A Review of Deep Learning Methods on ECG Data
Shenda Hong, Yuxi Zhou, Junyuan Shang, Cao Xiao, and Jimeng Sun. "Opportunities and Challenges of Deep Learning Methods for Electrocardiogram Data: A Systematic Review." Computers in Biology and Medicine. https://arxiv.org/pdf/2001.01550.pdf
We are keep updating new papers in this repo and our arXiv version! If you have any recommendations, please open an issue or send us an email, including below information:
- Title
- Link
- Venue
- Task
- Method
- Dataset
- A sentence of brief description.
Summary Table (Updating. Oct, 2020)
| ID | Year | Title | Link | Venue | Task | Method | Dataset |
|---|---|---|---|---|---|---|---|
| 1 | 2015 | Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks | link | TBME | beat classify | CNN | MIT-BIH arrhythmia |
| 2 | 2015 | Convolutional Neural Networks for patient-specific ECG classification | link | EMBC | beat classify | CNN | MIT-BIH arrhythmia |
| 3 | 2016 | ECG Monitoring System Integrated With IR-UWB Radar Based on CNN | link | IEEE ACCESS | arrhythmia classification | CNN | The radar data and ECG data are acquired by radar module NVA-R661 and BMD101 sensor chip |
| 4 | 2016 | A stacked contractive denoising auto-encoder for ECG signal denoising | link | PMEA | denoising | DAE | MIT-BIH arrhythmia, MIT-BIH Noise Stress Test |
| 5 | 2016 | Semi-supervised stacked label consistent autoencoder for reconstruction and analysis of biomedical signals | link | TBME | reconstruction | AE | MIT-BIH arrhythmia, edb |
| 6 | 2017 | Real-time multilead convolutional neural network for myocardial infarction detection | link | BHI | MI | CNN | PTBDB |
| 7 | 2017 | A deep convolutional neural network model to classify heartbeats | link | CBM | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 8 | 2017 | Automatic coordinate prediction of the exit of ventricular tachycardia from 12-lead electrocardiogram | link | CinC | localize VT | DAE | not found |
| 9 | 2017 | ENCASE: An ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks | link | CinC | AF | resnet+expert | Physionet Challenge 2017 |
| 10 | 2017 | Convolutional recurrent neural networks for electrocardiogram classification | link | CinC | AF | CNN+RNN | Physionet Challenge 2017 |
| 11 | 2017 | AF Classification from a short single lead ECG recording: the PhysioNet/Computing in Cardiology Challenge 2017 | link | CinC | AF | Physionet Challenge 2017 | |
| 12 | 2017 | Robust ECG signal classification for detection of atrial fibrillation using a novel neural network | link | CinC | AF | resnet | Physionet Challenge 2017 |
| 13 | 2017 | Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG | link | CinC | AF | CNN+feature | Physionet Challenge 2017 |
| 14 | 2017 | Cardiac arrhythmia detection from ECG combining convolutional and long short-term memory networks | link | CinC | AF | CNN+RNN | Physionet Challenge 2017 |
| 15 | 2017 | Atrial fibrillation detection using stationary wavelet transform and deep learning | link | CinC | AF | CNN+feature | Physionet Challenge 2017 |
| 16 | 2017 | Densely connected convolutional networks and signal quality analysis to detect atrial fibrillation using short single-lead ECG recordings | link | CinC | AF | DenseNet | Physionet Challenge 2017 |
| 17 | 2017 | Atrial fibrillation detection and ECG classification based on convolutional recurrent neural network | link | CinC | AF | CNN | Physionet Challenge 2017 |
| 18 | 2017 | Atrial fibrillation classification using qrs complex features and lstm | link | CinC | AF | LSTM+expert | Physionet Challenge 2017 |
| 19 | 2017 | Atrial fibrillation detection using feature based algorithm and deep convolutional neural network | link | CinC | AF | CNN+expert | Physionet Challenge 2017 |
| 20 | 2017 | Beat by beat: Classifying cardiac arrhythmias with recurrent neural networks | link | CinC | AF | RNN+attention | Physionet Challenge 2017 |
| 21 | 2017 | Annotating ECG Signals With Deep Neural Networks | link | Circulation | annotate ECG waves | BiLSTM | QTDB |
| 22 | 2017 | Cardiovascular risk stratification using off-the-shelf wearables and a multi-task deep learning algorithm | link | Circulation | prevalent hypertension, sleep apnea, and diabetes | CNN+RNN | see DeepHeart |
| 23 | 2017 | HeartID: A Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications | link | IEEE ACCESS | Biometric Human Identification | CNN | CEBSDB, WECG, FANTASIA, NSRDB, STDB, MITDB, AFDB, VFDB |
