique. It gives the highest accuracy for the larger dataset for both balanced and imbalanced datasets. In this paper, large and small datasets have been taken for clustering using K-means approach, Farthest first method, Density based technique, Filtered clustering method and X-means approach. K-means, density based and X-means gives the highest accuracy of 75.64%. For the larger balanced dataset when compared with the smaller balanced dataset.