J Korean Med Sci.  2024 Feb;39(5):e56. 10.3346/jkms.2024.39.e56.

Identification of Atrial Fibrillation With Single-Lead Mobile ECG During Normal Sinus Rhythm Using Deep Learning

• Kim J
• Lee SJ
• Ko B
• Lee M
• Lee YS
• Lee KH

• KMID: 2551982
• DOI: http://doi.org/10.3346/jkms.2024.39.e56

Abstract

Background
The acquisition of single-lead electrocardiogram (ECG) from mobile devices offers a more practical approach to arrhythmia detection. Using artificial intelligence for atrial fibrillation (AF) identification enhances screening efficiency. However, the potential of singlelead ECG for AF identification during normal sinus rhythm (NSR) remains under-explored. This study introduces a method to identify AF using single-lead mobile ECG during NSR.
Methods
We employed three deep learning models: recurrent neural network (RNN), long short-term memory (LSTM), and residual neural networks (ResNet50). From a dataset comprising 13,509 ECGs from 6,719 patients, 10,287 NSR ECGs from 5,170 patients were selected. Single-lead mobile ECGs underwent noise filtering and segmentation into 10-second intervals. A random under-sampling was applied to reduce bias from data imbalance. The final analysis involved 31,767 ECG segments, including 15,157 labeled as masked AF and 16,610 as Healthy.
Results
ResNet50 outperformed the other models, achieving a recall of 79.3%, precision of 65.8%, F1-score of 71.9%, accuracy of 70.5%, and an area under the receiver operating characteristic curve (AUC) of 0.79 in identifying AF from NSR ECGs. Comparative performance scores for RNN and LSTM were 0.75 and 0.74, respectively. In an external validation set, ResNet50 attained an F1-score of 64.1%, recall of 68.9%, precision of 60.0%, accuracy of 63.4%, and AUC of 0.68.
Conclusion
The deep learning model using single-lead mobile ECG during NSR effectively identified AF at risk in future. However, further research is needed to enhance the performance of deep learning models for clinical application.

Keyword

Artificial Intelligence; Atrial Fibrillation; Electrocardiography; Mobile Applications; Probability Learning

Figure

• 

  Fig. 1 Proposed method for AF prediction using single-lead mobile ECG in normal sinus rhythm.(A) Input stage with raw ECG signal. (B) Stage of data processing. (C) Segments of filtered ECG. (D) Application of ResNet50. (E) Final output stage.ECG = electrocardiogram, AF = atrial fibrillation, ResNet = residual neural network, Conv = convolutional layer, ReLU = rectified linear unit.

• 

  Fig. 2 Flow diagram of patient data.PID = patient identification number, AF = atrial fibrillation, ECG = electrocardiogram, NSR = normal sinus rhythm.

• 

  Fig. 3 Process of data preprocessing for atrial fibrillation detection in mobile ECG under normal sinus rhythm.(A) Raw ECG signal. (B) Filtered ECG signal. (C) Filtered ECG segments.ECG = electrocardiogram.

• 

  Fig. 4 Performance evaluation of proposed models using confusion matrices on the test set.(A) Confusion matrix of ResNet50, (B) Confusion matrix of RNN, (C) Confusion matrix of LSTM.ResNet = residual neural network, RNN = recurrent neural network, LSTM = long short-term memory.

• 

  Fig. 5 ROC curves demonstrating the performance of proposed models for atrial fibrillation prediction in mobile electrocardiogram during normal sinus rhythm.(A) ROC curve for the training set. (B) ROC curve for the internal validation set. (C) ROC curve for the test set.ROC = receiver operating characteristic, AUC = area under the receiver operating characteristic curve, ResNet = residual neural network, LSTM = long short-term memory, RNN = recurrent neural network.

Reference

1. Sanna T, Diener HC, Passman RS, Di Lazzaro V, Bernstein RA, Morillo CA, et al. Cryptogenic stroke and underlying atrial fibrillation. N Engl J Med. 2014; 370(26):2478–2486. PMID: 24963567.

2. Gladstone DJ, Spring M, Dorian P, Panzov V, Thorpe KE, Hall J, et al. Atrial fibrillation in patients with cryptogenic stroke. N Engl J Med. 2014; 370(26):2467–2477. PMID: 24963566.

3. Freedman B, Potpara TS, Lip GY. Stroke prevention in atrial fibrillation. Lancet. 2016; 388(10046):806–817. PMID: 27560276.

4. Barbarossa A, Guerra F, Capucci A. Silent atrial fibrillation: a critical review. J Atr Fibrillation. 2014; 7(3):1138. PMID: 27957123.

