Explainable AI Modeling in the Prediction of Cardiovascular Disease Risk

Abstract

The objective of this study was to develop explainable AI modeling in the prediction of cardiovascular disease. The XGBoost algorithm was used followed by rule extraction and argumentation theory that provides interpretability, explainability and accuracy in scenarios with low confidence results or dilemmas. Our findings are in agreement with previous research utilizing the XGBoost machine learning algorithm for prediction of cardiovascular risk, however it is supported by rule based explainability, offering significant advantages in terms of providing both global and local explainability. Further work is needed to enhance the argumentation-based rule interpretability, explainability and accuracy in scenarios with low confidence results or dilemmas.