Abstract
Electrocardiogram (ECG) is a method used by physicians to detect cardiac disease. Requirements for batch processing and accurate recognition of clinical data have led to the applications of deep-learning methods for feature extraction, classification, and denoising of ECGs; however, deep learning requires large amounts of data and multi-feature integration of datasets, with most available methods used for ECGs incapable of extracting global features or resulting in unstable, low quality training. To address these deficiencies, we proposed a novel generative adversarial architecture called RPSeqGAN using a training process reliant upon a sequence generative adversarial network (SeqGAN) algorithm that adopts the policy gradient (PG) in reinforcement learning. Based on clinical records collected from the MIT-BIH arrhythmia database, we compared our proposed model with three deep generative models to evaluate its stability by observing the variance of their loss curves. Additionally, we generated ECGs with five periods and evaluated them according to six metrics suitable for time series. The results indicate that the proposed model showed the highest stability and data quality.
Highlights
Increases in the annual incidence of cardiovascular disease have resulted in the use of electrocardiograms (ECGs) as a critical research target in precision medicine, especially for disease classification [1]–[3], morbidity prediction [4], and signal enhancement [5]
We addressed the instability during training and low quality of our model by implementing policy gradient (PG) [14] and Monte Carlo (MC) [15] search through the sequence generative adversarial network (SeqGAN) algorithm, followed by generation of different segments of ECGs with high simulation accuracy and different periods
DATASET AND PLATFORM The dataset was downloaded from the official website of the MIT-BIH Arrhythmia Database and it includes 48 30-min excerpts of two-channels ambulatory ECG records sampled at a rate of 360 Hz
Summary
Increases in the annual incidence of cardiovascular disease have resulted in the use of electrocardiograms (ECGs) as a critical research target in precision medicine, especially for disease classification [1]–[3], morbidity prediction [4], and signal enhancement [5]. Current analytical methods require an enormous quantity of clinical data with particular labels, there exists the problem that ECG signals are unable to support research requirements. Due to the sensitivity of clinical data represented by ECGs, researchers cannot access relevant data directly without encryption or composition. It is imperative to develop a generative method to efficiently and securely synthesize ECG data. As an initial simulation generation method, McSharry et al [6] presented a dynamic model based on.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
