Performance Analysis of Machine Learning Models for Liver Disease Patient Classification

Liver disease is a significant global health concern, necessitating the development of accurate and efficient diagnostic tools. This study presents a comparative analysis of various machine learning classifiers, including Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), XGBoost, and Ensemble Models, for the classification of liver disease patients. The challenge of class imbalance in the dataset is addressed using Synthetic Minority Over-sampling Technique (SMOTE), ensuring a more balanced and representative training process. Missing data is handled with the K-Nearest Neighbors (KNN) Imputer, while Recursive Feature Elimination (RFE) is employed to select the most relevant features, optimizing the model’s performance. Experimental results demonstrate the effectiveness of these approaches, with a detailed comparison of each classifier’s performance in terms of accuracy and F1-score. This study provides valuable insights into the strengths and limitations of different machine learning classifiers for liver disease classification, contributing to the advancement of predictive modeling in healthcare.