Integrating Genetic algorithm and Leverage the slap swarm algorithm to optimize the Multi-Objective Random Forest model to predict cerebrovascular disease

Abstract

Heart disease is now a big health worry for many people because it is the top cause of death in the world. Finding heart problems such as heart diseases, valve problems, and so on is one of the most important jobs and regular medical study. Heart problems may save numerous lives if it is found early. A lot of progress has been made in using machine learning methods in the medical field. In the suggested work, a new SSO-MORF (Slap Swarm Optimised Multi-Objective Random Forest) method for predicting heart disease was shown. For this proposed study, data on heart disease from many Universities was mined using data mining techniques such as categorisation and individual customer recognition. For getting the data ready and pulling out features, min–max normalisation along with principal component analysis, or PCA, had been used. So, a pretty simple guided machine learning method could be used to very correctly identify heart problems, which would be very useful. The RF method was used in this study to make a classification that had 99.46% accuracy, 98.4% memory, 98.7% precision, along with a 98.8% f1 score. The system is better at predicting heart disease compared to other cutting-edge methods, as shown by this result.