| 24 | 2017 | ECG data compression using a neural network model based on multi-objective optimization | link | PlosOne | data compression | FCNN | MIT-BIH arrhythmia |
| 25 | 2017 | Personalized Monitoring and Advance Warning System for Cardiac Arrhythmias | link | SR | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 26 | 2017 | Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients | link | T Cybernetics | AF | CNN | |
| 27 | 2017 | Localization of origins of premature ventricular contraction by means of convolutional neural network from 12-lead ECG | link | TBME | Localization | CNN | not found |
| 28 | 2017 | Recognition of emotions using multimodal physiological signals and an ensemble deep learning model | link | CMPB | emotion detection | SAE | DEAP |
| 29 | 2017 | Elimination of power line interference from ECG signals using recurrent neural networks | link | EMBC | denoisig | RNN | synthetic |
| 30 | 2018 | DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction | link | AAAI | diagnosis | CNN+RNN semi | close, https://ahajournals.org/doi/abs/10.1161/circ.136.suppl_1.21029 |
| 31 | 2018 | A Deep Learning Approach to Examine Ischemic ST Changes in Ambulatory ECG Recordings | link | AMIA | ST | CNN model from Inception V3 | ltstdb |
| 32 | 2018 | Towards end-to-end ECG classification with raw signal extraction and deep neural networks | link | BHI | classify MIT-BIH arrhythmia | RBM | MIT-BIH arrhythmia |
| 33 | 2018 | Automated detection of atrial fibrillation using long short-term memory network with RR interval signals | link | CBM | AF | CNN+RNN | afdb |
| 34 | 2018 | Detecting atrial fibrillation by deep convolutional neural networks | link | CBM | AF | CNN | afdb |
| 35 | 2018 | ECG authentication system design incorporating a convolutional neural network and generalized S-Transformation | link | CBM | Biometric Human Identification | CNN | ecgiddb, Physionet Challenge 2017 |
| 36 | 2018 | Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals | link | CBM | Coronary artery disease | CNN+RNN | incartdb |
| 37 | 2018 | Arrhythmia detection using deep convolutional neural network with long duration ECG signals | link | CBM | arrhythmia | CNN | MIT-BIH arrhythmia |
| 38 | 2018 | A novel application of deep learning for single-lead ECG classification | link | CBM | arrhythmia | DBN | MIT-BIH arrhythmia |
| 39 | 2018 | Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats | link | CBM | arrhythmia | CNN+RNN | MIT-BIH arrhythmia |
| 40 | 2018 | A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification | link | CBM | classify MIT-BIH arrhythmia | BiLSTM | MIT-BIH arrhythmia |
| 41 | 2018 | Deep Learning for Pulse Detection in Out-of-Hospital Cardiac Arrest Using the ECG | link | CinC | Pulse Detection | CNN+RNN | not found |
| 42 | 2018 | Electrocardiogram Monitoring and Interpretation: From Traditional Machine Learning to Deep Learning, and Their Combination | link | CinC | NA | ||
| 43 | 2018 | AF Detection by Exploiting the Spectral and Temporal Characteristics of ECG Signals With the LSTM Model | link | CinC | AF | LSTM for multi-head ECG | Physionet Challenge 2017 |
| 44 | 2018 | Classification of Atrial Fibrillation Using Stacked Auto Encoders Neural Networks | link | CinC | AF | AE | Physionet Challenge 2017 |
| 45 | 2018 | Generalization Studies of Neural Network Models for Cardiac Disease Detection Using Limited Channel ECG | link | CinC | Disease | CNN+RNN | PTBDB |
| 46 | 2018 | Deep learning based QRS multilead delineator in electrocardiogram signals | link | CinC | QRS | 1-D CNN, ECG delineation to find QRS width by two CNN+MLP | QTDB |
| 47 | 2018 | Artificial Intelligence Detects Pediatric Heart Murmurs With Cardiologist-Level Accuracy | link | Circulation | Detects Pediatric Heart Murmurs | 只说了deep neural network | 54 patients collected at duPont Hospital for Children using an Eko Core digital stethoscope |
| 48 | 2018 | Electrocardiographic Screening for Atrial Fibrillation While in Sinus Rhythm Using Deep Learning | link | Circulation | AF | CNN | Mayo Clinic database |
| 49 | 2018 | A 10-RR-Interval-Based Rhythm Classifier Using a Deep Neural Network | link | Circulation | 5 rhythms: normal sinus rhythm, atrial fibrillation, premature beats, bigeminy, and trigeminy | 只说了deep neural network | only PhysioNet |
| 50 | 2018 | Deep Learning to Detect Atrial Fibrillation From Short Noisy ECG Segments Measured With Wireless Sensors | link | Circulation | AF | CNN | Physionet Challenge 2017 |
| 51 | 2018 | ECG classification using three-level fusion of different feature descriptors | link | ESA | classify MIT-BIH arrhythmia | CNN+expert | MIT-BIH arrhythmia |
