Comparative Study of Machine Learning Models for Liver Disease Prediction

Liver disease continues to be a major public health issue worldwide, with delayed diagnosis contributing significantly to increased mortality and treatment challenges. This study aims to enhance diagnostic accuracy by machine learning models trained on a large, real-world clinical dataset. The research involves evaluating supervised models- Random Forest, Support Vector Machine, Logistic Regression, and Artificial Neural Networks. To determine their effectiveness in predicting liver disease. The research utilizes actual patient records to assess the capabilities of various learning algorithms. Data preprocessing, including normalization and feature selection, ensures reliable model outputs. Evaluation metrics such as accuracy, precision, recall, F-Score and ROC-AUC were used to measure model performance. in future extensions, the study will focus on refining feature engineering methods and incorporating deep learning architectures to further improve the prediction and early detection of liver disease. Future research will focus on exploring deep learning and hybrid modelling frameworks to further enhance diagnostic accuracy.