5. Seet RC, Friedman PA, Rabinstein AA. Prolonged rhythm monitoring for the detection of occult paroxysmal atrial fibrillation in ischemic stroke of unknown cause. Circulation. 2011; 124(4):477–486. PMID: 21788600.

6. Ziegler PD, Glotzer TV, Daoud EG, Singer DE, Ezekowitz MD, Hoyt RH, et al. Detection of previously undiagnosed atrial fibrillation in patients with stroke risk factors and usefulness of continuous monitoring in primary stroke prevention. Am J Cardiol. 2012; 110(9):1309–1314. PMID: 22819433.

7. Somani S, Russak AJ, Richter F, Zhao S, Vaid A, Chaudhry F, et al. Deep learning and the electrocardiogram: review of the current state-of-the-art. Europace. 2021; 23(8):1179–1191. PMID: 33564873.

8. Ribeiro AH, Ribeiro MH, Paixão GM, Oliveira DM, Gomes PR, Canazart JA, et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun. 2020; 11(1):1760. PMID: 32273514.

9. Baek YS, Lee SC, Choi W, Kim DH. A new deep learning algorithm of 12-lead electrocardiogram for identifying atrial fibrillation during sinus rhythm. Sci Rep. 2021; 11(1):12818. PMID: 34140578.

10. Attia ZI, Noseworthy PA, Lopez-Jimenez F, Asirvatham SJ, Deshmukh AJ, Gersh BJ, et al. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. Lancet. 2019; 394(10201):861–867. PMID: 31378392.

11. Sana F, Isselbacher EM, Singh JP, Heist EK, Pathik B, Armoundas AA. Wearable devices for ambulatory cardiac monitoring: JACC state-of-the-art review. J Am Coll Cardiol. 2020; 75(13):1582–1592. PMID: 32241375.

12. Perez MV, Mahaffey KW, Hedlin H, Rumsfeld JS, Garcia A, Ferris T, et al. Large-scale assessment of a smartwatch to identify atrial fibrillation. N Engl J Med. 2019; 381(20):1909–1917. PMID: 31722151.

13. Hwang J, Kim J, Choi KJ, Cho MS, Nam GB, Kim YH. Assessing accuracy of wrist-worn wearable devices in measurement of paroxysmal supraventricular tachycardia heart rate. Korean Circ J. 2019; 49(5):437–445. PMID: 30808083.

14. Ramkumar S, Nerlekar N, D’Souza D, Pol DJ, Kalman JM, Marwick TH. Atrial fibrillation detection using single lead portable electrocardiographic monitoring: a systematic review and meta-analysis. BMJ Open. 2018; 8(9):e024178.

15. Giebel GD, Gissel C. Accuracy of mHealth devices for atrial fibrillation screening: systematic review. JMIR Mhealth Uhealth. 2019; 7(6):e13641. PMID: 31199337.

16. Kwon S, Lee SR, Choi EK, Ahn HJ, Song HS, Lee YS, et al. Validation of adhesive single-lead ECG device compared with holter monitoring among non-atrial fibrillation patients. Sensors (Basel). 2021; 21(9):3122. PMID: 33946269.

17. Nault I, André P, Plourde B, Leclerc F, Sarrazin JF, Philippon F, et al. Validation of a novel single lead ambulatory ECG monitor - Cardiostat™ - Compared to a standard ECG Holter monitoring. J Electrocardiol. 2019; 53:57–63. PMID: 30641305.

18. Karaoğuz MR, Yurtseven E, Aslan G, Deliormanlı BG, Adıgüzel Ö, Gönen M, et al. The quality of ECG data acquisition, and diagnostic performance of a novel adhesive patch for ambulatory cardiac rhythm monitoring in arrhythmia detection. J Electrocardiol. 2019; 54:28–35. PMID: 30851474.

19. Cheung CC, Kerr CR, Krahn AD. Comparing 14-day adhesive patch with 24-h Holter monitoring. Future Cardiol. 2014; 10(3):319–322. PMID: 24976467.

20. Ramesh J, Solatidehkordi Z, Aburukba R, Sagahyroon A. Atrial fibrillation classification with smart wearables using short-term heart rate variability and deep convolutional neural networks. Sensors (Basel). 2021; 21(21):7233. PMID: 34770543.

21. Tutuko B, Rachmatullah MN, Darmawahyuni A, Nurmaini S, Tondas AE, Passarella R, et al. Short single-lead ECG signal delineation-based deep learning: implementation in automatic atrial fibrillation identification. Sensors (Basel). 2022; 22(6):2329. PMID: 35336500.

22. Khairuddin A, Azir KF, Kan PE. Limitations and future of electrocardiography devices: a review and the perspective from the Internet of Things. In : Proceedings of 2017 International Conference on Research and Innovation in Information Systems (ICRIIS); 2017 July 16–17; Langkawi, Malaysia. New York, NY, USA: IEEE;2017. p. 1–7.

