Abstract
Classifying arrhythmias can be a tough task for a human being and automating this task is highly desirable. Nevertheless fully automatic arrhythmia classification through Electrocardiogram (ECG) signals is a challenging task when the inter-patient paradigm is considered. For the inter-patient paradigm, classifiers are evaluated on signals of unknown subjects, resembling the real world scenario. In this work, we explore a novel ECG representation based on vectorcardiogram (VCG), called temporal vectorcardiogram (TVCG), along with a complex network for feature extraction. We also fine-tune the SVM classifier and perform feature selection with a particle swarm optimization (PSO) algorithm. Results for the inter-patient paradigm show that the proposed method achieves the results comparable to state-of-the-art in MIT-BIH database (53% of Positive predictive (+P) for the Supraventricular ectopic beat (S) class and 87.3% of Sensitivity (Se) for the Ventricular ectopic beat (V) class) that TVCG is a richer representation of the heartbeat and that it could be useful for problems involving the cardiac signal and pattern recognition.
Highlights
A completely automatic system for arrhythmia classification from ECG signals can be divided into four steps: (1) ECG signal preprocessing; (2) heartbeat segmentation; (3) feature extraction; and (4) learning/classification
In the inter-patient paradigm, heartbeats from a set of individuals are reserved exclusively for method evaluation and heartbeats from different individuals are employed during training of the classification models
To report results aligned with real world scenarios, it is recommended to follow the Association for the Advancement of Medical Instrumentation (AAMI) standard[5] and an inter-patient paradigm evaluation protocol such as proposed in ref. 2
Summary
A completely automatic system for arrhythmia classification from ECG signals can be divided into four steps: (1) ECG signal preprocessing; (2) heartbeat segmentation; (3) feature extraction; and (4) learning/classification. Report results only on the intra-patient paradigm is a serious problem found in the literature since the usage of heartbeats from the same patient for both the training and the testing makes the evaluation process biased[2]. This bias happens because models tend to learn the particularities of the individual’s heartbeats during the training, obtaining expressive numbers during evaluation (very close to 100%) as previously discussed[1,2,3,4]. Work Cristov & Bortonal, 200433 Özbay et al, 200634 Bortolan et al, 200735 Ubeyli, 200736 Yu & Chen, 200712 Yu & Chen, 200712 Minhas & Arif, 200837 Asl et al, 200838 Chen et al, 20146 Mert et al, 201439
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
