An improved hybrid AI model for prediction of arrhythmia using ECG signals. (February 2023)

• Record Type: Journal Article
• Authors: Varalakshmi, P.; Sankaran, Atshaya P.
• Is Part Of: Biomedical signal processing and control. Volume 80(2023)Part 1
• Publication Date: 2023-02
• Subjects: Arrhythmia -- Electrocardiogram (ECG) signals -- Deep learning -- Feature reduction; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104248
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: An arrhythmia is a disorder where the heart beats out of its usual rhythm. It means the heart beats irregularly. The rate of a person's heartbeat is determined by electrical signals flowing through the heart. These signals are produced by the Sino Atrial (SA) node in the heart which acts as a natural pacemaker. If these electrical signals are irregular, it leads to heart problem. In recent years, the individuals who are diagnosed with this condition has increased. In this paper we suggested a hybrid model for feature extraction and classification. Many deep learning algorithms and machine learning algorithms are used, from that two layered BiLSTM gives the best accuracy for feature extraction. Random forest gives the best accuracy for classification. Also feature reduction technique is used to minimize the training and testing time. The proposed hybrid model which comprised of BiLSTM and Random forest gives the best accuracy of 98.84% and shows the sensitivity and specificity of above 98% for all the classes. The proposed hybrid model with feature reduction technique produces an accuracy of 98.46% with lesser prediction time of 0.089 s. The hybrid BiLSTM + Random Forest + PCA model generates a higher average accuracy of 98.30% compared to LSTM + Random Forest + PCA hybrid model with 10-fold cross validation, which again ensures the consistency of the proposed models. Highlights: Hybrid model for feature extraction & classification of arrhythmia using ECG signals. ECG is denoised using DWT & segmented, given as input to DL for feature extraction. These features are reduced using PCA and LDA and passed to ML for classification. BiLSTM + PCA + Random Forest gives better performance.