Prediction Accuracy Model Aiming to Improve Prediction Accuracy in Congenital Heart Anomaly Detection using Hybrid Feature Selection with Modified Particle Swarm Optimization Approach

Abstract

Heart Disease is one of the primary causes of mortality and morbidity in the Globe since the 19th Century. Most of the Globalized Multi-Specialty Hospitals are not able to control and governed by emerging technologies, at the same time, the death rate escalates day by day in addition to Covid-19 is a multifaceted state. Heart disease classification involves identifying numerous health problems and sickness symptoms of ones' individual with significant feature selection, there is misclassification probability that could be very high and priceless. There are many diverse methods were designing for heart disease prediction systems in earlier days, even though it is unsolved and rising the death rate. As observed by many research groups, PSO is an intensive computational and inspired biologically inspired algorithms like Genetic Algorithms (GA) has a proven track record to handle computationally complex problems with competence for predicting heart diseases. This research contribution through the proposed model downs the computation time and increases the accuracy. The high-level comprehensibility, predictive accuracy are good and desired through this Intelligence Hybrid Approach (IHP) to reduce Heart attacks and control the death rate.