| 52 | 2018 | Using deep convolutional neural network for emotion detection on a physiological signals dataset (AMIGOS) | link | IEEE ACCESS | emotion detection | CNN | AMIGOS |
| 53 | 2018 | Combining convolutional neural network and distance distribution matrix for identification of congestive heart failure | link | IEEE ACCESS | diagnoise CHF | CNN+emotion detection | CHF2DB, NSRDB |
| 54 | 2018 | Automated ECG Classification Using Dual Heartbeat Coupling Based on Convolutional Neural Network | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 55 | 2018 | An Automatic Cardiac Arrhythmia Classification System With Wearable Electrocardiogram | link | IEEE ACCESS | classify MIT-BIH arrhythmia | SDAE | MIT-BIH arrhythmia |
| 56 | 2018 | Multimodal Biometric Authentication Systems Using Convolution Neural Network Based on Different Level Fusion of ECG and Fingerprint | link | IEEE ACCESS | Biometric Human Identification | CNN+SVM | PTBDB, CYBHi |
| 57 | 2018 | NON-INVASIVE DETECTION OF HYPERKALEMIA WITH A SMARTPHONE ELECTROCARDIOGRAM AND ARTIFICIAL INTELLIGENCE | link | JACC | DNN | ||
| 58 | 2018 | RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data | link | KDD | mortality | CRNN | MIMIC-III |
| 59 | 2018 | Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks | link | KDD | AF | BiRNN+attention+CNN | own collected |
| 60 | 2018 | A method to detect sleep apnea based on deep neural network and hidden markov model using single-lead ECG signal | link | Neurocomputing | Sleep | SAE | Apnea-ECG |
| 61 | 2018 | Patient-specific ECG classification by deeper CNN from generic to dedicated | link | Neurocomputing | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 62 | 2018 | Noninvasive assessment of dofetilide plasma concentration using a deep learning (neural network) analysis of the surface electrocardiogram: A proof of concept study | link | PlosOne | drug assessment | CNN | ecgrdvq, ecgdmmld |
| 63 | 2018 | Sleep-wake classification via quantifying heart rate variability by convolutional neural network | link | PMEA | sleep | CNN | own collected |
| 64 | 2018 | Multiclass classification of obstructive sleep apnea/hypopnea based on a convolutional neural network from a single-lead electrocardiogram | link | PMEA | sleep stage | CNN | own collected |
| 65 | 2018 | A deep learning approach for fetal QRS complex detection | link | PMEA | QRS | CNN | Physionet Challenge 2013 |
| 66 | 2018 | Abductive reasoning as a basis to reproduce expert criteria in ECG atrial fibrillation identification | link | PMEA | AF | LSTM+expert | Physionet Challenge 2017 |
| 67 | 2018 | Analyzing single-lead short ECG recordings using dense convolutional neural networks and feature-based post-processing to detect atrial fibrillation | link | PMEA | arrhythmia | densenet | Physionet Challenge 2017 |
| 68 | 2018 | ECG signal classification for the detection of cardiac arrhythmias using a convolutional recurrent neural network | link | PMEA | arrhythmia | resnet | Physionet Challenge 2017 |
| 69 | 2018 | Parallel use of a convolutional neural network and bagged tree ensemble for the classification of Holter ECG | link | PMEA | arrhythmia | CNN+tree | Physionet Challenge 2017 |
| 70 | 2018 | Ensembling convolutional and long short-term memory networks for electrocardiogram arrhythmia detection | link | PMEA | arrhythmia | CNN+LSTM | Physionet Challenge 2017 |
| 71 | 2018 | A convolutional neural network for ECG annotation as the basis for classification of cardiac rhythms | link | PMEA | arrhythmia | CNN | Physionet Challenge 2017 |
| 72 | 2018 | A robust deep convolutional neural network for the classification of abnormal cardiac rhythm using single lead electrocardiograms of variable length | link | PMEA | arrhythmia | CNN+feature | Physionet Challenge 2017 |
| 73 | 2018 | Detecting and interpreting myocardial infarction using fully convolutional neural networks | link | PMEA | MI | CNN | PTBDB |
| 74 | 2018 | Deep Feature Learning for Sudden Cardiac Arrest Detection in Automated External Defibrillators | link | SR | Sudden Cardiac Arrest Detection | CNN | CUDB, VFDB |
| 75 | 2018 | Monitoring Significant ST Changes through Deep Learning | link | JE | ST | CNN | LTSTDB |
| 76 | 2018 | Densely connected convolutional networks for detection of atrial fibrillation from short single-lead ECG recordings | link | JE | arrhythmia | CNN | Physionet Challenge 2017 |
