Shapley Additive Explanations (SHAP) for Cardiovascular Diseases Prediction

The increased number of deaths of cardiovascular diseases among people in both Low and Middle Income countries (LMICs) and in developed countries is alarming. There are Machine Learning (ML) models that have been developed for early diagnosis of CVDs, however, their success is low due to the black box nature of the models and the trust among the doctors is low thus hindering the models' acceptance. This research study focuses on developing an explainable AI model to predict CVDs over a period of ten years. The open CVD study dataset was used to develop multiple Machine learning models i.e KNN, Logistic Regression, XGBoost, Catboost, Random Forest and Decision tree. The models' performance was assessed based on F1-score, Accuracy, AUC, Precision, Recall, sensitivity, specificity and the confusion matrix metrices. From this study, it is observed that the XGBoost model performs better than the other models with an accuracy of 89%. SHapley Additive exPlanations (SHAP) explainable technique was later applied to all the models to understand their prediction for breaking the black box nature of Machine learning models. This research contributes to the identification of CVDs risk factors with the use of XAI and the early diagnosis of CVDs thus aiding in early intervention. The random Forest model performed better than the rest of the models with an accuracy of 98%.