The applications of the data mining in the different fields like e-business, commerce and trade has widely improved. The medical field also has lot of information but awareness is less. General health inspection is very important part of health care in many countries. Finding the persons at risk is important for providing the early warnings and takes the prevention to them. One of the major challenges that can be faced by learning classification model for risk prediction mainly depends on the unlabeled data that takes major portion of the collected dataset. Especially the unlabeled data in the dataset reveals about the people in the health examination whose health conditions can change greatly from healthy to too-ill. There is no proof for changing their health conditions. In this paper we propose a C 4.5 algorithm for risk predictions. C4.5 algorithm is used as the training algorithm to show rank of High risk cases with the decision tree. The health record dataset is clustered using the K-means clustering algorithm.
Article Details
Unique Paper ID: 145514
Publication Volume & Issue: Volume 4, Issue 10
Page(s): 873 - 876
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024