Detection of premature ventricular contraction (PVC) using linear and nonlinear techniques: an experimental study
Cardiovascular diseases are identified as one of the most dangerous diseases and the major causes of the death around the world. One of the most common cardiac arrhythmias that have always been a concern for cardiologists is premature ventricular contractions. Regarding its abundance among all ages, prediction and diagnosis of this type of arrhythmia has particular importance. One of the most common, most non-invasive; and the least costly method for investigation of heart diseases is to record and analyze the electrocardiogram (ECG) signals. The purpose of this study is to analyze the ECG in order to classify premature ventricular contraction heartbeats. Having proposed a new technique based on evolutionary optimization for R peak detection, several methodologies, such as morphological assessment, polynomial curve fitting, discrete wavelet transform, and nonlinear analysis, are employed to extract features from ECG signal. Support vector machine (SVM) classifier with a linear kernel is used to detect the normal and PVC heart rates. In order to evaluate the proposed method, in addition to the MIT-BIH database, the experimental data is used and the methodology performance is proved for both databases. Finally, using different feature selection criteria such as fisher distinction, minimal-redundancy maximum-relevance, and SVM-based recursive feature elimination with correlation bias reduction, six features are introduced as best ones. The proposed PVC detection algorithm acquires the overall detection accuracy of 99.78%, with the sensitivity of 99.91% and specificity of 99.37%, for MIT-BIH dataset.
KeywordsPremature ventricular contraction (PVC) Electrocardiogram (ECG) Discrete wavelet transform (DWT) Nonlinear analysis Support vector machine (SVM)
Authors are grateful to Dr. Ahmad Masoudi, Head of the Cardiac Intensive Care Unit, Qeshm Hospital, Qeshm Island, Iran, for his clinical help and outstanding suggestions to improve the quality of this manuscript.
- 6.Ghorbanian, P., Ghaffari, A., Jalali, A., Nataraj, C.: Heart arrhythmia detection using continuous wavelet transform and principal component analysis with neural network classifier. In: In Computing in Cardiology, pp. 669–672. IEEE (2010)Google Scholar
- 7.Melgani, F., Bazi, Y.: Detecting premature ventricular contractions in ECG signals with Gaussian processes. In: Computers in cardiology, pp. 237–240. IEEE (2008)Google Scholar
- 11.de Chazal, P., Reilly, R.B: Automatic classification of ECG beats using waveform shape and heart beat interval features. In: 2003 IEEE international conference on acoustics, speech, and signal processing. Proceedings. (ICASSP’03), Vol. 2, pp. II–269. IEEE (2003)Google Scholar
- 20.Ince, T., Kiranyaz, S., Gabbouj, M.: Automated patient-specific classification of premature ventricular contractions. In: 30th Annual international conference of the IEEE Engineering in Medicine and Biology Society, pp. 5474–5477. EMBS (2008)Google Scholar
- 22.Sotomi, Y., Iwakura, K., Higuchi, Y., Abe, K., Yoshida, J., Masai, T., Fujii, K.: The impact of systemic vascular resistance on the accuracy of the FloTrac/Vigileo™ system in the perioperative period of cardiac surgery: a prospective observational comparison study. J. Clin. Monit. Comput. 27(6), 639–646 (2013)CrossRefGoogle Scholar
- 26.Mukherjee, A., Ghosh, K.K.: An efficient wavelet analysis for ECG signal processing. In: 2012 International Conference on Informatics, Electronics & Vision (ICIEV), pp. 411–415. IEEE (2012)Google Scholar
- 30.Rebergen, D.J., Nagaraj, S.B., Rosenthal, E.S., Bianchi, M.T., van Putten, M.J., Westover, M.B.: ADARRI: a novel method to detect spurious R-peaks in the electrocardiogram for heart rate variability analysis in the intensive care unit. J. Clin. Monit. Comput. 32(1), 53–61 (2018)CrossRefGoogle Scholar
- 37.Hidalgo-Muñoz, A.R., López, M.M., Santos, I.M., Pereira, A.T., Vázquez-Marrufo, M., Galvao-Carmona, A., Tomé, A.M.: Application of SVM-RFE on EEG signals for detecting the most relevant scalp regions linked to affective valence processing. Expert Syst. Appl. 40(6), 2102–2108 (2013)CrossRefGoogle Scholar
- 39.Kim, E.Y., Lee, M.Y., Kim, S.H., Ha, K., Kim, K.P., Ahn, Y.M.: Diagnosis of major depressive disorder by combining multimodal information from heart rate dynamics and serum proteomics using machine-learning algorithm. Prog. Neuropsychopharmacol. Biol. Psychiatry 76, 65–71 (2017)CrossRefGoogle Scholar