Applications of Machine Learning in Ambulatory ECG

The ambulatory ECG (AECG) is an important diagnostic tool for many heart electrophysiology-related cases. AECG covers a wide spectrum of devices and applications. At the core of these devices and applications are the algorithms responsible for signal conditioning, ECG beat detection and classification, and event detections. Over the years, there has been huge progress for algorithm development and implementation thanks to great efforts by researchers, engineers, and physicians, alongside the rapid development of electronics and signal processing, especially machine learning (ML). The current efforts and progress in machine learning fields are unprecedented, and many of these ML algorithms have also been successfully applied to AECG applications. This review covers some key AECG applications of ML algorithms. However, instead of doing a general review of ML algorithms, we are focusing on the central tasks of AECG and discussing what ML can bring to solve the key challenges AECG is facing. The center tasks of AECG signal processing listed in the review include signal preprocessing, beat detection and classification, event detection, and event prediction. Each AECG device/system might have different portions and forms of those signal components depending on its application and the target, but these are the topics most relevant and of greatest concern to the people working in this area.

[1]  Jimeng Sun,et al.  Opportunities and Challenges in Deep Learning Methods on Electrocardiogram Data: A Systematic Review , 2020, ArXiv.

[2]  W.J. Tompkins,et al.  Neural-network-based adaptive matched filtering for QRS detection , 1992, IEEE Transactions on Biomedical Engineering.

[3]  R. L. Avitia,et al.  Bayesian Classification Models for Premature Ventricular Contraction Detection on ECG Traces , 2018, Journal of healthcare engineering.

[4]  Jiann-Shiun Yuan,et al.  ECG Arrhythmia Classification Using Transfer Learning from 2- Dimensional Deep CNN Features , 2018, 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS).

[5]  Teck Wee Chua,et al.  Type-2 Fuzzy System for ECG Arrhythmic Classification , 2007, 2007 IEEE International Fuzzy Systems Conference.

[6]  Karol Antczak,et al.  A Generative Adversarial Approach To ECG Synthesis And Denoising , 2020, ArXiv.

[7]  Marc Peter Deisenroth,et al.  Deep Reinforcement Learning: A Brief Survey , 2017, IEEE Signal Processing Magazine.

[8]  M Sabarimalai Manikandan,et al.  Efficient and robust ventricular tachycardia and fibrillation detection method for wearable cardiac health monitoring devices. , 2016, Healthcare technology letters.

[9]  L. Lhotska,et al.  Comparison of seven approaches for holter ECG clustering and classification , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[10]  R. Ebrahimpour,et al.  Improving ECG Classification Accuracy Using an Ensemble of Neural Network Modules , 2011, PloS one.

[11]  Joel Xue,et al.  Method to Annotate Arrhythmias by Deep Network , 2018, 2018 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData).

[12]  Qiao Li,et al.  AF classification from a short single lead ECG recording: The PhysioNet/computing in cardiology challenge 2017 , 2017, 2017 Computing in Cardiology (CinC).

[13]  P. Rubel,et al.  Improvement of QRS boundary recognition by means of unsupervised learning , 2003, Computers in Cardiology, 2003.

[14]  Tahir Bekiryazici,et al.  ECG Compression method based on convolutional autoencoder and discrete wavelet transform , 2020, 2020 28th Signal Processing and Communications Applications Conference (SIU).

[15]  Study of repolarization heterogeneity and electrocardiographic morphology with a modeling approach. , 2008, Journal of electrocardiology.

[16]  Omar Abuzaghleh,et al.  Stages-Based ECG Signal Analysis From Traditional Signal Processing to Machine Learning Approaches: A Survey , 2020, IEEE Access.

[17]  Wojciech Zareba,et al.  2017 ISHNE-HRS expert consensus statement on ambulatory ECG and external cardiac monitoring/telemetry. , 2017, Heart rhythm.

[18]  Kuanquan Wang,et al.  Quick detection of QRS complexes and R-waves using a wavelet transform and K-means clustering. , 2015, Bio-medical materials and engineering.

[19]  Steffen Leonhardt,et al.  Fusing QRS Detection, Waveform Features, and Robust Interval Estimation with a Random Forest to Classify Atrial Fibrillation. , 2017 .

[20]  Aggelos K. Katsaggelos,et al.  Detection of atrial fibrillation in ECG hand-held devices using a random forest classifier , 2017, 2017 Computing in Cardiology (CinC).

[21]  Guoliang Tao,et al.  Algorithm for Clustering Analysis of ECG Data , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[22]  Stanislaw Osowski,et al.  ECG beat recognition using fuzzy hybrid neural network , 2001, IEEE Trans. Biomed. Eng..

[23]  Yüksel Özbay,et al.  A fuzzy clustering neural network architecture for classification of ECG arrhythmias , 2006, Comput. Biol. Medicine.

[24]  Yukio Ozawa,et al.  Signal‐Averaged P‐Wave Analysis of Normal Controls and Patients with Paroxysmal Atrial Fibrillation: A Study in Gender Differences, Age Dependence, and Reproducibility , 2002, Clinical cardiology.

