Improving the Accuracy of Heart Failure Prediction Using the Particle Swarm Optimization Method

Abstract

Malfunction of the body's organs, heart failure, makes a person and those closest to them feel worried, which will result in the person's death. There are too many deaths caused by this deadly disease every year. The main problem throughout the world is heart disease, the death rate of which is getting higher and higher and is uncontrollable for various parties due to many factors, especially in terms of knowing it early or not being able to predict it accurately. Therefore, the aim of this research on heart failure problems is to improve heart failure predictions with optimal accuracy, namely the neural network method with the particle swarm optimization method. Previously, heart failure prediction research had been carried out using several methods, but here we will increase the accuracy of the methods that have been carried out. After the testing process on the neural network method and after being optimized and getting results from the particle swarm optimization method, the accuracy increased with an increase of 08.35%. As well as increasing AUC results with an increase of 0.067%. From the results of increasing the accuracy of the neural network method, testing the particle swarm optimization method on heart failure disease data can be used as a reference for stakeholders.