A novel method for detecting ST segment elevation myocardial infarction on a 12-lead electrocardiogram with a three-dimensional display

Abstract Objective Two main factors affect the accurate diagnosis of myocardial infarction (MI). The first is achieving accuracy in extracting electrocardiogram (ECG) time domain features and the second is proper analysis of the entire 12-lead ECG. ECG contains measurement data that reflect cardiac activity. However, accurate extraction of ECG features to identify cardiac abnormalities is affected by noise that can degrade the robustness of feature extraction. Each lead in the 12-lead ECG provides different information that can help diagnose MI. Although analyzing the entire 12-lead ECG improves accuracy, it is very time-consuming. This study aimed to propose a three-dimensional (3D) ECG method for detecting ST-segment elevation MI (STEMI) and to confirm the efficacy of the 3D ECG method. Methods The leads of the existing 12-lead ECG were categorized into limb lead and chest lead groups and reconstructed them in a 3D format using a 3D display method. We extracted new features from the 3D ECG plane and evaluated their ability to detect STEMI based on new features using the K-nearest neighbor classifier. Results The 3D ECG detected STEMI with 96.37% accuracy. Conclusion The proposed 3D ECG method can be easily used to read the entire 12-lead ECG even with the naked eye. Significance This method can detect STEMI by simply using the 3D ECG features, thus eliminating the need to extract features such as the ST segment via complicated calculation processes.

[1]  G. Lindsay,et al.  Detection of postoperative myocardial ischemia by bedside ST-segment analysis in coronary artery bypass graft patients. , 1998, Journal of cardiothoracic and vascular anesthesia.

[2]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[3]  Fred S Apple,et al.  Third universal definition of myocardial infarction , 2012 .

[4]  D. Paterson,et al.  ECG diagnosis of acute ischaemia and infarction: past, present and future. , 2006, QJM : monthly journal of the Association of Physicians.

[5]  Myoungho Lee,et al.  Adaptive threshold method for the peak detection of photoplethysmographic waveform , 2009, Comput. Biol. Medicine.

[6]  M. Cutler,et al.  Cardiac electrical remodeling in health and disease. , 2011, Trends in pharmacological sciences.

[7]  A. Guyton,et al.  Text book of medical physiology , 2013 .

[8]  Fan Li,et al.  A novel electrocardiogram parameterization algorithm and its application in myocardial infarction detection , 2015, Comput. Biol. Medicine.

[9]  Mark D. Huffman,et al.  Heart disease and stroke statistics--2013 update: a report from the American Heart Association. , 2013, Circulation.

[10]  Hao Wang,et al.  Multiple-feature-branch convolutional neural network for myocardial infarction diagnosis using electrocardiogram , 2018, Biomed. Signal Process. Control..

[11]  Michael G. Strintzis,et al.  ECG pattern recognition and classification using non-linear transformations and neural networks: A review , 1998, Int. J. Medical Informatics.

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

[13]  U. Rajendra Acharya,et al.  Application of Empirical Mode Decomposition (EMD) for Automated Detection of epilepsy using EEG signals , 2012, Int. J. Neural Syst..

[14]  V. Roger,et al.  Epidemiology of myocardial infarction. , 2007, The Medical clinics of North America.

[15]  O. Borst,et al.  Targeted antiplatelet therapy: novel treatment options for ischaemic heart disease. , 2018, European heart journal.

[16]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[17]  M. Das,et al.  Significance of a Fragmented QRS Complex Versus a Q Wave in Patients With Coronary Artery Disease , 2006, Circulation.

[18]  Iñaki Romero,et al.  Comparative study of algorithms for ECG segmentation , 2017, Biomed. Signal Process. Control..

[19]  Samarendra Dandapat,et al.  Multiscale Energy and Eigenspace Approach to Detection and Localization of Myocardial Infarction , 2015, IEEE Transactions on Biomedical Engineering.

[20]  U. Rajendra Acharya,et al.  Frontal Plane Vectorcardiograms: Theory and Graphics Visualization of Cardiac Health Status , 2010, Journal of Medical Systems.

[21]  A. Bays de Luna,et al.  The 12-Lead ECG in ST Elevation Myocardial Infarction , 2007 .

[22]  U. Rajendra Acharya,et al.  Classification of myocardial infarction with multi-lead ECG signals and deep CNN , 2019, Pattern Recognit. Lett..

[23]  U. Rajendra Acharya,et al.  Automated detection and localization of myocardial infarction using electrocardiogram: a comparative study of different leads , 2016, Knowl. Based Syst..

[24]  U. Rajendra Acharya,et al.  Current methods in electrocardiogram characterization , 2014, Comput. Biol. Medicine.

[25]  Ralf Bousseljot,et al.  Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet , 2009 .

[26]  K. Ong,et al.  An automated ECG classification system based on a neuro-fuzzy system , 2000, Computers in Cardiology 2000. Vol.27 (Cat. 00CH37163).