[25]  Alexander Binder,et al.  Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution , 2020, 2020 25th International Conference on Pattern Recognition (ICPR).

[26]  Feng Lin,et al.  A stacked contractive denoising auto-encoder for ECG signal denoising , 2016, Physiological measurement.

[27]  Steven C. H. Hoi,et al.  Online Learning: A Comprehensive Survey , 2018, Neurocomputing.

[28]  P. Song,et al.  Deep-learning-based risk stratification for mortality of patients with acute myocardial infarction , 2019, PloS one.

[29]  Fabiola De Marco,et al.  Classification of Premature Ventricular Contraction Using Deep Learning , 2020, 2020 Computing in Cardiology.

[30]  Corneliu T. C. Arsene,et al.  Complex Deep Learning Models for Denoising of Human Heart ECG signals , 2019, ArXiv.

[31]  Wisnu Jatmiko,et al.  Investigation Reinforcement Learning Method for R-Wave Detection on Electrocardiogram Signal , 2019, 2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI).

[32]  M. Malik,et al.  Precision of QT Interval Measurement by Advanced Electrocardiographic Equipment , 2006, Pacing and clinical electrophysiology : PACE.

[33]  Bartlomiej Sniezynski,et al.  Electrocardiogram Quality Assessment with Autoencoder , 2021, ICCS.

[34]  Tomáš Vičar,et al.  Deep-Learning Premature Contraction Localization in 12-lead ECG From Whole Signal Annotations , 2020, 2020 Computing in Cardiology.

[35]  Kipp W. Johnson,et al.  Deep Neural Networks Can Predict New-Onset Atrial Fibrillation From the 12-Lead ECG and Help Identify Those at Risk of Atrial Fibrillation–Related Stroke , 2021, Circulation.

[36]  Corneliu T. C. Arsene,et al.  Design of Deep Convolutional Neural Network Architectures for Denoising Electrocardiographic Signals , 2020, 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB).

[37]  Fayzan F. Chaudhry,et al.  Deep learning and the electrocardiogram: review of the current state-of-the-art , 2021, Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology.

[38]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[39]  J. Xue.  Robust QT Interval Estimation—From Algorithm to Validation , 2009, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[40]  Bin He,et al.  Localization of Origins of Premature Ventricular Contraction by Means of Convolutional Neural Network From 12-Lead ECG , 2018, IEEE Transactions on Biomedical Engineering.

[41]  Danilo Pani,et al.  The History and Challenges of SCP-ECG: The Standard Communication Protocol for Computer-Assisted Electrocardiography , 2021, Hearts.

[42]  G. Deco,et al.  Investigating the underlying Markovian dynamics of ECG rhythms by information flow , 2001 .

[43]  Qiuzhen Xue,et al.  Late potential recognition by artificial neural networks , 1997, IEEE Transactions on Biomedical Engineering.

[44]  Paulo Félix,et al.  Arrhythmia classification from the abductive interpretation of short single-lead ECG records , 2017, 2017 Computing in Cardiology (CinC).

[45]  Dongping Du,et al.  Automatic Classification of Heartbeats Using ECG Signals via Higher Order Hidden Markov Model , 2020, 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE).

[46]  Heba Ismail,et al.  ECG Monitoring Systems: Review, Architecture, Processes, and Key Challenges , 2020, Sensors.

[47]  Pu Wang,et al.  LSTM-Based Auto-Encoder Model for ECG Arrhythmias Classification , 2020, IEEE Transactions on Instrumentation and Measurement.

[48]  Nino Isakadze,et al.  How useful is the smartwatch ECG? , 2019, Trends in cardiovascular medicine.

[49]  Huazhong Yang,et al.  Patient-specific ECG classification based on recurrent neural networks and clustering technique , 2017, 2017 13th IASTED International Conference on Biomedical Engineering (BioMed).

[50]  Fei Wang,et al.  A novel ECG signal compression method using spindle convolutional auto-encoder , 2019, Comput. Methods Programs Biomed..

[51]  Habib Hajimolahoseini,et al.  Ecg Delineation for Qt Interval Analysis Using an Unsupervised Learning Method , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[52]  N.V. Thakor,et al.  Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection , 1991, IEEE Transactions on Biomedical Engineering.

[53]  F. Plesinger,et al.  Automatic Detection of Atrial Fibrillation and Other Arrhythmias in Holter ECG Recordings using PQRS Morphology and Rhythm Features. , 2017 .

[54]  Krishna Kant Singh,et al.  ECG Beat Classifiers: A Journey from ANN To DNN , 2020 .

[55]  Brian Young,et al.  Added value of new acute coronary syndrome computer algorithm for interpretation of prehospital electrocardiograms. , 2004, Journal of electrocardiology.

[56]  Michael A Rosenberg,et al.  Use of a Noninvasive Continuous Monitoring Device in the Management of Atrial Fibrillation: A Pilot Study , 2012, Pacing and clinical electrophysiology : PACE.

