| 要約: | Early and accurate detection of liver disease is critical to improving patient outcomes yet remains challenging due to class imbalance and noisy clinical data. In this study, we present a robust ensemble learning framework applied to the Indian Liver Patient Dataset, incorporating systematic data cleaning, normalization, and Synthetic Minority Over‑Sampling (SMOTE) to address missing values, outliers, and class skew. We then perform correlation-based feature reduction before training a stacking classifier that combines Random Forest, XGBoost, and ExtraTrees base learners with an ExtraTrees meta‑learner. Using stratified 10‑fold cross‑validation on the balanced cohort (n = 792), our ensemble achieves 91.6 % accuracy, 92 % F1‑score, and a high area under the ROC curve, outperforming individual models and prior published approaches. These results demonstrate the potential of heterogeneous ensembles for clinical decision support in hepatology and lay the groundwork for prospective validation in diverse patient populations.
|
|---|
