AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

Tutuko B., Nurmaini S., Tondas A.E., Rachmatullah M.N., Darmawahyuni A., Esafri R., Firdaus F., Sapitri A.I.

Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, 30139, Indonesia; Department of Cardiology and Vascular Medicine, Dr. Mohammad Hoesin Hospital, Palembang, Indonesia


Background: Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R–R intervals to determine the heart rate variability (HRV). An accurate HRV is the gold standard for predicting the AF condition; therefore, a current challenge is to determine whether a DL approach can be used to analyze raw ECG data in a broad range of devices. This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8232 records based on three datasets and tested with 3610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity. Result: Meanwhile, when tested using unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity at a sample period of 0.02 seconds using the DL Cloud System. To improve the confidence of the AFibNet model, it also validated with 18 arrhythmias condition defined as Non-AF-class. Thus, the data is increased from 11,842 to 26,349 instances for three-class, i.e., Normal sinus (N), AF and Non-AF. The result found 96.36% accuracy, 93.65% sensitivity, and 96.92% specificity. Conclusion: These findings demonstrate that the proposed approach can use unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment © 2021, The Author(s).

1D-convolutional neural network; Atrial fibrillation; Cloud deep learning


BMC Medical Informatics and Decision Making

Publisher: BioMed Central Ltd

Volume 21, Issue 1, Art No 216, Page – , Page Count

Journal Link:

