Liver Disease Detection Model Using ML–Ensemble Approach With Interpolative Approach As Stacked Model

Medical diagnostics faces considerable challenges regarding the discovery and classification of inflammations that connect to liver conditions and fat accumulation and fibrosis. Such diseases need early detection as they could lead to severe health problems which calls for modern predictive modelling techniques. Multiple complex features require dedicated combination with heuristic approaches because this strategy improves the accuracy of clinical predictions. The proposed design utilizes different aspects of liver disease data to enhance diagnostic accuracy. The research adopts LR+XGB CLASSIFER in which LR is used for feature extraction method to locate dependent and independent variables while recognizing essential attributes that influence liver disease development. The overall design of the proposed approach focuses on leveraging various aspects of liver disease datasets to improve diagnostic precision. Specifically, the Logistic Regression (LR) model is employed as a feature extraction method to identify both dependent and independent variables, ensuring that critical attributes contributing to liver disease progression are accurately captured. An ensemble approach XGB classifier uses as a classification component and improves the accuracy. The model boosts predictive ability because it utilizes combined statistical techniques to extract complex patterns from the provided input data. The combined methodology attains a 96% accuracy rate which indicates its capability to detect liver conditions early while performing classifications when compared with two base classifiers like SVM and Decision tree.