Jaya Algorithm-based Optimization of Random Forest for Liver Disease

Liver disease is a significant public health issue worldwide, and early detection is critical for successful therapy and control. The traditional diagnosis is usually invasive and not easily available. To achieve this, several machine learning (ML) models such as Support Vector Machine (SVM), Random Forest, Logistic Regression, and Cat Boost were compared based on various clinical markers such as liver function tests, bilirubin, and lifestyle variables. All the models were first tested for predictive capability followed by optimization using Jaya Optimization for hyper parameter optimization and feature selection. The optimization process further optimized the accuracy and efficiency of every model. Among them, Random Forest had consistently better predictive capabilities after optimization. The research culminates in the creation of a clear and user-friendly decision-support system (DSS) intended to help healthcare professionals in early intervention and detection. Through the integration of ML and optimization methods, the suggested approach makes contributions to liver disease diagnosis becoming more precise, accessible, and efficient, hence improving patient outcomes.