doi: 10.1186/s12911-021-01571-1

Issn: 14726947

Type: All Open Access, Gold, Green


De Chazal, P., O’Dwyer, M., Reilly, R.B., Automatic classification of heartbeats using ECG morphology and heartbeat interval features (2004) IEEE Trans Biomed Eng., 51 (7), pp. 1196-1206. , PID: 15248536; Mant, J., Fitzmaurice, D.A., Hobbs, F.R., Jowett, S., Murray, E.T., Holder, R., Davies, M., Lip, G.Y., Accuracy of diagnosing atrial fibrillation on electrocardiogram by primary care practitioners and interpretative diagnostic software: analysis of data from screening for atrial fibrillation in the elderly (safe) trial (2007) Bmj., 335 (7616), p. 380. , PID: 17604299; Torres-Soto, J., Ashley, E.A., Multi-task deep learning for cardiac rhythm detection in wearable devices (2020) NPJ Digit Med., 3 (1), pp. 1-8; Faust, O., Kareem, M., Shenfield, A., Ali, A., Acharya, U.R., Validating the robustness of an internet of things based atrial fibrillation detection system (2020) Pattern Recogn Lett., 133, pp. 55-61; Pranata, R., Yonas, E., Chintya, V., Tondas, A.E., Raharjo, S.B., Evidence-based case report: The use of D-dimer assay to exclude left atrial thrombus in patient with atrial fibrillation > 48 hours (2019) J Atr Fibrillation, 11 (6), p. 2149. ,; Pranata, R., Tondas, A.E., Yonas, E., Chintya, V., Yamin, M., Efficacy and safety of catheter ablation for atrial fibrillation in congenital heart disease—a systematic review and meta-analysis (2019) Indian Pacing Electrophysiol J., 19 (6), pp. 216-221. , PID: 31541679; Yuniadi, Y., Hanafy, D.A., Rahardjo, S.B., Tondas, A.E., Maharani, E., Hermanto, D.Y., Munawar, M., indonesian heart association guidelines of management of atrial fibrillation (2014) Indones J Cardiol., 2014, pp. 102-133; Shah, A.P., Rubin, S.A., Errors in the computerized electrocardiogram interpretation of cardiac rhythm (2007) J Electrocardiol., 40 (5), pp. 385-390. , PID: 17531257; Bowry, A.D., Lewey, J., Dugani, S.B., Choudhry, N.K., The burden of cardiovascular disease in low-and middle-income countries: epidemiology and management (2015) Can J Cardiol., 31 (9), pp. 1151-1159. , PID: 26321437; Ribeiro, A.H., Ribeiro, M.H., Paixão, G.M., Oliveira, D.M., Gomes, P.R., Canazart, J.A., Ferreira, M.P., Meira, W., Jr., Automatic diagnosis of the 12-lead ECG using a deep neural network (2020) Nat Commun., 11 (1), pp. 1-9; Nurmaini, S., Umi Partan, R., Caesarendra, W., Dewi, T., Naufal Rahmatullah, M., Darmawahyuni, A., Bhayyu, V., Firdaus, F., An automated ECG beat classification system using deep neural networks with an unsupervised feature extraction technique (2019) Appl Sci., 9 (14), p. 2921; Tison, G.H., Sanchez, J.M., Ballinger, B., Singh, A., Olgin, J.E., Pletcher, M.J., Vittinghoff, E., Gladstone, R.A., Passive detection of atrial fibrillation using a commercially available smartwatch (2018) JAMA Cardiol., 3 (5), pp. 409-416. , PID: 5875390; Nurmaini, S., Tondas, A.E., Darmawahyuni, A., Rachmatullah, M.N., Partan, R.U., Firdaus, F., Tutuko, B., Khoirani, R., Robust detection of atrial fibrillation from short-term electrocardiogram using convolutional neural networks (2020) Future Gener Comput Syst., 113, pp. 304-317; Faust, O., Ciaccio, E.J., Acharya, U.R., A review of atrial fibrillation detection methods as a service (2020) Int J Environ Res Public Health., 17 (9), p. 3093; Ebrahimi, Z., Loni, M., Daneshtalab, M., Gharehbaghi, A., A review on deep learning methods for ECG arrhythmia classification (2020) Expert Syst Appl: X., 7, p. 100033; Andersen, R.S., Peimankar, A., Puthusserypady, S., A deep learning approach for real-time detection of atrial fibrillation (2019) Expert Syst Appl., 115, pp. 465-473; Faust, O., Hagiwara, Y., Hong, T.J., Lih, O.S., Acharya, U.R., Deep learning for healthcare applications based on physiological signals: a review (2018) Comput Methods Progr Biomed., 161, pp. 1-13; Darmawahyuni, A., Nurmaini, S., Yuwandini, M., Rachmatullah, M.N., Firdaus, F., Tutuko, B., Congestive heart failure waveform classification based on short time-step analysis with recurrent network (2020) Inform Med Unlocked., 21, p. 100441; Farhadi, J., Attarodi, G., Dabanloo, N.J., Mohandespoor, M., Eslamizadeh, M., Classification of atrial fibrillation using stacked auto encoders neural networks (2018) 2018 Computing in Cardiology Conference (Cinc), 45, pp. 1-3; Erdenebayar, U., Kim, H., Park, J.-U., Kang, D., Lee, K.-J., Automatic prediction of atrial fibrillation based on convolutional neural network using a short-term normal electrocardiogram signal (2019) J Korean Med Sci., 34 (7); Cai, W., Chen, Y., Guo, J., Han, B., Shi, Y., Ji, L., Wang, J., Luo, J., Accurate detection of atrial fibrillation from 12-lead ECG using deep neural network (2020) Comput Biol Med., 116, p. 103378. , PID: 31778896; Liaqat, S., Dashtipour, K., Zahid, A., Assaleh, K., Arshad, K., Ramzan, N., Detection of atrial fibrillation using a machine learning approach (2020) Information., 11 (12), p. 549; Zhou, X., Zhu, X., Nakamura, K., Noro, M., Atrial fibrillation detection using convolutional neural networks (2018) 9Th International Conference on Awareness Science and Technology (Icast). IEEE, 2018, pp. 84-89; Huang, M.-L., Wu, Y.-S., Classification of atrial fibrillation and normal sinus rhythm based on convolutional neural network (2020) Biomed Eng Lett., 10 (2), pp. 183-193; Al Rahhal, M.M., Bazi, Y., Al Zuair, M., Othman, E., BenJdira, B., Convolutional neural networks for electrocardiogram classification (2018) J Med Biol Eng., 38 (6), pp. 1014-1025; Kiranyaz, S., Ince, T., Gabbouj, M., Real-time patient-specific ECG classification by 1-D convolutional neural networks (2015) IEEE Trans Biomed Eng., 63 (3), pp. 664-675. , PID: 26285054; Acharya, U.R., Oh, S.L., Hagiwara, Y., Tan, J.H., Adam, M., Gertych, A., San, T.R., A deep convolutional neural network model to classify heartbeats (2017) Comput Biol Med., 89, pp. 389-396. , PID: 28869899; Hannun, A.Y., Rajpurkar, P., Haghpanahi, M., Tison, G.H., Bourn, C., Turakhia, M.P., Ng, A.Y., Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network (2019) Nat Med., 25 (1), pp. 65-69. , COI: 1:CAS:528:DC%2BC1MXmvVOgsLs%3D, PID: 30617320; Li, Y., Pang, Y., Wang, J., Li, X., Patient-specific ECG classification by deeper CNN from generic to dedicated (2018) Neurocomputing., 314, pp. 336-346; Oh, S.L., Ng, E.Y., San Tan, R., Acharya, U.R., Automated beat-wise arrhythmia diagnosis using modified u-net on extended electrocardiographic recordings with heterogeneous arrhythmia types (2019) Comput Biol Med., 105, pp. 92-101. , PID: 30599317; Subasi, A., Qaisar, S.M., Heartbeat Classification Using Parametric and time–frequency Methods. In: Modelling and Analysis of Active Biopotential Signals in Healthcare, 2 (2053-563), pp. 11-29. ,, IOP Publishing; Li, F., Wu, J., Jia, M., Chen, Z., Pu, Y., Automated heartbeat classification exploiting convolutional neural network with channel-wise attention (2019) IEEE Access., 7, pp. 122955-122963; Yıldırım, Ö., Pławiak, P., Tan, R.-S., Acharya, U.R., Arrhythmia detection using deep convolutional neural network with long duration ECG signals (2018) Comput Biol Med., 102, pp. 411-420. , PID: 30245122; Shaker, A.M., Tantawi, M., Shedeed, H.A., Tolba, M.F., Generalization of convolutional neural networks for ECG classification using generative adversarial networks (2020) IEEE Access., 8, pp. 35592-35605; Hamon, R., Junklewitz, H., Sanchez, I., (2020) Robustness and Explainability of Artificial Intelligence. Publications Office of the European Union; Jagadeeswari, V., Subramaniyaswamy, V., Logesh, R., Vijayakumar, V., A study on medical internet of things and big data in personalized healthcare system (2018) Health Inf Sci Syst., 6 (1), pp. 1-20; Alkmim, M.B., Figueira, R.M., Marcolino, M.S., Cardoso, C., Mpdcunha, L.R., de Cunha, D.F., Antunes, A.P., Et, A., Improving patient access to specialized health care: The telehealth network of Minas Gerais, Brazil (2012) Bull World Health Organ, 90, pp. 373-378; Draghici, A.E., Taylor, J.A., The physiological basis and measurement of heart rate variability in humans (2016) J Physiol Anthropol., 35 (1), pp. 1-8; Tondas, A.E., Halim, R.A., Guyanto, M., Minimal or no touch electrocardiography recording and remote heart rhythm monitoring during covid-19 pandemic era (2020) Indones J Cardiol., 41 (2), pp. 133-141; Moody, G., A new method for detecting atrial fibrillation using RR intervals (1983) Comput Cardiol, pp. 227-230; Goldberger, A.L., Amaral, L.A., Glass, L., Hausdorff, J.M., Ivanov, P.C., Mark, R.G., Mietus, J.E., Stanley, H.E., Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals (2000) Circulation., 101 (23), pp. 215-220; Liu, F., Liu, C., Zhao, L., Zhang, X., Wu, X., Xu, X., Liu, Y., He, Z., An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection (2018) J Med Imaging Health Inf., 8 (7), pp. 1368-1373; Petrutiu, S., Sahakian, A.V., Swiryn, S., Abrupt changes in fibrillatory wave characteristics at the termination of paroxysmal atrial fibrillation in humans (2007) Europace., 9 (7), pp. 466-470. , PID: 17540663; Moody, G., Spontaneous termination of atrial fibrillation: A challenge from physionet and computers in cardiology 2004 (2004) In: Computers in Cardiology, 2004, pp. 101-104. , IEEE; Iyengar, N., Peng, C., Morin, R., Goldberger, A.L., Lipsitz, L.A., Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics (1996) Am J Physiol-Regul Integr Comp Physiol, 271 (4), pp. 1078-1084; Moody, G.B., Mark, R.G., The impact of the MIT-BIH arrhythmia database (2001) IEEE Eng Med Biol Mag., 20 (3), pp. 45-50. , COI: 1:STN:280:DC%2BD38%2FhvFaitw%3D%3D, PID: 11446209; Zheng, J., Zhang, J., Danioko, S., Yao, H., Guo, H., Rakovski, C., A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients (2020) Sci Data., 7 (1), pp. 1-8; Ahmed, N., Zhu, Y., Early detection of atrial fibrillation based on ECG signals (2020) Bioengineering., 7 (1), p. 16. , COI: 1:CAS:528:DC%2BB3cXhsFGrtL7F; Mahdiani, S., Jeyhani, V., Peltokangas, M., Vehkaoja, A., Is 50 Hz high enough ECG sampling frequency for accurate HRV analysis? (2015) 37Th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2015, pp. 5948-5951; Kwon, O., Jeong, J., Kim, H.B., Kwon, I.H., Park, S.Y., Kim, J.E., Choi, Y., Electrocardiogram sampling frequency range acceptable for heart rate variability analysis (2018) Healthcare Inf Res., 24 (3), p. 198; Lim, K., Ranganathan, P., Chang, J., Patel, C., Mudge, T., Reinhardt, S., Understanding and designing new server architectures for emerging warehouse-computing environments (2008) ACM SIGARCH Comput Archit News., 36 (3), pp. 315-326; Hong, S., Fu, Z., Zhou, R., Yu, J., Li, Y., Wang, K., Cheng, G., Cardiolearn: A cloud deep learning service for cardiac disease detection from electrocardiogram (2020) Companion Proceedings of the Web Conference, 2020, pp. 148-152; Zhang, X., Gu, K., Miao, S., Zhang, X., Yin, Y., Wan, C., Yu, Y., Shan, T., Automated detection of cardiovascular disease by electrocardiogram signal analysis: a deep learning system (2020) Cardiovasc Diagn Ther., 10 (2), p. 227. , PID: 32420103

Indexed by Scopus

Leave a Comment