Improved Heart Disease Prediction Using Particle Swarm Optimization Based Stacked Sparse Autoencoder

Heart disease is the leading cause of death globally. The most common type heart coronary disease, which occurs when there a build-up plaque inside arteries that supply blood to heart, making circulation difficult. prediction challenge in clinical machine learning. Early detection people at risk vital preventing its progression. This paper proposes deep learning approach achieve improved disease. An enhanced stacked sparse autoencoder network (SSAE) developed efficient feature consists multiple autoencoders and softmax classifier. Additionally, models, algorithm’s parameters need be optimized appropriately obtain performance. Hence, we propose particle swarm optimization (PSO) based technique tune autoencoder. by PSO improves classification performance SSAE. Meanwhile, multilayer architecture usually leads internal covariate shift, problem affects generalization ability network; hence, batch normalization introduced prevent this problem. experimental results show proposed method effectively predicts obtaining accuracy 0.973 0.961 on Framingham Cleveland datasets, respectively, thereby outperforming other methods similar studies.