A Comparison of Data Mining Algorithms for Liver Disease Prediction on Imbalanced Data
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.
Copyright (c) 2019 Ain Najwa Arbain, B. Yushalinie Pillay Balakrishnan (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
International Journal of Data Science and Advanced Analytics (IJDSAA) is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. This license allows users to copy, distribute and transmit an article, adapt the article as long as the author is attributed and the article is not used for commercial purposes.
The author(s) confirms
- The manuscript submission has not been previously published, nor is it before another journal for consideration (or an explanation has been provided in Comments to the Editor).
- The published materials used in the manuscript were obtained permission for reproduction. (if any)