Hybrid Optimization Algorithms for Accurate Prediction and Classification of Cardiovascular Diseases

A collection of precise prediction models is necessary to lessen the burden of cardiovascular disease (CVD), which continues to be a leading cause of death worldwide. This work presents a unique hybrid optimization approach for improving the categorization and prediction of cardiac disease. Support Vector Machine (SVM), Salp Swarm Optimized Neural Network (SSO-NN), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Bayesian Optimization of SVM (BO-SVM), and by combining PSO and gradient descent (PSOGD) are some of the advanced machine learning algorithms that have been implemented with improved accuracy. Training, testing, and validation are done using the Cleveland and Framingham datasets. Imputation for missing data and feature scaling using MinMaxScaler are important preprocessing processes. In order to evaluate performance parameters like as sensitivity, specificity, and accuracy. As a consequence, the hybrid PSOGD algorithm achieved impressive results, with accuracies with the dataset of Cleveland having 99.56% and other dataset Framingham having 98.80%. The model's robustness was shown by the sensitivity and specificity results. The measures like Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) over epochs, the performance analysis is further testified to for model validation. It suggests that hybrid optimization algorithms that improve CVD prediction models be praised as essential for management planning and early identification. By exposing scalable alternatives for heart disease prediction, our study offers crucial help in the area where AI and health intersect.