An Advanced Liver Disease Detection Tool with a Stacking-Ensemble-based Machine Learning Approach

Liver diseases (LD) encompass a variety of disorders associated with the liver, including infectious hepatitis, obesity, cirrhosis, and malignancy, which constitute significant health issues in the world. Due to the minimal symptoms, comprehending the disease becomes extremely difficult until its severe stages; earlier detection is advantageous for appropriate action, which could save lives. This study developed a StackLD framework based on the stacking-ensemble-based machine learning approach. In the preliminary phase, we collected the Indian Liver Patient Dataset (ILPD) dataset, which contains 11 features, and the dataset highlighted a significant discrepancy. To overcome this, we used the SMOTE to rebalance the dataset, facilitating the development of robust machine learning models. We applied 7 different models such as XGB, LGBM, DT, KNN, RF, KNN, and stacking approaches with several evaluation metrics on independent test methods The analysis presented that the stacking technique executed superior in accuracy, sensitivity, specificity, and area under the curve, with values of 0.8622, 0.8933, 0.8369, and 0.9275, respectively. These outcomes indicate that our approach effectively differentiates between positive and negative classes. This study illustrates that the Alkphos, Sgot, and Sgpt elements have a significant role in determining liver disease (LD) from various features. As a result, a web server was built using these attributes, demonstrating that our model accurately predicts liver disorders at an early stage which is useful insight into the medical field with the potential to improve diagnostic procedures and patient outcomes.