Liver Disease Classification Using Explainable Artificial Intelligence

Liver disease poses a significant health burden worldwide, necessitating accurate prediction methods for early diagnosis and intervention. In this study, we employed models including Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Bayes Classifier, augmented by Explainable Artificial Intelligence (XAI), to predict the presence of liver disease in individuals. SVM served as the primary predictive model, while XAI technique Local Interpretable Model-agnostic Explanations (LIME) provided insights into the model’s decision-making process, enhancing interpretability and trustworthiness. Through this approach, we aimed to improve diagnostic accuracy and facilitate informed clinical decision-making. An Multi-criteria decision analysis (MCDA) has been conducted using Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to find out the best model considering different performance measures as criteria. Our findings emphasize the utility of integrating traditional AI methods with XAI technique LIME for enhancing predictive modeling in healthcare settings.