An Interpretable PyCaret Approach for Alzheimer's Disease Prediction

Alzheimer's Disease (AD) is a major global health concern. The research focuses on early and accurate diagnosis of AD for its effective treatment and management. This study presents a novel Machine Learning (ML) approach utilizing PyCaret and SHAP for early and interpretable AD prediction. PyCaret employs a span of classification algorithms and the study identifies the best model. SHAP value determines the contribution of individual features for the final prediction thereby enhancing the model’s interpretability. The feature selection using SHAP improves the overall performance of the model. The proposed XAI framework improves clinical decision making and patient care by providing a reliable and transparent method for early AD detection.