| 77 | 2018 | Region Aggregation Network: Improving Convolutional Neural Network for ECG Characteristic Detection | link | EMBC | annotate ECG waves | CNN | QTDB |
| 78 | 2018 | A Generative Modeling Approach to Limited Channel ECG Classification | link | EMBC | classify | RNN (encoder decoder) | PTBDB |
| 79 | 2018 | Classification of Heart Diseases Based On ECG Signals Using Long Short-Term Memory | link | EMBC | beat classify | RNN | UCR |
| 80 | 2018 | Finger ECG based Two-phase Authentication Using 1D Convolutional Neural Networks | link | EMBC | identification | CNN | own collected |
| 81 | 2018 | QRS Detection and Measurement Method of ECG Paper Based on Convolutional Neural Networks | link | EMBC | QRS detection | CNN | incartdb |
| 82 | 2018 | Bidirectional Recurrent Neural Network And Convolutional Neural Network (BiRCNN) For ECG Beat Classification | link | EMBC | beat classify | CRNN | MIT-BIH arrhythmia |
| 83 | 2018 | Premature Ventricular Contraction Detection from Ambulatory ECG Using Recurrent Neural Networks | link | EMBC | PVC | RNN | MIT-BIH arrhythmia |
| 84 | 2019 | A Comparison of Patient History- and EKG-based Cardiac Risk Scores | link | AMIA | Patient-specific risk scores | resnet | close, electronic health records in the Partners health care system, associated with Brigham and Women’s hospital (BWH) |
| 85 | 2019 | Synthesis of Electrocardiogram V Lead Signals from Limb Lead Measurement using R peak Aligned Generative Adversarial Network | link | BHI | Synthesis V Lead | GAN | PTBDB |
| 86 | 2019 | I-Vector Based Patient Adaptation of Deep Neural Networks for Automatic Heartbeat Classification | link | BHI | classify MIT-BIH arrhythmia | FCNN | MIT-BIH arrhythmia |
| 87 | 2019 | Accurate detection of atrial fibrillation from 12-lead ECG using deep neural network | link | CBM | AF | CNN | Chinese PLA General Hospital, CardioCloud Medical Technology (Beijing) Co. Ltd, CPSC |
| 88 | 2019 | ECG anomaly class identification using LSTM and error profile modeling | link | CBM | classify MIT-BIH arrhythmia | LSTM | MIT-BIH arrhythmia |
| 89 | 2019 | Automated beat-wise arrhythmia diagnosis using modified U-net on extended electrocardiographic recordings with heterogeneous arrhythmia types | link | CBM | classify MIT-BIH arrhythmia | Unet | MIT-BIH arrhythmia |
| 90 | 2019 | Automatic driver stress level classification using multimodal deep learning | link | ESA | driver stress level classification | CNN+LSTM | closed |
| 91 | 2019 | A deep learning approach for real-time detection of atrial fibrillation | link | ESA | AF | CNN+RNN | afdb, mitdb, nsrdb |
| 92 | 2019 | A novel multi-module neural network system for imbalanced heartbeats classification | link | ESA | classify beats MIT-BIH & others | CNN | MIT-BIH arrhythmia |
| 93 | 2019 | A robust deep convolutional neural network with batch-weighted loss for heartbeat classification | link | ESA | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 94 | 2019 | QRS detection method based on fully convolutional networks for capacitive electrocardiogram | link | ESA | QRS | CNN | MIT-BIH arrhythmia |
| 95 | 2019 | A LSTM and CNN Based Assemble Neural Network Framework for Arrhythmias Classification | link | ICASSP | arrhythmia | CNN+LSTM | incartdb |
| 96 | 2019 | Inter- and Intra- Patient ECG Heartbeat Classification for Arrhythmia Detection: A Sequence to Sequence Deep Learning Approach | link | ICASSP | classify MIT-BIH arrhythmia | CRNN | MIT-BIH arrhythmia |
| 97 | 2019 | An Ensemble of Deep Recurrent Neural Networks for P-wave Detection in Electrocardiogram | link | ICASSP | P wave detection | RNN | QTDB |
| 98 | 2019 | A Multi-Class Automatic Sleep Staging Method Based on Long Short-Term Memory Network Using Single-Lead Electrocardiogram Signals | link | IEEE ACCESS | Sleep Staging | LSTM | own collected |
| 99 | 2019 | Noise Rejection for Wearable ECGs Using Modified Frequency Slice Wavelet Transform and Convolutional Neural Networks | link | IEEE ACCESS | noise detection | CNN+features | 12-lead Lenovo Smart ECG device |
| 100 | 2019 | A Novel Deep Arrhythmia-Diagnosis Network for Atrial Fibrillation Classification Using Electrocardiogram Signals | link | IEEE ACCESS | AF heartbeats, MIT-BIH AF | CNN+BiLSTM | afdb |
| 101 | 2019 | Deep Ensemble Detection of Congestive Heart Failure Using Short-Term RR Intervals | link | IEEE ACCESS | CHF | CNN+RNN | BIDMC, CHF2DB |
| 102 | 2019 | A Probabilistic Process Neural Network and Its Application in ECG Classification | link | IEEE ACCESS | disease classification, Chinese Cardiovascular Disease Database (CCDD) | probabilistic process neural network (PPNN) | CCDD |
| 103 | 2019 | Automatic Cardiac Arrhythmia Classification Using Combination of Deep Residual Network and Bidirectional LSTM | link | IEEE ACCESS | CPSC | resnet+BiLSTM | CPSC |
| 104 | 2019 | Personal Identification Using a Robust Eigen ECG Network Based on Time-Frequency Representations of ECG Signals | link | IEEE ACCESS | Biometric Human Identification | principal component analysis network | CUDB, PTBDB |
| 105 | 2019 | Early and remote detection of possible heartbeat problems with convolutional neural networks and multipart interactive training | link | IEEE ACCESS | beat classification | resnet | Kaggle Classifying Heart Sounds Challenge |
| 106 | 2019 | ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network | link | IEEE ACCESS | arrhythmia classification | CNN+features | MIT-BIH arrhythmia |
| 107 | 2019 | Automatic classification of CAD ECG signals with SDAE and bidirectional long short-term term network | link | IEEE ACCESS | classify MIT-BIH arrhythmia | SDAE+BiLSTM | MIT-BIH arrhythmia |
| 108 | 2019 | Simultaneous Human Health Monitoring and Time-Frequency Sparse Representation Using EEG and ECG Signals | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN+generalized minimax-concave (GMC) | MIT-BIH arrhythmia |
| 109 | 2019 | A Novel Wearable Electrocardiogram Classification System Using Convolutional Neural Networks and Active Learning | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN + active learning | MIT-BIH arrhythmia |
| 110 | 2019 | Interpretability Analysis of Heartbeat Classification Based on Heartbeat Activity’s Global Sequence Features and BiLSTM-Attention Neural Network | link | IEEE ACCESS | classify MIT-BIH arrhythmia | BiLSTM-Attention | MIT-BIH arrhythmia |
| 111 | 2019 | Morphological Arrhythmia Automated Diagnosis Method Using Gray-Level Co-Occurrence Matrix Enhanced Convolutional Neural Network | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN+??? | MIT-BIH arrhythmia |
| 112 | 2019 | Automated Heartbeat Classification Using 3-D Inputs Based on Convolutional Neural Network With Multi-Fields of View | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 113 | 2019 | Automated Heartbeat Classification Exploiting Convolutional Neural Network With Channel-Wise Attention | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN+Attention | MIT-BIH arrhythmia |
| 114 | 2019 | Impact of ECG Dataset Diversity on Generalization of CNN Model for Detecting QRS Complex | link | IEEE ACCESS | QRS detection | CNN | MIT-BIH arrhythmia, INCART, QT |
| 115 | 2019 | Noise Reduction in ECG Signals Using Fully Convolutional Denoising Autoencoders | link | IEEE ACCESS | Noise Reduction | CNN+DAE | MIT-BIH arrhythmia, NSTDB |
| 116 | 2019 | ECG Arrhythmias Detection Using Auxiliary Classifier Generative Adversarial Network and Residual Network | link | IEEE ACCESS | MIT-BIH + 2018 China physiological signal challenge (CPSC) | GAN(data augmentation)+CRNN | MIT-BIH, CPSC |
| 117 | 2019 | Real-Time Detection of Acute Cognitive Stress Using a Convolutional Neural Network From Electrocardiographic Signal | link | IEEE ACCESS | Detection of Acute Cognitive Stress | CNN | own collected |
| 118 | 2019 | Atrial Fibrillation Detection Using an Improved Multi-Scale Decomposition Enhanced Residual Convolutional Neural Network | link | IEEE ACCESS | Atrial Fibrillation Detection | 1-D CNN, multis-cale residual neural network | Physionet Challenge 2017 |
| 119 | 2019 | ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network With Center and Margin Loss | link | IEEE ACCESS | Biometric Human Identification | resnet | Physionet Challenge 2017, PTBDB, ECG-ID, MIT-BIH arrhythmia |
| 120 | 2019 | Automated Detection and Localization of Myocardial Infarction With Staked Sparse Autoencoder and TreeBagger | link | IEEE ACCESS | PTBDB, MI | SAE | PTBDB |
| 121 | 2019 | Preprocessing Method for Performance Enhancement in CNN-Based STEMI Detection From 12-Lead ECG | link | IEEE ACCESS | ST | CNN | SNUBH |
| 122 | 2019 | Classification of Atrial Fibrillation Recurrence Based on a Convolution Neural Network With SVM Architecture | link | IEEE ACCESS | Atrial Fibrillation Detection | CNN+SVM | West China Hospital |
| 123 | 2019 | MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals | link | IJCAI | AF | CNN+RNN+attention | Physionet Challenge 2017 |
