Detection and Prediction of Liver Disease Using Interpolative Ensembled Stacked (IES) Hybrid Model (Random Forest Classifier (RFC) and Logistic Regression (LR))
Abstract
In this work proposed Interpolative Ensembled Stacker hybrid algorithm named Random Forest Classifier and Logistic Regression in prediction and detection of liver disease. The ensemble model harnesses the strengths of both algorithms to enhance predictive accuracy. Leveraging a diverse set of features, the proposed model achieved greater impressive accuracy. The Random Forest component contributes its ability to handle complex interactions and non-linear relationships, while Logistic Regression provides interpretability and simplicity. The synergy between these models not only improves predictive performance but also enhances the transparency of the decision-making process. In this work comprehensive comparative analysis also performed between proposed and established models. This proposed ensemble approach holds promise for accurate and reliable liver disease prediction, offering a valuable tool for early diagnosis and intervention in health care domain.
Keywords
Liver Disease, Interpolative Ensembled Stacked (IES), Hybrid algorithm, RFC and LR, the impact of Covid-19.