[27]  Muhammad Arif,et al.  Detection and Localization of Myocardial Infarction using K-nearest Neighbor Classifier , 2012, Journal of Medical Systems.

[28]  Marco Valgimigli,et al.  2017 ESC Guidelines for the management of acute myocardial infarction in patients presenting with ST-segment elevation: The Task Force for the management of acute myocardial infarction in patients presenting with ST-segment elevation of the European Society of Cardiology (ESC). , 2018, European heart journal.

[29]  I. Menown,et al.  Optimizing the initial 12-lead electrocardiographic diagnosis of acute myocardial infarction. , 2000, European heart journal.

[30]  E E Eddleman,et al.  Computer analysis of the orthogonal electrocardiogram and vectorcardiogram in 1,002 patients with myocardial infarction. , 1971, American heart journal.

[31]  Li Sun,et al.  ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection , 2012, IEEE Transactions on Biomedical Engineering.

[32]  M. Schalij,et al.  Position of ST-deviation measurements relative to the J-point: Impact for ischemia detection. , 2017, Journal of electrocardiology.

[33]  P. Boyden,et al.  Electrical remodeling in ischemia and infarction. , 1999, Cardiovascular research.

[34]  O Pahlm,et al.  Panoramic display of the orderly sequenced 12-lead ECG. , 1994, Journal of Electrocardiology.

[35]  Y. Birnbaum,et al.  High-risk ECG patterns in ACS--need for guideline revision. , 2013, Journal of electrocardiology.

[36]  Huihua Kenny Chiang,et al.  A new 3-D display method for 12-lead ECG , 2001, IEEE Transactions on Biomedical Engineering.

[37]  K. M. Lewis,et al.  Sensible Analysis of the 12-Lead ECG , 2000 .

[38]  H V Pipberger,et al.  Computer analysis of the orthogonal electrocardiogram and vectorcardiogram in 939 cases with hypertensive cardiovascular disease. , 1973, American heart journal.

[39]  Madhuchhanda Mitra,et al.  A Rough-Set-Based Inference Engine for ECG Classification , 2006, IEEE Transactions on Instrumentation and Measurement.

[40]  B. Williams,et al.  Paramedic Identification of Electrocardiograph J-Point and ST-Segments , 2008, Prehospital and Disaster Medicine.

[41]  Pedro David Arini,et al.  Assessment of delayed ventricular activation after myocardial infarction , 2019, Biomed. Signal Process. Control..

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

[43]  Andrew C Oehler,et al.  QRS‐T Angle: A Review , 2014, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[44]  Todd T Schlegel,et al.  When deriving the spatial QRS-T angle from the 12-lead electrocardiogram, which transform is more Frank: regression or inverse Dower? , 2010, Journal of electrocardiology.

[45]  C. Chakraborty,et al.  An Integrated ECG Feature Extraction Scheme Using PCA and Wavelet Transform , 2009, 2009 Annual IEEE India Conference.

[46]  Alistair A. Young,et al.  Atlas-Based Quantification of Cardiac Remodeling Due to Myocardial Infarction , 2014, PloS one.

[47]  D. Atar,et al.  ESC Guidelines for the Management of Acute Myocardial Infarction in Patients Presenting With ST-Segment Elevation , 2013 .

[48]  U. Rajendra Acharya,et al.  Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals , 2017, Inf. Sci..

[49]  T. Tamura,et al.  Formal Design Methods for Reliable Computer-Aided Diagnosis: A Review , 2012, IEEE Reviews in Biomedical Engineering.

[50]  J. Leung,et al.  Automated electrocardiograph ST segment trending monitors: accuracy in detecting myocardial ischemia. , 1998 .

[51]  David G. Stork,et al.  Pattern Classification , 1973 .

[52]  Changyu Shen,et al.  Fragmented Wide QRS on a 12-Lead ECG: A Sign of Myocardial Scar and Poor Prognosis , 2008, Circulation. Arrhythmia and electrophysiology.

[53]  D. Altman,et al.  Statistics Notes: Diagnostic tests 1: sensitivity and specificity , 1994 .

[54]  A. Goldberger.  Clinical Electrocardiography: A Simplified Approach , 1977 .

[55]  U. Rajendra Acharya,et al.  ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform , 2013, Biomed. Signal Process. Control..

[56]  Philip de Chazal,et al.  Automatic classification of heartbeats using ECG morphology and heartbeat interval features , 2004, IEEE Transactions on Biomedical Engineering.

[57]  L S Dreifus,et al.  Diagnostic accuracy of a 15-lead hybrid computer-aided electrocardiographic system. , 1973, European journal of cardiology.

[58]  T. Jernberg,et al.  Delay From First Medical Contact to Primary PCI and All‐Cause Mortality: A Nationwide Study of Patients With ST‐Elevation Myocardial Infarction , 2014, Journal of the American Heart Association.