Liver Disease Prediction using Machine learning and Deep Learning

Abstract

Recently liver diseases are becoming most lethal disorder in a number of countries. The count of patients with liver disorder has been going up because of alcohol intake, breathing of harmful gases, and consumption of food which is spoiled and drugs. Liver patient data sets are being studied for the purpose of developing classification models to predict liver disorder. This data set was used to implement prediction and classification algorithms which in turn reduces the workload on doctors.The data set used in this paper is Liver Patient taken from UCI Repository (i.e. Supervised Learning). There is a plenty of data on patients undergoing medical examination at hospitals and these data has been extracted on liver patients whose information can be further used for future improvement of their conditions. In other words, historical and classified input of patients and output data is fed into various algorithms or classifiers for predicting the future data of patients. In this work, we proposed apply machine learning and deep learning algorithms to check the entire patient’s liver disorder.The algorithms used here for predicting liver patients are Decision Tree, KNNeighbor and Artifical Neural Network. Based on the analysis and result calculations, it was found that these algorithm has obtained good accuracy after feature selection. A Decision Tree boasts remarkable accuracy at 99.96%, leading the pack in precise liver disease predictions. Meanwhile, the KNearestNeighbour model follows closely at 97.42%, with Artificial Neural Networks achieving 71.55% accuracy, offering diverse options for predictive analysis.