A Comparative Study of Data Mining Techniques for HCV Patients’ Data

Abstract: Hepatitis C is one of the most widespread sources of the liver failure and cancer and represents a major public health problem. Data mining techniques play’s significant role in the field of Health informatics. Therefore we have applied different data mining techniques which include Naïve Bayesian Classification, Decision Tree and Fuzzy C-means on hepatitis C patients’ data for observing the factors of high prevalence of the risk of hepatitis C virus. The dataset has been taken from the machine learning warehouse of University of California. Missing values of the instances are adjusted using mean value attribute method and the dimensions are trimmed down using PCA which capitulate the seven attributes including class attribute. It has been presented that the results obtained by the algorithms in this paper are better than the other techniques of the compared research papers.

Keywords: Hepatitis C Virus (HCV), Data Mining, Clustering, Classification, Naïve Bayesian Classification, Decision Tree and Fuzzy C Mean (FCM).

Department of Computer Science, University of Karachi, tahseenjilani@uok.edu.pk, mshoaibuok@gmail.com, smrehanrasheed@gmail.com, bilal.ur.rahman@hotmail.com

[PDF]

Cite: Tahseen A. Jilani, Muhammad Shoaib, Rehan Rasheed, Bilal ur rehman, "A Comparative Study of Data Mining Techniques for HCV Patients’ Data," Progress in Intelligent Computing and Applications , vol. 4, no. 1, pp. 10-17, March 2015.