Arrhythmia classification from single-lead ECG signals using the inter-patient paradigm. (April 2021)

• Record Type: Journal Article
• Authors: Dias, Felipe Meneguitti; Monteiro, Henrique L.M.; Cabral, Thales Wulfert; Naji, Rayen; Kuehni, Michael; Luz, Eduardo José da S.
• Is Part Of: Computer methods and programs in biomedicine. Volume 202(2021)
• Publication Date: 2021-04
• Subjects: Electrocardiogram -- ECG classification -- Machine learning -- Inter-patient -- Segmentation error -- Jitter; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.105948
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Addition of artificially generated jitter to the R-wave position to test the robustness of the classification system against segmentation errors. Individual performance analysis of each group of features against segmentation errors. Competitive results in comparison with other state-of-the-art methods for ECG classification. Abstract: Background and objectives: Arrhythmia is a heart disease characterized by the change in the regularity of the heartbeat. Since this disorder can occur sporadically, Holter devices are used for continuous long-term monitoring of the subject's electrocardiogram (ECG). In this process, a large volume of data is generated. Consequently, the use of an automated system for detecting arrhythmias is highly desirable. In this work, an automated system for classifying arrhythmias using single-lead ECG signals is proposed. Methods: The proposed system uses a combination of three groups of features: RR intervals, signal morphology, and higher-order statistics. To validate the method, the MIT-BIH database was employed using the inter-patient paradigm. Besides, the robustness of the system against segmentation errors was tested by adding jitter to the R-wave positions given by the MIT-BIH database. Additionally, each group of features had its robustness against segmentation error tested as well. Results: The experimental results of the proposed classification system with jitter show that the sensitivities for the classes N, S, and V are 93.7, 89.7, and 87.9, respectively. Also, the corresponding positive predictive values are 99.2, 36.8, and 93.9, respectively. Conclusions: The proposed method was able to outperform several state-of-the-art methods, even though the R-wave position was synthetically corrupted by added jitter. The obtained results show that our approach can be employed in real scenarios where segmentation errors and the inter-patient paradigm are present.