An efficient clustering algorithm for predicting diseases from hemogram blood test samples

Abstract

This research work primarily focuses on predicting diseases from the hemogram blood test data set by using data mining techniques. In this research, a new clustering algorithm which is named as weight based k-means algorithm is developed for identifying the leukemia, inflammatory, bacterial or viral infection, HIV infection and pernicious anaemia diseases from the hemogram blood test samples data set. The newly proposed weight based k-means algorithm efficiency is evaluated with Fuzzy C-means and K-means clustering algorithms. These algorithms performances are evaluated by using the cluster accuracy, error rate and execution time. From the results investigation, it is known that the proposed weight based k-means algorithm performance is better than the other algorithms.