Explainable AI for Enhanced Interpretation of Liver Cirrhosis Biomarkers

Abstract

Liver cirrhosis is a terminal pathological result of chronic liver damage, illicit drugs, hepatotoxicity, and non-alcoholic steatohepatitis. Assessment of liver cirrhosis via non-invasive methods in order to circumvent the limitations of liver biopsy. This research builds upon the growing body of knowledge in liver cirrhosis assessment by examining a dataset comprising cases of primary biliary cirrhosis. Prior research has primarily concentrated on comparative analyses and development of machine learning models integrating imaging modalities such as ultrasound, magnetic resonance imaging (MRI), and elastography, with limited focus on serum biomarkers. This research endeavors to address the neglected aspects of liver cirrhosis assessment by leveraging Explainable AI algorithm to bridge the gap between AI models and human comprehension via providing insights into the intricate decision-making process of the proposed machine learning model, thus enhancing transparency and trustworthiness. This novel approach aims to overcome the limitations of previous works and contribute to improved liver cirrhosis diagnosis.