Harmonizing Machine Learning Algorithms for Enhanced Liver Disease Prediction: A Comparative Study of Accuracy and Efficacy

In this review paper, various machine learning techniques applied to predict liver disease have been studied. Non-Alcoholic ‎Fatty Liver Disease (NAFLD) is a leading cause of global mortality, which affects millions of people worldwide. The diagnosis ‎of NAFLD can be both costly and complex. Therefore, this research aims to reduce these challenges by assessing the capability ‎of various machine learning models to prevent NAFLD, thereby reducing the overall cost of diagnosis. We have used 3 classification algorithms-‎Logistic Regression, Support Vector Machine, along the Random Forest technique for enhanced prediction accuracy. ‎Our study evaluates these models based on metrics like accuracy, precision, recall, and F1 score. Also, we are inclined towards ‎developing a hybrid model to further improve efficiency. Based on our study of various other papers, it was found that integrating-‎ing multiple Machine Learning (ML) techniques helps to significantly enhance the performance, offering an efficient approach ‎towards the diagnosis‎.