Prediction of Cardiovascular Disease Risk in the General Population: A GSA-ELM Approach

Medical treatment is a need since it ensures our continued existence as a species. Conditions affecting the heart and blood arteries are collectively known as cardiovascular disease. Decisions regarding the appropriate medicines for people at high risk for cardiovascular disease were informed by early methods of illness prediction. Machine learning algorithms are crucial for creating reliable forecasts of cardiac problems because of the abundance of available health care data. The proposed method is based on three primary phases: preprocessing, feature extraction, and model training. To lessen the impact of distracting noise, HD statistics use filtering and de-noising during the preprocessing phase. In order to extract features, the gray-level Co-Occurrence Matrix is employed. Next, GSA-ELM models are trained based on the retrieved characteristics. Compared to GSA and ELM, the two most popular alternatives, the suggested technique is better. They were able to reach a maximum accuracy of 95.74% by implementing the suggested technique.