Liver Disease Classification by Analysing Salient Features of Liver Function Test (LFT): An Explainable Machine Learning Approach

The liver is a vital organ that performs numerous crucial functions for overall health. However, liver malfunctions can prove fatal, underscoring the urgency of early disease detection. Traditional liver disease classification methods are hampered by complexity and variability, prompting the adoption of Machine Learning (ML) algorithms. In this study, we endeavor to develop a soft computing model leveraging Liver Function Tests (LFTs) for accurate disease classification. Notably, our analysis revealed L2 regularized XGBoost as the standout performer, achieving an impressive 99.94% accuracy. Moreover, our investigation delved deeper into the root causes of liver diseases, shedding light on their underlying mechanisms and relationship to liver function components. By integrating Explainable AI (XAI), our model ensures transparency and provides invaluable insights for informed decision-making. Our project aims to deliver an efficient and robust classification model for liver diseases, poised to significantly impact early detection and patient outcomes.