ECG Language Processing (ELP): A New Technique to Analyze ECG Signals

Overview

Journal Comput Methods Programs Biomed

Specialty Medical Informatics

Date 2021 Feb 19

PMID 33607552

Citations 6

Authors

Sajad Mousavi

Fatemeh Afghah

Fatemeh Khadem

U Rajendra Acharya

Affiliations

Soon will be listed here.

Abstract

Background: A language is constructed of a finite/infinite set of sentences composing of words. Similar to natural languages, the Electrocardiogram (ECG) signal, the most common noninvasive tool to study the functionality of the heart and diagnose several abnormal arrhythmias, is made up of sequences of three or four distinct waves, including the P-wave, QRS complex, T-wave, and U-wave. An ECG signal may contain several different varieties of each wave (e.g., the QRS complex can have various appearances). For this reason, the ECG signal is a sequence of heartbeats similar to sentences in natural languages) and each heartbeat is composed of a set of waves (similar to words in a sentence) of different morphologies.

Methods: Analogous to natural language processing (NLP), which is used to help computers understand and interpret the human's natural language, it is possible to develop methods inspired by NLP to aid computers to gain a deeper understanding of Electrocardiogram signals. In this work, our goal is to propose a novel ECG analysis technique, ECG language processing (ELP), focusing on empowering computers to understand ECG signals in a way physicians do.

Results: We evaluated the proposed approach on two tasks, including the classification of heartbeats and the detection of atrial fibrillation in the ECG signals. Overall, our technique resulted in better performance or comparable performance with smaller neural networks compared to other deep neural networks and existing algorithms.

Conclusion: Experimental results on three databases (i.e., PhysioNet's MIT-BIH, MIT-BIH AFIB, and PhysioNet Challenge 2017 AFIB Dataset databases) reveal that the proposed approach as a general idea can be applied to a variety of biomedical applications and can achieve remarkable performance.

Citing Articles

Ensemble classifier fostered detection of arrhythmia using ECG data.

Ramkumar M, Alagarsamy M, Balakumar A, Pradeep S Med Biol Eng Comput. 2023; 61(9):2453-2466.

PMID: 37145258 DOI: 10.1007/s11517-023-02839-6.

Single-arm diagnostic electrocardiography with printed graphene on wearable textiles.

Ozturk O, Golparvar A, Acar G, Guler S, Yapici M Sens Actuators A Phys. 2022; 349:114058.

PMID: 36447633 PMC: 9686048. DOI: 10.1016/j.sna.2022.114058.

State-of-the-Art Deep Learning Methods on Electrocardiogram Data: Systematic Review.

Petmezas G, Stefanopoulos L, Kilintzis V, Tzavelis A, Rogers J, Katsaggelos A JMIR Med Inform. 2022; 10(8):e38454.

PMID: 35969441 PMC: 9425174. DOI: 10.2196/38454.

Golden Standard or Obsolete Method? Review of ECG Applications in Clinical and Experimental Context.

Stracina T, Ronzhina M, Redina R, Novakova M Front Physiol. 2022; 13:867033.

PMID: 35547589 PMC: 9082936. DOI: 10.3389/fphys.2022.867033.

Nurse Staffing Practices and Postoperative Atrial Fibrillation Among Cardiac Surgery Patients: A Multisite Cohort Study.

Rochefort C, Bourgon Labelle J, Farand P CJC Open. 2022; 4(1):37-46.

PMID: 35072026 PMC: 8767127. DOI: 10.1016/j.cjco.2021.08.013.

