The Application of Machine Learning in Liver Disease Diagnosis: Analysis of Algorithm Performance and Axiological Implications

Abstract

Liver disease remains a significant global health challenge, requiring accurate and timely diagnosis to improve patient outcomes and reduce healthcare costs. This study investigates the application of four machine learning classification algorithms—Decision Tree, Random Forest, Naïve Bayes, and K-Nearest Neighbors (KNN)—to predict the presence of liver disease using a dataset sourced from Kaggle. These algorithms were evaluated based on performance metrics such as accuracy, precision, recall, and F1 score. Both Decision Tree and Random Forest achieved the highest accuracy rate of 72.41%, demonstrating their robustness in classifying liver disease cases. However, these models showed some limitations in identifying patients without liver disease. Naïve Bayes, with an accuracy of 60.34%, exhibited an impressive recall rate of 96.97%, indicating its potential in detecting liver disease cases, though at the cost of lower precision. KNN, with an accuracy of 70.69%, proved to be a competitive option in the classification task. Beyond technical performance, the study also explores the ethical and axiological implications of using machine learning in healthcare, emphasizing the importance of fairness, transparency, and human oversight. The research highlights the need for responsible deployment of machine learning technologies, ensuring they are aligned with ethical standards to avoid biases and enhance healthcare outcomes. This study demonstrates that machine learning can significantly support liver disease diagnosis, though it must be integrated with a comprehensive ethical framework to ensure equitable and transparent decision-making in clinical practice.