An Efficient Hybrid Classification Model for Heart Disease Prediction

Abstract

Abstract Background: Heart disease prediction is a critical healthcare task for identifying individuals at risk and enabling timely intervention. Accurate prediction models can help reduce morbidity and mortality rates associated with cardiovascular conditions. Various approaches, such as feature selection and hybrid models, have been proposed to improve the effectiveness and accuracy of the prediction of heart disease. Method: The study employs the Genetic Algorithm-Support Vector Machine-Convolutional Neural Network (GA-SVM-CNN) approach and evaluates it on three diverse datasets: UCI, Z-Alizadeh Sani, and Cardiovascular Disease Dataset. The genetic algorithm is utilized first to select the most relevant features from the datasets, effectively reducing dimensionality, eliminating irrelevant or redundant features, and choosing the most suitable ones. Subsequently, the hybrid SVM-CNN model is trained using the selected features, harnessing the complementary capabilities of both techniques to enhance prediction accuracy. Results: The performance of the GA-SVM-CNN approach is assessed using the three benchmark datasets and models. On the UCI dataset, the approach achieves an impressive accuracy of 98%, indicating its effectiveness in accurately predicting heart disease. On the Z-Alizadeh Sani dataset, the approach achieves an accuracy of 97%. On the Cardiovascular Disease Dataset, the approach achieves an accuracy of 86%. These high accuracy rates across different datasets underscore the efficacy of the GA-SVM-CNN approach in heart disease prediction. Conclusion: The combination of the genetic algorithm’s feature selection and the hybrid SVM-CNN model’s predictive power leads to superior performance in heart disease prediction. By accurately identifying individuals at risk of heart disease, this approach can enable timely interventions and contribute to more effective healthcare interventions.