23. Maan A, Mansour M, Ruskin JN, Heist EK. Impact of catheter ablation on P-wave parameters on 12-lead electrocardiogram in patients with atrial fibrillation. J Electrocardiol. 2014; 47(5):725–733. PMID: 24850319.

24. Hu X, Jiang J, Ma Y, Tang A. Novel P wave indices to predict atrial fibrillation recurrence after radiofrequency ablation for paroxysmal atrial fibrillation. Med Sci Monit. 2016; 22:2616–2623. PMID: 27450644.

25. Miao Y, Xu M, Yang L, Zhang C, Liu H, Shao X. Investigating the association between P wave duration and atrial fibrillation recurrence after radiofrequency ablation in early persistent atrial fibrillation patients. Int J Cardiol. 2022; 351:48–54. PMID: 34954277.

26. Letsas KP, Pappas LK, Gavrielatos G, Efremidis M, Sideris A, Kardaras F. ST-segment elevation induced during the transseptal procedure for radiofrequency catheter ablation of atrial fibrillation. Int J Cardiol. 2007; 114(1):e12–e14. PMID: 17049645.

27. Lee W, Seo K. Downsampling for binary classification with a highly imbalanced dataset using active learning. Big Data Research. 2022; 28:100314.

28. Qazi N, Raza K. Effect of feature selection, SMOTE and under sampling on class imbalance classification. In : Proceedings of 2012 UKSim 14th International Conference on Computer Modelling and Simulation; 2012 March 28–30; Cambridge, UK. New York, NY, USA: IEEE;2012. p. 145–150.

29. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In : Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2016 June 27–30; Las Vegas, NV, USA. New York, NY, USA: IEEE;2016. p. 770–778.

30. He F, Liu T, Tao D. Why ResNet works? Residuals generalize. IEEE Trans Neural Netw Learn Syst. 2020; 31(12):5349–5362. PMID: 32031953.

31. Hüsken M, Stagge P. Recurrent neural networks for time series classification. Neurocomputing. 2003; 50:223–235.

32. Singh S, Pandey SK, Pawar U, Janghel RR. Classification of ECG arrhythmia using recurrent neural networks. Procedia Comput Sci. 2018; 132:1290–1297.

33. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997; 9(8):1735–1780. PMID: 9377276.

34. Yu Y, Si X, Hu C, Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput. 2019; 31(7):1235–1270. PMID: 31113301.

35. Karim F, Majumdar S, Darabi H, Chen S. LSTM fully convolutional networks for time series classification. IEEE Access. 2018; 6:1662–1669.

36. Reyad M, Sarhan AM, Arafa M. A modified Adam algorithm for deep neural network optimization. Neural Comput Appl. 2023; 35(23):17095–17112.

37. Jia X, Feng X, Yong H, Meng D. Weight decay with tailored Adam on scale-invariant weights for better generalization. IEEE Trans Neural Netw Learn Syst. Forthcoming. 2022; DOI: 10.1109/TNNLS.2022.3213536.

38. Simundic AM. Diagnostic accuracy—part 1: basic concepts: sensitivity and specificity, ROC analysis, STARD Statement. Point Care. 2012; 11(1):6–8.

39. Nigusse AB, Mengistie DA, Malengier B, Tseghai GB, Langenhove LV. Wearable smart textiles for long-term electrocardiography monitoring—a review. Sensors (Basel). 2021; 21(12):4174. PMID: 34204577.

40. Coppola EE, Gyawali PK, Vanjara N, Giaime D, Wang L. Atrial fibrillation classification from a short single lead ECG recording using hierarchical classifier. In : Proceedings of 2017 Computing in Cardiology (CinC); 2017 September 24–27; Rennes, France. New York, NY, USA: IEEE;2017.

41. Yazdani S, Laub P, Luca A, Vesin JM. Heart rhythm classification using short-term ECG atrial and ventricular activity analysis. In : Proceedings of 2017 Computing in Cardiology (CinC); 2017 September 24–27; Rennes, France. New York, NY, USA: IEEE;2017.

42. Bahit MC, Sacco RL, Easton JD, Meyerhoff J, Cronin L, Kleine E, et al. Predictors of atrial fibrillation development in patients with embolic stroke of undetermined source: an analysis of the RE-SPECT ESUS trial. Circulation. 2021; 144(22):1738–1746. PMID: 34649459.

43. Gladstone DJ, Dorian P, Spring M, Panzov V, Mamdani M, Healey JS, et al. Atrial premature beats predict atrial fibrillation in cryptogenic stroke: results from the EMBRACE trial. Stroke. 2015; 46(4):936–941. PMID: 25700289.