Abstract
The liver is a vital organ in the human body since it is in charge of metabolism, detoxification, storage, digestion, blood sugar regulation, and immunological function. As a result, any harm or dysfunction to it can result in serious illness. Hence, early detection of it provides effective treatment, prevents further damage, cost-effective, and overall increases the survival rate of a particular individual. In this paper, we have taken the BUPA Liver Disease (LD) dataset from the UCI repository. We worked with several machine learning algorithms (MLAs) such as Decision Tree (DT), K-Nearest Neighbors (KNN), Multilayer Perceptron (MLP), Adaptiveptive Boosting (AB), Random Forest (RF), Gradient Boosting (GB), Extreme Gradient Boosting (XGB), Logistic Regression (LR), Gaussian Naive Bayes (NB), Extra Tree (ET), Light Gradient-Boosting Machine (LGBM), and Support Vector Machine (SVM). After applying these twelve methods, we made predictions about the possibility of having the liver disease or not. Here, we have found DT to be the best among the twelve algorithms with accuracy, precision, recall, and Fl-Score of 86.67%, 0.87, 0.87, and 0.86, respectively.
Funding Information
  • CSIR (09/1277(0001)/2019-EMR-I)

This publication has 18 references indexed in Scilit: