Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Journal of Electrocardiology
Review
a r t i c l e i n f o a b s t r a c t
Article history: Due to its simplicity and low cost, analyzing an electrocardiogram (ECG) is the most common technique for de-
Received 15 May 2019 tecting cardiac arrhythmia. The massive amount of ECG data collected every day, in home and hospital, may pre-
revised 18 July 2019 clude data review by human operators/technicians. Therefore, several methods are proposed for either fully
accepted 8 August 2019
automatic arrhythmia detection or event selection for further verification by human experts. Traditional machine
Available online xxxx
learning approaches have made significant progress in the past years. However, those methods rely on hand-
crafted feature extraction, which requires in-depth domain knowledge and preprocessing of the signal
(e.g., beat detection). This, plus the high variability in wave morphology among patients and the presence of
noise, make it challenging for computerized interpretation to achieve high accuracy. Recent advances in deep
learning make it possible to perform automatic high-level feature extraction and classification. Therefore, deep
learning approaches have gained interest in arrhythmia detection. In this work, we reviewed the recent advance-
ment of deep learning methods for automatic arrhythmia detection. We summarized existing literature from five
aspects: utilized dataset, application, type of input data, model architecture, and performance evaluation. We also
reported limitations of reviewed papers and potential future opportunities.
© 2019 Published by Elsevier Inc.
https://doi.org/10.1016/j.jelectrocard.2019.08.004
0022-0736/© 2019 Published by Elsevier Inc.
Please cite this article as: S. Parvaneh, J. Rubin, S. Babaeizadeh, et al., Cardiac arrhythmia detection using deep learning: A review, Journal of
Electrocardiology, https://doi.org/10.1016/j.jelectrocard.2019.08.004
2 S. Parvaneh et al. / Journal of Electrocardiology xxx (xxxx) xxx
Fig. 1. (a) traditional machine learning and (b) deep neural network for classification.
hidden layers. Compared to traditional machine learning, feature ex- 1- Convolutional Neural Network (CNN): CNNs use single or multiple
traction/selection and classification is automatically performed within convolution and pooling layers followed by fully connected layer
the deep network. Deep learning based algorithms led to outstanding for classification.
performance on various benchmark datasets [7–9]. Especially, 2- Recurrent Neural Network (RNN): RNNs perform the same task for
convolutional neural networks (CNNs) have been used successfully for every element of an input sequence while output is dependent on
solving complex image analysis tasks (both non-medical [10] and med- the previous computation. This network architecture has a memory
ical [11] tasks). Of note, deep neural networks in recent years have been that captures information about data history, and what has been es-
developed or adapted for analysis of 1-D biosignals (time-series) timated so far.
[7,8,12]. 3- Auto-encoder: An auto-encoder is a neural network that is trained to
Well known deep learning architectures [13] include: attempt to copy its input to its output [13].
Fig. 2. (a) Interest over time for deep learning, and (b) research trend for deep learning between January 2010 and December 2018.
Please cite this article as: S. Parvaneh, J. Rubin, S. Babaeizadeh, et al., Cardiac arrhythmia detection using deep learning: A review, Journal of
Electrocardiology, https://doi.org/10.1016/j.jelectrocard.2019.08.004
S. Parvaneh et al. / Journal of Electrocardiology xxx (xxxx) xxx 3
4- Deep Belief Network (DBN): DBNs are a composition of unsuper- Utilized dataset and main goal
vised networks such as restricted Boltzmann machines (RBMs) or
auto-encoders where each sub-network's hidden layer serves as Only a limited number of research papers used private datasets and
the visible layer for the next [13]. the majority of selected papers used the following public datasets:
Performance evaluation
Papers that used MITDB, CUDB, and AFDB used two approaches for
performance evaluation:
a) Splitting data into train and test sets: train data was used for training
a model and test data was used for model evaluation.
b) Using k-fold cross validation: In the kth run, k-1 folds are used for
Fig. 3. Trend of deep learning research for arrhythmia detection. training a model and one fold is used for model evaluation.
Please cite this article as: S. Parvaneh, J. Rubin, S. Babaeizadeh, et al., Cardiac arrhythmia detection using deep learning: A review, Journal of
Electrocardiology, https://doi.org/10.1016/j.jelectrocard.2019.08.004
4 S. Parvaneh et al. / Journal of Electrocardiology xxx (xxxx) xxx
Table 1
A summary table of ECG beats categorized as per ANSI/AAMI EC57; 2012 standard [20].
N S V F Q
Normal Atrial premature Premature ventricular contraction Fusion of ventricular and normal Paced
Left bundle branch block Aberrant atrial premature Ventricular escape Fusion of paced and normal
Right bundle branch block Nodal (junctional) premature Unclassified
Atrial escape Supra ventricular premature
Nodal (junctional) escape
Conclusion
Please cite this article as: S. Parvaneh, J. Rubin, S. Babaeizadeh, et al., Cardiac arrhythmia detection using deep learning: A review, Journal of
Electrocardiology, https://doi.org/10.1016/j.jelectrocard.2019.08.004
S. Parvaneh et al. / Journal of Electrocardiology xxx (xxxx) xxx 5
References [10] Taigman Y, Yang M, Ranzato MA, Wolf L. Deepface: closing the gap to human-level
performance in face verification. Proceedings of the IEEE conference on computer vi-
[1] Tang DH, Gilligan AM, Romero K. Economic burden and disparities in healthcare re- sion and pattern recognition; 2014. p. 1701–8.
source use among adult patients with cardiac arrhythmia. Appl Health Econ Health [11] Rubin J, Sanghavi D, Zhao C, Lee K, Qadir A, Xu-Wilson M. Large scale automated
Policy 2014;12:59–71. reading of frontal and lateral chest x-rays using dual convolutional neural networks
[2] Khoo CW, Krishnamoorthy S, Lim HS, Lip GY. Atrial fibrillation, arrhythmia burden arXiv preprint arXiv:804.07839 ; 2018.
and thrombogenesis. Int J Cardiol 2012;157:318–23. [12] Rubin J, Parvaneh S, Rahman A, Conroy B, Babaeizadeh S. Densely connected
[3] Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, et al. convolutional networks for detection of atrial fibrillation from short single-lead
Cardiologist-level arrhythmia detection and classification in ambulatory electrocar- ECG recordings. J Electrocardiol 2018;51(6):S18–21.
diograms using a deep neural network. Nat Med 2019;25:65–9 2019/01/01. [13] Goodfellow I, Bengio Y, Courville A. Deep learning. MIT press; 2016.
[4] Parvaneh S, Rubin J. Electrocardiogram monitoring and interpretation: from tradi- [14] Goldberger A, Amaral L, Glass L, Hausdorff J, Ivanov P, Mark R, et al. PhysioBank,
tional machine learning to deep learning, and their combination. Computing 2018; PhysioToolkit, and PhysioNet: components of a new research resource for complex
45:1. physiologic signals. Circulation 2000;101:e215.
[5] Interest over time for deep learning. Available https://trends.google.com/trends/ [15] Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med
explore?date=2012-01-01%202019-04-11&geo=US&q=%2Fm%2F0h1fn8h. Biol Mag 2001;20:45–50.
[6] Research trend for deep learning. Available https://app.dimensions.ai/analytics/ [16] Nolle F, Badura F, Catlett J, Bowser R, Sketch M. CREI-GARD, a new concept in com-
publication/viz/overview-publications?search_text=%22deep%20learning% puterized arrhythmia monitoring systems. Computers in Cardiology 1986;13:515–8.
22&search_type=kws&search_field=text_search. [17] Moody G. A new method for detecting atrial fibrillation using RR intervals. Com-
[7] Parvaneh S, Rubin J, Rahman A, Conroy B, Babaeizadeh S. Analyzing single-lead short puters in Cardiology 1983:227–30.
ECG recordings using dense convolutional neural networks and feature-based post- [18] Clifford G, Liu C, Moody B, Silva I, Li Q, Johnson A, et al. AF classification from a short
processing to detect atrial fibrillation. Physiol Meas 2018;39:084003. single lead ECG recording: the PhysioNet computing in cardiology challenge 2017
[8] Potes C, Parvaneh S, Rahman A, Conroy B. Classifier ensemble for detection of abnor- presented at the Computing in Cardiology Rennes-France ; 2017.
mal heart sounds; 2016. [19] Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, et al.
[9] Rubin J, Parvaneh S, Rahman A, Conroy B, Babaeizadeh S. "Densely connected Physiobank, physiotoolkit, and physionet. Circulation 2000;101:e215–20.
convolutional networks and signal quality analysis to detect atrial fibrillation [20] Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A, et al. A deep
using short single-lead ECG recordings," presented at the Computing in Cardiology convolutional neural network model to classify heartbeats. Comput Biol Med
Rennes-France; 2017. 2017;89:389–96.
Please cite this article as: S. Parvaneh, J. Rubin, S. Babaeizadeh, et al., Cardiac arrhythmia detection using deep learning: A review, Journal of
Electrocardiology, https://doi.org/10.1016/j.jelectrocard.2019.08.004