References

Jiang K, Huang C, Ye S, Chen H . High accuracy in automatic detection of atrial fibrillation for Holter monitoring. J Zhejiang Univ Sci B. 2012; 13(9):751-6. PMC: 3437373. DOI: 10.1631/jzus.B1200107. View

Murat F, Yildirim O, Talo M, Baloglu U, Demir Y, Rajendra Acharya U . Application of deep learning techniques for heartbeats detection using ECG signals-analysis and review. Comput Biol Med. 2020; 120:103726. DOI: 10.1016/j.compbiomed.2020.103726. View

Mousavi S, Afghah F, Rajendra Acharya U . SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach. PLoS One. 2019; 14(5):e0216456. PMC: 6504038. DOI: 10.1371/journal.pone.0216456. View

Mousavi S, Afghah F, Rajendra Acharya U . HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks. Comput Biol Med. 2020; 127:104057. PMC: 7875017. DOI: 10.1016/j.compbiomed.2020.104057. View

Asgari S, Mehrnia A, Moussavi M . Automatic detection of atrial fibrillation using stationary wavelet transform and support vector machine. Comput Biol Med. 2015; 60:132-42. DOI: 10.1016/j.compbiomed.2015.03.005. View

Yildirim O, Plawiak P, Tan R, Rajendra Acharya U . Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput Biol Med. 2018; 102:411-420. DOI: 10.1016/j.compbiomed.2018.09.009. View

Martis R, Rajendra Acharya U, Lim C, Mandana K, Ray A, Chakraborty C . Application of higher order cumulant features for cardiac health diagnosis using ECG signals. Int J Neural Syst. 2013; 23(4):1350014. DOI: 10.1142/S0129065713500147. View

. Understanding the ECG: reading the waves. Harv Health Lett. 2016; 36(4):5. View

Mousavi S, Afghah F, Razi A, Rajendra Acharya U . ECGNET: Learning where to attend for detection of atrial fibrillation with deep visual attention. IEEE EMBS Int Conf Biomed Health Inform. 2020; 2019. PMC: 7570949. DOI: 10.1109/BHI.2019.8834637. View

10.

Xia Y, Wulan N, Wang K, Zhang H . Detecting atrial fibrillation by deep convolutional neural networks. Comput Biol Med. 2018; 93:84-92. DOI: 10.1016/j.compbiomed.2017.12.007. View

11.

Zaeri-Amirani M, Afghah F, Mousavi S . A Feature Selection Method Based on Shapley Value to False Alarm Reduction in ICUs A Genetic-Algorithm Approach. Annu Int Conf IEEE Eng Med Biol Soc. 2018; 2018:319-323. DOI: 10.1109/EMBC.2018.8512266. View

12.

Clifford G, Liu C, Moody B, Lehman L, Silva I, Li Q . AF Classification from a Short Single Lead ECG Recording: the PhysioNet/Computing in Cardiology Challenge 2017. Comput Cardiol (2010). 2018; 44. PMC: 5978770. DOI: 10.22489/CinC.2017.065-469. View

13.

Mousavi S, Afghah F . Inter- and intra-patient ECG heartbeat classification for arrhythmia detection: A sequence to sequence deep learning approach. Proc IEEE Int Conf Acoust Speech Signal Process. 2020; 2019:1308-1312. PMC: 7570975. DOI: 10.1109/icassp.2019.8683140. View

14.

Rajendra Acharya U, Oh S, Hagiwara Y, Tan J, Adam M, Gertych A . A deep convolutional neural network model to classify heartbeats. Comput Biol Med. 2017; 89:389-396. DOI: 10.1016/j.compbiomed.2017.08.022. View

15.

Mousavi S, Fotoohinasab A, Afghah F . Single-modal and multi-modal false arrhythmia alarm reduction using attention-based convolutional and recurrent neural networks. PLoS One. 2020; 15(1):e0226990. PMC: 6953791. DOI: 10.1371/journal.pone.0226990. View

16.

Xu R, Wunsch 2nd D . Survey of clustering algorithms. IEEE Trans Neural Netw. 2005; 16(3):645-78. DOI: 10.1109/TNN.2005.845141. View

17.

HURST J . Naming of the waves in the ECG, with a brief account of their genesis. Circulation. 1998; 98(18):1937-42. DOI: 10.1161/01.cir.98.18.1937. View

18.

Pan J, Tompkins W . A real-time QRS detection algorithm. IEEE Trans Biomed Eng. 1985; 32(3):230-6. DOI: 10.1109/TBME.1985.325532. View