Effective Heart Disease Prediction and Classification using RNN With Genetic Approach

Diagnosing heart disease is viewed as a difficult problem mostly it can offer a mechanized gauge can as be strengthening activity easily made. This research presents classifiers utilizing the proposed pre-processing method Enhanced Decision Support System (EDSS) with a larger part casting a ballot strategy to further develop prediction accuracy. A generally utilized benchmark dataset is utilized in this exploration. This task becomes more challenging when the dataset includes missing values across different features. The second phase involves Principal Component Analysis (PCA), which is known for addressing the issue of missing attribute values. The proposed methodology extracts high-impact features through Feature Extraction using Principal Component Analysis (FE-MCA). The main objective of this research is to present an optimization function using Support Vector Machines (SVM). This function is integrated into a Genetic Algorithm (GA) to identify the most relevant features for Heart Disease Detection. The results of the GA-SVM method are compared with those of several other feature selection approaches.