Evaluation and Classification of Master Health Checkup Database using Data Mining Techniques Manimannan G.1,*, Priya R. Lakshmi2 1Assistant Professor, Department of Mathematics, TMG College of Arts and Science, Chennai, India 2Assistant Professor, Department of Statistics, Dr. Ambedkar Govt. Arts College, Vyasarpadi, Chennai, India *Corresponding author email id: manimannang@gmail.com
Online published on 21 May, 2020. Abstract The intention of this paper is to explore the possibility of identifying meaningful groups of MHC database that are scaled as the best with respect to their medical observations (parameters) using Self Organizing Map (SOM). Initially, k means clustering is used to identify underlying groups based on 29 medical parameters and cross validate the derived clusters using SOM. The next stage of this research paper is to analyze the MHC database and achieved that only 3 groups could be meaningfully formed for all the data. This indicates that only 3 types of patients existed over the study period. Further, the MHC patients find themselves classified into Normal (Cluster N), Under Weight (Cluster UW) and Obesity (Cluster O) categories depending on certain medical observations. A generalization of the results is under investigation to obtain an incorporated class of 3 groups of MHC patients for any given samples. Top Keywords Self organizing map, k-mean clustering, Classification, Data mining and master health checkup. Top |