Early detection of coronary artery disease in patients studied with magnetocardiography: An automatic classification system based on signal entropy

We propose an automatic system for the classification of coronary artery disease (CAD) based on entropy measures of MCG recordings. Ten patients with coronary artery narrowing ≥ or ≤ 50% were categorized by a multilayer perceptron (MLP) neural network based on Linear Discriminant Analysis (LDA). Best results were obtained with MCG at rest: 99% sensitivity, 97% specificity, 98% accuracy, 96% and 99% positive and negative predictive values for single heartbeats. At patient level, these results correspond to a correct classification of all patients. The classifier's suitability to detect CAD-induced changes on the MCG at rest was validated with surrogate data.

[1]  Raimund Erbel,et al.  Predictive value of the magnetocardiogram for location of regional ischemia or infarction as detected by quantitative analysis of the coronary arteriogram , 2007 .

[2]  Sergio Cerutti,et al.  Comparison of entropy-based regularity estimators: application to the fetal heart rate signal for the identification of fetal distress , 2006, IEEE Transactions on Biomedical Engineering.

[3]  Jukka Nenonen,et al.  Recording locations in multichannel magnetocardiography and body surface potential mapping sensitive for regional exercise-induced myocardial ischemia , 2001, Basic Research in Cardiology.

[4]  D. Grönemeyer,et al.  Quantification of cardiac magnetic field orientation during ventricular de- and repolarization , 2008, Physics in medicine and biology.

[5]  P. Hill,et al.  Resting Magnetocardiography Predicts 3‐Year Mortality in Patients Presenting with Acute Chest Pain without ST Segment Elevation , 2008, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[6]  S M Pincus,et al.  Approximate entropy as a measure of system complexity. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Philip Langley,et al.  Comparison of magnetocardiography and electrocardiography: a study of automatic measurement of dispersion of ventricular repolarization. , 2006, 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.

[8]  Silvia Comani,et al.  Performance comparison of six independent components analysis algorithms for fetal signal extraction from real fMCG data , 2007, Physics in medicine and biology.

[9]  L Oikarinen,et al.  ST-segment level and slope in exercise-induced myocardial ischemia evaluated with body surface potential mapping. , 2001, The American journal of cardiology.

[10]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[11]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[12]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[13]  Hyukchan Kwon,et al.  Non-invasive magnetocardiography for the early diagnosis of coronary artery disease in patients presenting with acute chest pain. , 2010, Circulation journal : official journal of the Japanese Circulation Society.

[14]  Steven M. Pincus,et al.  A regularity statistic for medical data analysis , 1991, Journal of Clinical Monitoring.

[15]  Akihiko Kandori,et al.  Subtraction Magnetocardiogram for Detecting Coronary Heart Disease , 2010, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[16]  D. Geue,et al.  RELIABILITY OF AUTOMATED DETERMINATION OF QRST TIMES IN ECG AND MCG , 2009 .

[17]  S. Nakatani,et al.  Repolarization Spatial‐Time Current Abnormalities in Patients with Coronary Heart Disease , 2009, Pacing and clinical electrophysiology : PACE.

[18]  David L. Donoho,et al.  Nonlinear Wavelet Methods for Recovery of Signals, Densities, and Spectra from Indirect and Noisy Da , 1993 .

[19]  Jens Haueisen,et al.  Passive vortex currents in magneto- and electrocardiography: comparison of magnetic and electric signal strengths , 2006, Physics in medicine and biology.

[20]  Niels Wessel,et al.  Detection of patients with coronary artery disease using cardiac magnetic field mapping at rest. , 2007, Journal of electrocardiology.

[21]  C. Breathnach.  Magnetism in medicine. , 1983, Irish medical journal.

[22]  Zhonghua Sun,et al.  Diagnostic value of coronary CT angiography with prospective ECG-gating in the diagnosis of coronary artery disease: a systematic review and meta-analysis , 2012, The International Journal of Cardiovascular Imaging.

[23]  A Schirdewan,et al.  Cardiac magnetic field mapping quantified by Kullback–Leibler entropy detects patients with coronary artery disease , 2010, Physiological measurement.

[24]  B. Hailer,et al.  Sensitivity and specificity of magnetocardiography, using computerized classification of current density vectors maps, in ischemic patients with normal ECG and echocardiogram , 2007 .

[25]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[26]  P. Hugenholtz,et al.  Magnetocardiography Predicts Coronary Artery Disease in Patients with Acute Chest Pain , 2005, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[27]  D. Chakrabarti,et al.  A fast fixed - point algorithm for independent component analysis , 1997 .

[28]  Birgit Hailer,et al.  The Value of Magnetocardiography in Patients with and Without Relevant Stenoses of the Coronary Arteries Using an Unshielded System , 2005, Pacing and clinical electrophysiology : PACE.

[29]  Gregor Eiling,et al.  Changes in Dipolar Structure of Cardiac Magnetic Field Maps after ST Elevation Myocardial Infarction , 2011, Annals of noninvasive electrocardiology : the official journal of the International Society for Holter and Noninvasive Electrocardiology, Inc.

[30]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[31]  H. Crijns,et al.  Combined use of exercise electrocardiography, coronary calcium score and cardiac CT angiography for the prediction of major cardiovascular events in patients presenting with stable chest pain. , 2013, International journal of cardiology.

[32]  C. Stein.  Estimation of the Mean of a Multivariate Normal Distribution , 1981 .

[33]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[34]  E. Oja,et al.  Independent Component Analysis , 2001 .

[35]  In-Seon Kim,et al.  Usefulness of magnetocardiogram to detect unstable angina pectoris and non-ST elevation myocardial infarction. , 2009, The American journal of cardiology.

[36]  Pierre Comon.  Independent component analysis - a new concept? signal processing , 1994 .

[37]  Josephine Chen,et al.  Age and Sex Dependent Variations in the Normal Magnetocardiogram Compared with Changes Associated with Ischemia , 2004, Annals of Biomedical Engineering.

[38]  Peter Van Leeuwen,et al.  Identification of patients with coronary artery disease using magnetocardiographic signal analysis / Identifizierung von Patienten mit koronarer Herzkrankheit anhand magnetokardiographischer Signalanalyse , 2006, Biomedizinische Technik. Biomedical engineering.