Improved delineation model of a standard 12-lead electrocardiogram based on a deep learning algorithm

• Published in: BMC medical informatics and decision making 2023-07, Vol.23 (1), p.139-15, Article 139
• Main Authors: Darmawahyuni, Annisa, Nurmaini, Siti, Rachmatullah, Muhammad Naufal, Avi, Prazna Paramitha, Teguh, Samuel Benedict Putra, Sapitri, Ade Iriani, Tutuko, Bambang, Firdaus, Firdaus
• Format: Article
• Language: English
• Subjects: 12-lead electrocardiogram; Algorithms; Analysis; Artificial neural networks; Automation; Bidirectional long short-term memory; CAI; Cardiology; Clinical medicine; Computer assisted instruction; Convolutional neural network; Deep Learning; Delineation; Delineation model; ECG waveform; EKG; Electrocardiogram; Electrocardiography; Electrocardiography - methods; Feature extraction; Health aspects; Heart; Heart Rate; Humans; Information retrieval; Isoelectric line; Long short-term memory; Machine learning; Methods; Morphology; Neural networks; Neural Networks, Computer; Noise; P waves; Performance measurement; Segmentation; Signal processing; Signal Processing, Computer-Assisted; Technology application; Waveforms; Wavelet transforms
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-023-02233-0

Signal delineation of a standard 12-lead electrocardiogram (ECG) is a decisive step for retrieving complete information and extracting signal characteristics for each lead in cardiology clinical practice. However, it is arduous to manually assess the leads, as a variety of signal morphological variations in each lead have potential defects in recording, noise, or irregular heart rhythm/beat. A computer-aided deep-learning algorithm is considered a state-of-the-art delineation model to classify ECG waveform and boundary in terms of the P-wave, QRS-complex, and T-wave and indicated the satisfactory result. This study implemented convolution layers as a part of convolutional neural networks for automated feature extraction and bidirectional long short-term memory as a classifier. For beat segmentation, we have experimented beat-based and patient-based approach. The empirical results using both beat segmentation approaches, with a total of 14,588 beats were showed that our proposed model performed excellently well. All performance metrics above 95% and 93%, for beat-based and patient-based segmentation, respectively. This is a significant step towards the clinical pertinency of automated 12-lead ECG delineation using deep learning.