The liver, as the largest internal organ in the human body, plays a pivotal role in numerous physiological processes, orchestrating over 500 metabolic activities crucial for maintaining bodily functions. However, the Hepatitis C Virus (HCV) poses a grave threat to liver health, necessitating early identification of liver diseases to halt the progression to carcinoma and potentially save lives. This research aims to train ensemble-based algorithms for classifying and detecting Hepatitis, Fibrosis, and Cirrhosis. Employing rigorous preprocessing techniques, 80% of the dataset was allocated to train five ensemble-based algorithms: AdaBoost, Random Forest, Rotation Forest, XGBoost, and LightGBM. These algorithms were evaluated across four performance metrics—accuracy, precision, recall, and F1-score. Remarkably, LightGBM emerged as the frontrunner, boasting an exceptional accuracy rate of 98.37%. Rotation Forest followed closely with an accuracy of 96.74%, while XGBoost attained an accuracy of 95.12%. Random Forest and AdaBoost secured 94.19% and 93.30% accuracy, respectively. These findings underscore LightGBM’s prowess as a promising algorithm for detecting and classifying liver diseases. By leveraging advanced machine learning techniques, particularly ensemble-based algorithms, this research contributes to the ongoing efforts to enhance early detection, improve patient outcomes, and foster more effective management strategies for liver-related ailments in clinical settings
