A Comparison of Data Mining Algorithms for Liver Disease Prediction on Imbalanced Data

  • Ain Najwa Arbain Asia Pacific University of Technology & Innovation
  • B. Yushalinie Pillay Balakrishnan Asia Pacific University of Technology & Innovation
Keywords: Liver disease Prediction, Imbalanced Data, Data Mining, Classification

Abstract

Liver is one of the most important organs in the human body but due to unhealthy lifestyle and excessive alcohol intake, liver disease has been increasing at an alarming rate globally hence it calls for an immediate attention to predict the disease before it is too late. However, medical data is often associated to be imbalanced and complex. Hence, the aim of this project is to investigate the data mining algorithm to predict liver disease on imbalanced data through random sampling. Results are compared and analysed based on accuracy and ROC index. K-Nearest Neighbour (k-NN) outperforms the other algorithms such as Logistic Regression, AutoNeural and Random Forest with the accuracy of 99.794%. As a conclusion, the model proposed in this research is performing better than past researchers conducted on Andhra Pradesh liver disease dataset.

Published
2019-02-09
How to Cite
Arbain, A. N., & Balakrishnan, B. Y. P. (2019). A Comparison of Data Mining Algorithms for Liver Disease Prediction on Imbalanced Data. International Journal of Data Science and Advanced Analytics, 1(1), 1-11. Retrieved from http://ijdsaa.com/index.php/welcome/article/view/2
Section
Articles