Efficient heart disease prediction-based on optimal feature selection using DFCSS and classification by improved Elman-SFO

• Published in: IET systems biology Vol. 14; no. 6; pp. 380 - 390
• Main Authors: Wankhede, Jaishri, Kumar, Magesh, Sambandam, Palaniappan
• Format: Journal Article
• Language: English
• Published: England The Institution of Engineering and Technology 01.12.2020
• Subjects: Algorithms; Bayes methods; California Irvine Cleveland heart disease dataset; cardiology; cardiovascular disease; cardiovascular system; clinical data analysis; Computer Simulation; CVD dataset; data analysis; data classification; data cleaning; data handling; data mining; data normalisation; data pre‐processing process; data transformation; decision function‐based chaotic salp swarm algorithm; decision trees; DFCSS–IENN‐based SFO algorithm; DFCSS–IESFO; diseases; efficient heart disease prediction‐based; feature extraction; feature selection; feature selection process; Heart Diseases - classification; high‐classification accuracy; Humans; improved Elman neural network; improved Elman‐SFO; learning (artificial intelligence); medical diagnostic computing; neural nets; Neural Networks, Computer; optimal feature selection; optimal features; optimal weight value; pattern classification; regression analysis; Research Article; sailfish optimisation algorithm; support vector machines; values imputation; data mining; regression analysis; California Irvine Cleveland heart disease dataset; feature extraction; efficient heart disease prediction-based; data classification; CVD dataset; clinical data analysis; DFCSS–IENN-based SFO algorithm; data transformation; learning (artificial intelligence); feature selection; optimal weight value; medical diagnostic computing; improved Elman neural network; pattern classification; cardiovascular disease; cardiovascular system; support vector machines; data analysis; optimal features; DFCSS–IESFO; diseases; data normalisation; data pre-processing process; cardiology; high-classification accuracy; feature selection process; improved Elman-SFO; data cleaning; decision trees; sailfish optimisation algorithm; decision function-based chaotic salp swarm algorithm; Bayes methods; data handling; optimal feature selection; values imputation; neural nets
• ISSN: 1751-8849; 1751-8857; 1751-8857
• DOI: 10.1049/iet-syb.2020.0041

Prediction of cardiovascular disease (CVD) is a critical challenge in the area of clinical data analysis. In this study, an efficient heart disease prediction is developed based on optimal feature selection. Initially, the data pre-processing process is performed using data cleaning, data transformation, missing values imputation, and data normalisation. Then the decision function-based chaotic salp swarm (DFCSS) algorithm is used to select the optimal features in the feature selection process. Then the chosen attributes are given to the improved Elman neural network (IENN) for data classification. Here, the sailfish optimisation (SFO) algorithm is used to compute the optimal weight value of IENN. The combination of DFCSS–IENN-based SFO (IESFO) algorithm effectively predicts heart disease. The proposed (DFCSS–IESFO) approach is implemented in the Python environment using two different datasets such as the University of California Irvine (UCI) Cleveland heart disease dataset and CVD dataset. The simulation results proved that the proposed scheme achieved a high-classification accuracy of 98.7% for the CVD dataset and 98% for the UCI dataset compared to other classifiers, such as support vector machine, K-nearest neighbour, Elman neural network, Gaussian Naive Bayes, logistic regression, random forest, and decision tree.