Comparative Analysis Of Liver Diseases By Using Machine Learning

ABSTRACT: Liver diseases constitute a major public health concern worldwide, often leading to life- threatening conditions if not diagnosed and treated in time. Conventional diagnostic methods rely heavily on clinical expertise and laboratory tests, which can be time-consuming and may not always yield accurate early detection. With the growing availability of healthcare data, machine learning (ML) techniques have emerged as powerful tools for disease prediction and classification. This paper presents a comparative analysis of liver disease prediction using multiple ML algorithms, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). The study utilizes the Indian Liver Patient Dataset (ILPD) and applies various preprocessing and feature selection techniques to optimize model performance. Results are evaluated using accuracy, precision, recall, F1-score, and ROC-AUC metrics. The analysis reveals that ensemble methods such as Random Forest outperform other models in both accuracy and robustness, offering a promising direction for automated liver disease diagnostics. Keywords : Liver, K-Nearest Neighbors , machine learning