| 124 | 2019 | K-margin-based Residual-convolution-recurrent Neural Network for Atrial Fibrillation Detection | link | IJCAI | AF | CNN + BiLSTM | Physionet Challenge 2017 |
| 125 | 2019 | PREDICTION OF THE HEART RATE CORRECTED QT INTERVAL (QTC) FROM A NOVEL, MULTILEAD SMARTPHONE-ENABLED ECG USING A DEEP NEURAL NETWORK | link | JACC | QT | DNN | |
| 126 | 2019 | APPLICATION OF ARTIFICIAL INTELLIGENCE TO DETECT ST ELEVATION MI WITH A SINGLE LEAD EKG | link | JACC | ST MI | CNN | |
| 127 | 2019 | Ambulatory Atrial Fibrillation Monitoring Using Wearable Photoplethysmography with Deep Learning | link | KDD | AF | resnet | own collected |
| 128 | 2019 | Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram | link | Nature medicine | diagnose ALVD on 12 lead | CNN, 6 Conv layers | Mayo |
| 129 | 2019 | Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network | link | Nature medicine | classify 12 rhythm classes | resnet | own collected |
| 130 | 2019 | Adversarial de-noising of electrocardiogram | link | Neurocomputing | Denoising | GAN | MIT-BIH arrhythmia, MIT-BIH Noise Stress Test |
| 131 | 2019 | Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients | link | PlosOne | predict needs for urgent revascularization | CNN+RNN | own collected |
| 132 | 2019 | Mixed convolutional and long short-term memory network for the detection of lethal ventricular arrhythmia | link | PlosOne | detection of VF | CNN+RNN | VFDB, CUDB, AHADB |
| 133 | 2019 | Ventricular ectopic beat detection using a wavelet transform and a convolutional neural network | link | PMEA | Ventricular ectopic beat | CNN | MIT-BIH arrhythmia, AHADB |
| 134 | 2019 | Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings | link | PMEA | arrhythmia | resnet+expert | Physionet Challenge 2017 |
| 135 | 2019 | Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network | link | SR | data generation | BiLSTM+CNN+GAN | MIT-BIH arrhythmia |
| 136 | 2019 | Sequential Factorized Autoencoder for Localizing the Origin of Ventricular Activation From 12-Lead Electrocardiograms | link | TBME | localizing the origin of VT | RNN + AE | own collected |
| 137 | 2019 | PGANs: Personalized Generative Adversarial Networks for ECG Synthesis to Improve Patient-Specific Deep ECG Classification | link | AAAI | semi-supervised classification | GAN+LSTM | MIT-BIH arrhythmia |
| 138 | 2019 | Inter-Patient ECG Classification with Symbolic Representations and Multi-Perspective Convolutional Neural Networks | link | JBHI | classify MIT-BIH arrhythmia | symbolic features + CNN | MIT-BIH arrhythmia |
| 139 | 2019 | Detection of First-Degree Atrioventricular Block on Variable-Length Electrocardiogram via a Multimodal Deep Learning Method | link | CinC | IAVB | CRNN | CPSC |
| 140 | 2019 | Fetal Electrocardiography and Deep Learning for Prenatal Detection of Congenital Heart Disease | link | CinC | CHD | CNN | own collected |
| 141 | 2019 | U-Net Architecture for the Automatic Detection and Delineation of the Electrocardiogram | link | CinC | segmentation | CNN (unet) | QTDB |
| 142 | 2019 | Pay Attention and Watch Temporal Correlation: A Novel 1-D Convolutional Neural Network for ECG Record Classification | link | CinC | classify | CRNN | CPSC, Physionet Challenge 2017 |
| 143 | 2019 | Deep Convolutional Encoder-Decoder Framework for Fetal ECG Signal Denoising | link | CinC | denoisig | CNN (encoder decoder) | Fetal ECG Synthetic database of Physionet |
| 144 | 2019 | PVC Recognition for Wearable ECGs Using Modified Frequency Slice Wavelet Transform and Convolutional Neural Network | link | CinC | PVC | CNN | CPSC |
| 145 | 2019 | Validation of a Deep Learning-Enabled Electrocardiogram Algorithm to Detect and Predict Cardiac Contractile Dysfunction in the Community | link | Circulation | disease | unclear | own collected |
| 146 | 2019 | Deep Neural Networks Can Predict 1-Year Mortality Directly From ECG Signal, Even When Clinically Interpreted as Normal | link | Circulation | mortality | unclear | own collected |
| 147 | 2019 | A Deep Neural Network for Predicting Incident Atrial Fibrillation Directly From 12-Lead Electrocardiogram Traces | link | Circulation | AF | unclear | own collected |
| 148 | 2019 | A Deep Learning Model to Predict Outcome After Thoracoscopic Surgery for Atrial Fibrillation Using Single Beat Electrocardiographic Samples | link | Circulation | Benefits of Thoracoscopic surgery for atrial fibrillation | CNN | own collected |
| 149 | 2019 | Developing Convolutional Neural Networks for Deep Learning of Ventricular Action Potentials to Predict Risk for Ventricular Arrhythmias | link | Circulation | Ventricular Arrhythmias | CNN | own collected |
