Evaluation of mathematical models for QRS feature extraction and QRS morphology classification in ECG signals

Abstract It is plausible to assume that the component waves in ECG signals constitute a unique human characteristic because morphology and amplitudes of recorded beats are governed by multiple individual factors. According to the best of our knowledge, the issue of automatically classifying different ’identities’ of QRS morphology has not been explored within the literature. This work proposes five alternative mathematical models for representing different QRS morphologies providing the extraction of a set of features related to QRS shape. The technique incorporates mechanisms of combining the mathematical functions Gaussian, Mexican-Hat and Rayleigh probability density function and also a mechanism for clipping the waveform of those functions. The searching for the optimal parameters which minimize the normalized RMS error between each mathematical model and a given QRS search window enables to find an optimal model. Such modeling behaves as a robust alternative for delineating heartbeats, classifying beat morphologies, detecting subtle and anomalous changes, compression of QRS complex windows among others. The validation process evaluates the ability of each model to represent different QRS morphology classes within 159 full ECG signal records from QT database and 584 QRS search windows from MIT-BIH Arrhythmia database. From the experimental results, we rank the winning rates for which each mathematical model best models and also discriminates the most predominant QRS morphologies Rs, rS, RS, qR, qRs, R, rR’s and QS. Furthermore, the average time errors computed for QRS onset and offset locations when using the corresponding winner mathematical models for delineation purposes were, respectively, 12.87 ± 8.5  ms and 1.47 ± 10.06  ms.

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

[2]  P. C. Cortez,et al.  An innovative approach of QRS segmentation based on first-derivative, Hilbert and Wavelet Transforms. , 2012, Medical engineering & physics.

[3]  João Paulo do Vale Madeiro,et al.  Techniques for QRS Complex Detection , 2019, Developments and Applications for ECG Signal Processing.

[4]  Lorenzo Chiari,et al.  A wavelet-based ECG delineation algorithm for 32-bit integer online processing , 2011, Biomedical engineering online.

[5]  Abdelhamid Daamouche,et al.  ECG as a biometric for individual's identification , 2017, 2017 5th International Conference on Electrical Engineering - Boumerdes (ICEE-B).

[6]  Bartosz Proniewski,et al.  Classification of sleep disordered breathing in the evaluation of acoustic sound in correlation with the ECG signal , 2014, Computing in Cardiology 2014.

[7]  Durbadal Mandal,et al.  An Efficient QRS Complex Detection Using Optimally Designed Digital Differentiator , 2018, Circuits, Systems, and Signal Processing.

[8]  P Caminal,et al.  Automatic detection of wave boundaries in multilead ECG signals: validation with the CSE database. , 1994, Computers and biomedical research, an international journal.

[9]  R. Merletti,et al.  Hermite expansions of compact support waveforms: applications to myoelectric signals , 1994, IEEE Transactions on Biomedical Engineering.

[10]  Piotr Augustyniak,et al.  Wearable Patient Home Monitoring Based on ECG and ACC Sensors , 2011 .

[11]  Daejin Park,et al.  Efficient Fiducial Point Detection of ECG QRS Complex Based on Polygonal Approximation , 2018, Sensors.

[12]  P. C. Cortez,et al.  A new approach to QRS segmentation based on wavelet bases and adaptive threshold technique. , 2007, Medical engineering & physics.

[13]  Vincenzo Piuri,et al.  Deep-ECG: Convolutional Neural Networks for ECG biometric recognition , 2019, Pattern Recognit. Lett..

[14]  Li Zhang,et al.  A lightweight QRS detector for single lead ECG signals using a max-min difference algorithm , 2017, Comput. Methods Programs Biomed..

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

[16]  M R Homaeinezhad,et al.  A robust wavelet-based multi-lead Electrocardiogram delineation algorithm. , 2009, Medical engineering & physics.

[17]  Xiao Hu,et al.  Automatic detection of onset and offset of QRS complexes independent of isoelectric segments , 2014 .

[18]  Jean-Marc Vesin,et al.  Extraction of QRS fiducial points from the ECG using adaptive mathematical morphology , 2016, Digit. Signal Process..

[19]  Angelo Brayner,et al.  Classical and Modern Features for Interpretation of ECG Signal , 2019, Developments and Applications for ECG Signal Processing.

[20]  P. C. Cortez,et al.  Evaluating Gaussian and Rayleigh-Based Mathematical Models for T and P-waves in ECG , 2017, IEEE Latin America Transactions.

[21]  P. Laguna,et al.  Adaptive estimation of QRS complex wave features of ECG signal by the hermite model , 2007, Medical and Biological Engineering and Computing.

[22]  P. C. Cortez,et al.  New approach for T-wave peak detection and T-wave end location in 12-lead paced ECG signals based on a mathematical model. , 2013, Medical engineering & physics.

[23]  Olle Pahlm,et al.  A Method for Evaluation of QRS Shape Features Using a Mathematical Model for the ECG , 1981, IEEE Transactions on Biomedical Engineering.

[24]  Victor Hugo C. de Albuquerque,et al.  A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification , 2019, Future Gener. Comput. Syst..

[25]  Raúl Alcaraz,et al.  Application of the phasor transform for automatic delineation of single-lead ECG fiducial points , 2010, Physiological measurement.

[26]  Pablo Laguna,et al.  A wavelet-based ECG delineator: evaluation on standard databases , 2004, IEEE Transactions on Biomedical Engineering.

[27]  L. Sharma,et al.  Novel T-wave Detection Technique with Minimal Processing and RR-Interval Based Enhanced Efficiency , 2019, Cardiovascular Engineering and Technology.

[28]  R. Jane,et al.  Evaluation of an automatic threshold based detector of waveform limits in Holter ECG with the QT database , 1997, Computers in Cardiology 1997.

[29]  J. J. Rieta,et al.  Gaussian modeling of the P-wave morphology time course applied to anticipate paroxysmal atrial fibrillation , 2015, Computer methods in biomechanics and biomedical engineering.

[30]  Eliasz Kantoch.  Technical verification of applying wearable physiological sensors in ubiquitous health monitoring , 2013, Computing in Cardiology 2013.

[31]  Derek Abbott,et al.  Revisiting QRS Detection Methodologies for Portable, Wearable, Battery-Operated, and Wireless ECG Systems , 2014, PloS one.

[32]  Victor Hugo C. de Albuquerque,et al.  Heart Arrhythmia Classification Based on Statistical Moments and Structural Co-occurrence , 2019, Circuits, Systems, and Signal Processing.

[33]  I. Khalil,et al.  ECG biometric recognition in different physiological conditions using robust normalized QRS complexes , 2012, 2012 Computing in Cardiology.

[34]  Yuan-Ting Zhang,et al.  Heartbeats Based Biometric Random Binary Sequences Generation to Secure Wireless Body Sensor Networks , 2018, IEEE Transactions on Biomedical Engineering.

[35]  Ye Li,et al.  A Wearable Context-Aware ECG Monitoring System Integrated with Built-in Kinematic Sensors of the Smartphone , 2015, Sensors.

[36]  João Paulo do Vale Madeiro,et al.  Delineation of QRS Complex: Challenges for the Development of Widely Applicable Algorithms , 2019, Developments and Applications for ECG Signal Processing.

[37]  A. Hasslocher-Moreno,et al.  Development of a risk score to predict sudden death in patients with Chaga's heart disease. , 2015, International journal of cardiology.