A Study on Rural Health care Data sets using Clustering Algorithms

Rural healthcare datasets are often large, relational-and dynamic. These datasets contain records related to child welfare, pregnant woman health information and socioeconomic status of family. Data mining is very popular and essential in the healthcare industry due to fact that huge amounts of heterogeneous data being generated through healthcare transactions. It is a processing procedure of extracting credible, novel, effective and understandable patterns from database. Additionally, database consists of inconsistent and noisy data. This paper focuses on pattern generated from rural healthcare datasets using clustering algorithms thus helps in decision making process. The result of the experiment shows the comparison between the cluster generated and also justifying the uniqueness of the cluster by the values of attributes of these patterns. These patterns are generated on socioeconomic status of the locality and the data sets used are from Rural Maternity and Child Welfare (RMCW) database. These clustering techniques are implemented and analysed using a clustering tool WEKA.