| 150 | 2019 | Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs | link | Circulation | demographics | CNN | own collected |
| 151 | 2019 | Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discovery | link | Circulation | segmentation | CNN + HMM | own collected |
| 152 | 2019 | BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series | link | IJCAI | beat level anomaly detection | CNN + GAN | MIT-BIH arrhythmia |
| 153 | 2019 | Artificial intelligence algorithm for predicting mortality of patients with acute heart failure | link | PlosOne | mortality | DNN | own collected |
| 154 | 2019 | Detection of atrial fibrillation and other abnormal rhythms from ECG using a multi-layer classifier architecture | link | PMEA | arrhythmia | MLP | Physionet Challenge 2017 |
| 155 | 2019 | Deep-ECG: Convolutional Neural Networks for ECG biometric recognition | link | PRL | identification | CNN | IDEAL, PTBDB |
| 156 | 2019 | Classification of myocardial infarction with multi-lead ECG signals and deep CNN | link | PRL | MI | CNN | PTBDB |
| 157 | 2019 | ECG-based personal recognition using a convolutional neural network | link | PRL | identification | CNN | PTBDB, CEBSDB, NSRDB, MITDB |
| 158 | 2019 | Deep learning approaches for automatic detection of sleep apnea events from an electrocardiogram | link | CMPB | sleep | DNN, CNN, RNN | own collected |
| 159 | 2019 | A new approach for arrhythmia classification using deep coded features and LSTM networks | link | CMPB | classify MIT-BIH arrhythmia | CNN + RNN, AE | MIT-BIH arrhythmia |
| 160 | 2019 | A deep neural network learning algorithm outperforms a conventional algorithm for emergency department electrocardiogram interpretation | link | JE | ECG interpretation | CNN | own collected |
| 161 | 2019 | Deep learning to automatically interpret images of the electrocardiogram: Do we need the raw samples? | link | JE | arrhythmia | CNN | Physionet Challenge 2017 |
| 162 | 2019 | Dual-Input Neural Network Integrating Feature Extraction and Deep Learning for Coronary Artery Disease Detection Using Electrocardiogram and Phonocardiogram | link | IEEE ACCESS | CAD | CRNN + expert | own collected |
| 163 | 2019 | A Deep Bidirectional GRU Network Model for Biometric Electrocardiogram Classification Based on Recurrent Neural Networks | link | IEEE ACCESS | identification | CRNN | ECGID, MITDB |
| 164 | 2019 | Localization of Myocardial Infarction With Multi-Lead Bidirectional Gated Recurrent Unit Neural Network | link | IEEE ACCESS | MI | RNN | PTBDB |
| 165 | 2019 | Feature Enrichment Based Convolutional Neural Network for Heartbeat Classification From Electrocardiogram | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 166 | 2019 | ECG Generation With Sequence Generative Adversarial Nets Optimized by Policy Gradient | link | IEEE ACCESS | ECG generation | CNN + GAN | MIT-BIH arrhythmia |
| 167 | 2019 | Dense Convolutional Networks With Focal Loss and Image Generation for Electrocardiogram Classification | link | IEEE ACCESS | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 168 | 2019 | An Automatic System for Real-Time Identifying Atrial Fibrillation by Using a Lightweight Convolutional Neural Network | link | IEEE ACCESS | AF | CNN + experts | AFDB |
| 169 | 2019 | Biosignal Generation and Latent Variable Analysis With Recurrent Generative Adversarial Networks | link | IEEE ACCESS | ECG generation | RNN + GAN | UCR |
| 170 | 2019 | A Parallel GRU Recurrent Network Model and its Application to Multi-Channel Time-Varying Signal Classification | link | IEEE ACCESS | classify | RNN | CCDD |
| 171 | 2019 | Inter-Patient CNN-LSTM for QRS Complex Detection in Noisy ECG Signals | link | IEEE ACCESS | QRS detection | CRNN | MIT-BIH arrhythmia, European ST-T |
| 172 | 2019 | ECG Biometric Recognition: Template-Free Approaches Based on Deep Learning | link | EMBC | identification | CNN | PTBDB |
| 173 | 2019 | Deep Learning Based Patient-Specific Classification of Arrhythmia on ECG signal | link | EMBC | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 174 | 2019 | A Deep Learning Method to Detect Atrial Fibrillation Based on Continuous Wavelet Transform | link | EMBC | AF | CNN | MIT-BIH Arrhythmia Database (DB1) [11], the MIT-BIH Malignant Ventricular Arrhythmia Database (DB2) [12], the MIT-BIH Atrial Fibrillation Database (DB3) [13], the Long- Term AF Database (DB4) [14], the MIT-BIH Normal Sinus Rhythm Database (DB5) [15] and the MIT-BIH Noise Stress Test Database (DB6) [16] |
