Preprocessing Method for Performance Enhancement in CNN-Based STEMI Detection From 12-Lead ECG

ST elevation myocardial infarction (STEMI) is an acute life-threatening disease. It shows a high mortality risk when a patient is not timely treated within the golden time, prompt diagnosis with limited information such as electrocardiogram (ECG) is crucial. However, previous studies among physicians and paramedics have shown that the accuracy of STEMI diagnosis by the ECG is not sufficient. Thus, we propose a detecting algorithm based on a convolutional neural network (CNN) for detecting the STEMI on 12-lead ECG in order to support physicians, especially in an emergency room. We mostly focus on enhancing the detecting performance using a preprocessing technique. First, we reduce the noise of ECG using a notch filter and high-pass filter. We also segment pulses from ECG to focus on the ST segment. We use 96 normal and 179 STEMI records provided by Seoul National University Bundang Hospital (SNUBH) for the experiment. The sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve are increased from 0.685, 0.350, and 0.526 to 0.932, 0.896, and 0.943, respectively, depending on the preprocessing technique. As our result shows, the proposed method is effective to enhance STEIM detecting performance. Also, the proposed algorithm would be expected to help timely and the accurate diagnosis of STEMI in clinical practices.

[1]  Hin Wai Lui,et al.  Multiclass classification of myocardial infarction with convolutional and recurrent neural networks for portable ECG devices , 2018 .

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

[3]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[4]  Mattias Ohlsson,et al.  Detecting acute myocardial infarction in the 12-lead ECG using Hermite expansions and neural networks , 2004, Artif. Intell. Medicine.

[5]  Tapobrata Lahiri,et al.  Analysis of ECG signal by chaos principle to help automatic diagnosis of myocardial infarction , 2009 .

[6]  N. Altman.  An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression , 1992 .

[7]  M.A. Mneimneh,et al.  An adaptive kalman filter for removing baseline wandering in ECG signals , 2006, 2006 Computers in Cardiology.

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

[9]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

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

[11]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[12]  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.

[13]  U. Rajendra Acharya,et al.  Automated characterization and classification of coronary artery disease and myocardial infarction by decomposition of ECG signals: A comparative study , 2017, Inf. Sci..

[14]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[15]  David W. Mortara,et al.  A Deep Learning Approach to Examine Ischemic ST Changes in Ambulatory ECG Recordings , 2018, AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science.

[16]  Maarten L. Simoons,et al.  The third universal definition of myocardial infarction , 2013 .

[17]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

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

[19]  Pei-Chann Chang,et al.  A Hybrid System with Hidden Markov Models and Gaussian Mixture Models for Myocardial Infarction Classification with 12-Lead ECGs , 2009, 2009 11th IEEE International Conference on High Performance Computing and Communications.

[20]  Dirk P. Kroese,et al.  Why the Monte Carlo method is so important today , 2014 .

[21]  Vinod Kumar,et al.  Detection of myocardial infarction in 12 lead ECG using support vector machine , 2018, Appl. Soft Comput..

[22]  François Charpillet,et al.  A Multi-HMM Approach to ECG Segmentation , 2006, 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI'06).

[23]  J. Mair,et al.  A decision tree for the early diagnosis of acute myocardial infarction in nontraumatic chest pain patients at hospital admission. , 1995, Chest.

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

[25]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[26]  Xu Wang,et al.  Noise Reduction in ECG Signal Based on Adaptive Wavelet Transform , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[27]  Celia Shahnaz,et al.  Denoising of ECG signals based on noise reduction algorithms in EMD and wavelet domains , 2012, Biomed. Signal Process. Control..

[28]  Mohammad Bagher Shamsollahi,et al.  Multiadaptive Bionic Wavelet Transform: Application to ECG Denoising and Baseline Wandering Reduction , 2007, EURASIP J. Adv. Signal Process..

[29]  Nils Strodthoff,et al.  Detecting and interpreting myocardial infarction using fully convolutional neural networks , 2018, Physiological measurement.

[30]  I. M. Spaans,et al.  7 Het bepalen van de kwaliteit van de circulatie , 2010 .

[31]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[32]  Kurt S. Hoffmayer,et al.  Physician Accuracy in Interpreting Potential ST‐Segment Elevation Myocardial Infarction Electrocardiograms , 2013, Journal of the American Heart Association.

[33]  L. Gallo.  Cardiovascular Disease , 1995, GWUMC Department of Biochemistry Annual Spring Symposia.

[34]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[35]  G Daniel,et al.  Real-time 3D vectorcardiography: an application for didactic use , 2007 .

[36]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[37]  U. Rajendra Acharya,et al.  Automated Diagnosis of Myocardial Infarction ECG Signals Using Sample Entropy in Flexible Analytic Wavelet Transform Framework , 2017, Entropy.

[38]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[39]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[40]  Bosko Bojovic,et al.  Detection of Acute Myocardial Infarction from serial ECG using multilayer support vector machine , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

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

[42]  Olle Pahlm,et al.  ST-segment deviation analysis of the admission 12-lead electrocardiogram as an aid to early diagnosis of acute myocardial infarction with a cardiac magnetic resonance imaging gold standard. , 2007, Journal of the American College of Cardiology.

[43]  Vili Podgorelec,et al.  Decision trees , 2018, Encyclopedia of Database Systems.