Enhancing Liver Disease Classification Based on a Stacked Machine Learning Model

Liver Disease (LD) poses a serious global health issue, emphasizing the need for precise and dependable diagnostic solutions. This research introduces an enhanced Machine Learning (ML) approach based on a stacked ensemble framework to classify LD cases, leveraging a publicly accessible dataset from Kaggle comprising patient records from India. Six ML models were applied, namely Random Forest (RF), Support Vector Machine (SVM), Dummy Classifier (DC), Extra Trees classifier (ET), K-Nearest Neighbors (KNN), and Logistic Regression (LR), with ET achieving the highest accuracy at 79.82%. To improve prediction accuracy, a stacked ensemble was developed using ET and RF as base classifiers and SVM as the meta-classifier, which boosted the overall accuracy to 98.53%. The study evaluated performance using accuracy, precision, recall, F1-score, and AUC. The findings highlight the effectiveness of stacking-based ML methods in building accurate and reliable diagnostic tools for liver disease classification.