| 175 | 2019 | An Electrocardiogram Delineator via Deep Segmentation Network | link | EMBC | annotate ECG waves | CNN | QTDB |
| 176 | 2019 | Spectro-Temporal Feature Based Multi-Channel Convolutional Neural Network for ECG Beat Classification | link | EMBC | beat classify | CNN + experts | MIT-BIH arrhythmia |
| 177 | 2019 | Cardiovascular disease diagnosis using cross-domain transfer learning | link | EMBC | classify | CNN | CPSC |
| 178 | 2020 | LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices | link | JBHI | classify MIT-BIH arrhythmia | LSTM | MIT-BIH arrhythmia |
| 179 | 2020 | Atrial Fibrillation Prediction With Residual Network Using Sensitivity and Orthogonality Constraints | link | JBHI | AF | spectrogram + ResNet CNN | AFDB, Physionet Challenge 2017 |
| 180 | 2020 | MFB-CBRNN: A Hybrid Network for MI Detection Using 12-Lead ECGs | link | JBHI | MI | CRNN | PTBDB |
| 181 | 2020 | Assessing and Mitigating Bias in Medical Artificial Intelligence: The Effects of Race and Ethnicity on a Deep Learning Model for ECG Analysis | link | Circulation | LVEF | CNN | own collected |
| 182 | 2020 | Toward improving ECG biometric identification using cascaded convolutional neural networks | link | Neurocomputing | identification | CNN | FANTASIA, CEBSDB, NSRDB, STDB, AFDB |
| 183 | 2020 | Single-modal and multi-modal false arrhythmia alarm reduction using attention- based convolutional and recurrent neural networks | link | PlosOne | arrhythmia | CRNN | PhysioNet challenge 2015 |
| 184 | 2020 | Detection of strict left bundle branch block by neural network and a method to test detection consistency | link | PMEA | LBBB | DNN | International Society for Computerized Electrocardiology (ISCE) and the Telemetric and Holter Initiative (THEW-project.org) held a competition |
| 185 | 2020 | End-to-end trained encoder–decoder convolutional neural network for fetal electrocardiogram signal denoising | link | PMEA | denoisig | CNN (encoder decoder) | Fetal ECG Synthetic database of Physionet |
| 186 | 2020 | Precision Medicine and Artificial Intelligence: A Pilot Study on Deep Learning for Hypoglycemic Events Detection based on ECG | link | SR | Hypoglycemic Events Detection | CRNN | own collected |
| 187 | 2020 | Transfer Learning in ECG Classification from Human to Horse Using a Novel Parallel Neural Network Architecture | link | SR | transfer diagnosis from human to horse | CNN | MIT-BIH arrhythmia, equine electrocardiogram |
| 188 | 2020 | Multi-branch fusion network for Myocardial infarction screening from 12-lead ECG images | link | CMPB | MI | CNN | own collected |
| 189 | 2020 | ML–ResNet: A novel network to detect and locate myocardial infarction using 12 leads ECG | link | CMPB | MI | CNN | PTBDB |
| 190 | 2020 | Heartbeat classification using deep residual convolutional neural network from 2-lead electrocardiogram | link | JE | classify MIT-BIH arrhythmia | CNN | MIT-BIH arrhythmia |
| 191 | 2020 | Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial Networks | link | IEEE ACCESS | ECG generation | CNN + GAN | MIT-BIH arrhythmia |
| 192 | 2020 | Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network | link | Nature Medicine | Mortality prediction | CNN | US health system (Geisinger) |
| 193 | 2020 | Deep learning models for electrocardiograms are susceptible to adversarial attack | link | Nature Medicine | Adversarial attack in disease detection | GAN | PhysioNet Challenge 2017 |
| 194 | 2019 | An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction | link | The Lancet | AF detection during sinus rhythm | CNN | Mayo Clinic |
| 195 | 2020 | Automatic Multi-Label ECG Diagnosis of Impulse or Conduction Abnormalities in Patients with Deep Learning Algorithm: A Cohort Study | link | The Lancet Digital Health | Arrhythmias | CNN | Three campuses of Tongji Hospital (Huazhong University of Science and Technology, Wuhan, China) and CPSC |
| 196 | 2020 | Improve robustness of DNN for ECG signal classification: a noise-to-signal ratio perspective | link | ICLR2020, AI4AH workshop | Improving robustness against adversarial noises | MLP+CNN | MIT-BIH Arrhythmia |
| 196 | 2019 | Deep Learning Applied to Attractor Images Derived from ECG Signals for Detection of Genetic Mutation | link | CinC 2019 | Generating attractor images from ECG signals | Symmetric Projection Attractor Reconstruction (SPAR) + pre-trained network from Matlab 2019a Deep Learning Toolbox | 42 anaesthetised mice |