[57]  Mehmet Korürek,et al.  A new arrhythmia clustering technique based on Ant Colony Optimization , 2008, J. Biomed. Informatics.

[58]  U. Rajendra Acharya,et al.  An efficient compression of ECG signals using deep convolutional autoencoders , 2018, Cognitive Systems Research.

[59]  Xiao-dong Chen,et al.  Automatic Premature Ventricular Contraction Detection Using Deep Metric Learning and KNN , 2021, Biosensors.

[60]  Masoud Daneshtalab,et al.  A review on deep learning methods for ECG arrhythmia classification , 2020, Expert Syst. Appl. X.

[61]  Safdar Mahmood,et al.  A Survey on Machine Learning Approaches to ECG Processing , 2020, 2020 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA).

[62]  M. Awal,et al.  An adaptive level dependent wavelet thresholding for ECG denoising , 2014 .

[63]  Bernadette Dorizzi,et al.  ECG signal analysis through hidden Markov models , 2006, IEEE Transactions on Biomedical Engineering.

[64]  Yasin Kaya,et al.  Feature selection using genetic algorithms for premature ventricular contraction classification , 2015, 2015 9th International Conference on Electrical and Electronics Engineering (ELECO).

[65]  Annisa Darmawahyuni,et al.  An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique , 2019, Applied Sciences.

[66]  Bing Zhou,et al.  Intelligent Analysis of Premature Ventricular Contraction Based on Features and Random Forest , 2019, Journal of healthcare engineering.

[67]  P. Noseworthy,et al.  A comprehensive artificial intelligence–enabled electrocardiogram interpretation program , 2020, Cardiovascular Digital Health Journal.

[68]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[69]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[70]  Ming Liu,et al.  ECG signal enhancement based on improved denoising auto-encoder , 2016, Eng. Appl. Artif. Intell..

[71]  Abdulhamit Subasi,et al.  Effect of Multiscale PCA De-noising in ECG Beat Classification for Diagnosis of Cardiovascular Diseases , 2015, Circuits Syst. Signal Process..

[72]  Keerthi Ram,et al.  ECGNet: Deep Network for Arrhythmia Classification , 2018, 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA).

[73]  A. Koski.  Modelling ECG signals with hidden Markov models , 1996, Artif. Intell. Medicine.

[74]  R. Erbel,et al.  Prediction of atrial fibrillation in patients with cardiac dysfunctions: P wave signal-averaged ECG and chemoreflexsensitivity in atrial fibrillation. , 2007, Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology.

[75]  Taghi M. Khoshgoftaar,et al.  Survey on deep learning with class imbalance , 2019, J. Big Data.

[76]  Carsten Peterson,et al.  Clustering ECG complexes using Hermite functions and self-organizing maps , 2000, IEEE Trans. Biomed. Eng..

[77]  Antonis A. Armoundas,et al.  T-Wave Alternans as an Arrhythmic Risk Stratifier: State of the Art , 2013, Current Cardiology Reports.

[78]  N. Yu. Zolotykh,et al.  Electrocardiogram Generation and Feature Extraction Using a Variational Autoencoder , 2020, ArXiv.

[79]  A. Mitchell,et al.  Effectiveness of a single lead AliveCor electrocardiogram application for the screening of atrial fibrillation , 2020, Medicine.

[80]  T. Conrad,et al.  Transfer learning for ECG classification , 2021, Scientific Reports.

[81]  O. Dössel,et al.  Machine learning enables noninvasive prediction of atrial fibrillation driver location and acute pulmonary vein ablation success using the 12-lead ECG , 2021, Cardiovascular digital health journal.

[82]  I Romero,et al.  PCA and ICA applied to noise reduction in multi-lead ECG , 2011, 2011 Computing in Cardiology.

[83]  ECG Guided Automated Diagnostic Intervention of Cardiac Arrhythmias with Extra-Cardiac Noise Detection using Neural Network , 2021, 2021 7th International Conference on Optimization and Applications (ICOA).

[84]  Yoshua Bengio,et al.  Object Recognition with Gradient-Based Learning , 1999, Shape, Contour and Grouping in Computer Vision.

[85]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[86]  Thomas B. Schön,et al.  Automatic diagnosis of the 12-lead ECG using a deep neural network , 2020, Nature Communications.

[87]  Mohamed Amine Chikh,et al.  Discrete hidden Markov model classifier for premature ventricular contraction detection , 2015 .

[88]  Karol Antczak,et al.  Deep Recurrent Neural Networks for ECG Signal Denoising , 2018, ArXiv.

[89]  Benjamin A. Teplitzky,et al.  Deep learning for comprehensive ECG annotation , 2020, Heart rhythm.

[90]  Patrick W. Johnson,et al.  Artificial Intelligence-Enabled Assessment of the Heart Rate Corrected QT Interval Using a Mobile Electrocardiogram Device. , 2021, Circulation.