A topological approach to delineation and arrhythmic beats detection in unprocessed long-term ECG signals

BACKGROUND AND OBJECTIVE Arrhythmias are one of the most common symptoms of cardiac failure. They are usually diagnosed using ECG recordings, particularly long ambulatory recordings (AECG). These recordings are tedious to interpret by humans due to their extent (up to 48 h) and the relative scarcity of arrhythmia events. This makes automated systems for detecting various AECG anomalies indispensable. In this work we present a novel procedure based on topological principles (Morse theory) for detecting arrhythmic beats in AECG. It works in nearly real-time (delayed by a 14 s window), and can be applied to raw (unprocessed) ECG signals. METHODS The procedure is based on a subject-specific adaptation of the one-dimensional discrete Morse theory (ADMT), which represents the signal as a sequence of its most important extrema. The ADMT algorithm is applied twice; for low-amplitude, high-frequency noise removal, and for detection of the characteristic waves of individual ECG beats. The waves are annotated using the ADMT algorithm and template matching. The annotated beats are then compared to the adjacent beats with two measures of similarity: the distance between two beats, and the difference in shape between them. The two measures of similarity are used as inputs to a decision tree algorithm that classifies the beats as normal or abnormal. The classification performance is evaluated with the leave-one-record-out cross-validation method. RESULTS Our approach was tested on the MIT-BIH database, where it exhibited a classification accuracy of 92.73%, a sensitivity of 73.35%, a specificity of 96.70%, a positive predictive value of 88.01%, and a negative predictive value of 95.73%. CONCLUSIONS Compared to related studies, our algorithm requires less preprocessing while retaining the capability to detect and classify beats in almost real-time. The algorithm exhibits a high degree of accuracy in beats detection and classification that are at least comparable to state-of-the-art methods.

[1]  J. Catalano.  Guide to ECG analysis , 1993 .

[2]  Mohammad Hasan Moradi,et al.  Using phase space reconstruction for patient independent heartbeat classification in comparison with some benchmark methods , 2011, Comput. Biol. Medicine.

[3]  L. Khadra,et al.  Detection of life-threatening cardiac arrhythmias using the wavelet transformation , 1997, Medical and Biological Engineering and Computing.

[4]  H Gholam Hosseini,et al.  The comparison of different feed forward neural network architectures for ECG signal diagnosis. , 2006, Medical engineering & physics.

[5]  Andrej Zemva,et al.  Hardware Implementation of a Modified Delay-Coordinate Mapping-Based QRS Complex Detection Algorithm , 2007, EURASIP J. Adv. Signal Process..

[6]  Seyed Kamaledin Setarehdan,et al.  Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal , 2008, Artif. Intell. Medicine.

[7]  Ataollah Ebrahimzadeh,et al.  Detection of premature ventricular contractions using MLP neural networks: A comparative study , 2010 .

[8]  R. Lazzara,et al.  Premature ventricular complex morphology. A marker for left ventricular structure and function. , 1990, Circulation.

[9]  Manuel Blanco-Velasco,et al.  ECG signal denoising and baseline wander correction based on the empirical mode decomposition , 2008, Comput. Biol. Medicine.

[10]  Jean Vuillemin,et al.  A data structure for manipulating priority queues , 1978, CACM.

[11]  Philippe Ravier,et al.  Detection of PVC in ECG signals using fractional linear prediction , 2016, Biomed. Signal Process. Control..

[12]  S. Yoo,et al.  Support Vector Machine Based Arrhythmia Classification Using Reduced Features , 2005 .

[13]  Ali Ghaffari,et al.  ECG arrhythmia recognition via a neuro-SVM-KNN hybrid classifier with virtual QRS image-based geometrical features , 2012, Expert Syst. Appl..

[14]  A. Al-Fahoum,et al.  Combined wavelet transformation and radial basis neural networks for classifying life-threatening cardiac arrhythmias , 1999, Medical & Biological Engineering & Computing.

[15]  Nikola Bogunovic,et al.  Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features , 2011, Artif. Intell. Medicine.

[16]  Willis J. Tompkins,et al.  Quantitative Investigation of QRS Detection Rules Using the MIT/BIH Arrhythmia Database , 1986, IEEE Transactions on Biomedical Engineering.

[17]  Cong Wang,et al.  ECG beat classification via deterministic learning , 2017, Neurocomputing.

[18]  Dimitrios I. Fotiadis,et al.  Automatic arrhythmia detection based on time and time-frequency analysis of heart rate variability , 2004, Comput. Methods Programs Biomed..

[19]  Stanislaw Osowski,et al.  Support vector machine-based expert system for reliable heartbeat recognition , 2004, IEEE Transactions on Biomedical Engineering.

[20]  Aydin Akan,et al.  Evaluation of bagging ensemble method with time-domain feature extraction for diagnosing of arrhythmia beats , 2012, Neural Computing and Applications.

[21]  Heeyoung Kim,et al.  Detection of PVC by using a wavelet-based statistical ECG monitoring procedure , 2017, Biomed. Signal Process. Control..

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

[23]  Juan Pablo Martínez,et al.  Heartbeat Classification Using Feature Selection Driven by Database Generalization Criteria , 2011, IEEE Transactions on Biomedical Engineering.

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

[25]  Abdelfatah Charef,et al.  PVC discrimination using the QRS power spectrum and self-organizing maps , 2009, Comput. Methods Programs Biomed..

[26]  Kup-Sze Choi,et al.  Heartbeat classification using disease-specific feature selection , 2014, Comput. Biol. Medicine.

[27]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[28]  C. Chiou,et al.  Cardiac arrhythmia diagnosis method using linear discriminant analysis on ECG signals , 2009 .

[29]  Yakup Kutlu,et al.  A multi-stage automatic arrhythmia recognition and classification system , 2011, Comput. Biol. Medicine.

[30]  Adel Belouchrani,et al.  QRS detection based on wavelet coefficients , 2012, Comput. Methods Programs Biomed..

[31]  Peter John Wood,et al.  Ieee Transactions on Pattern Analysis and Machine Intelligence Theory and Algorithms for Constructing Discrete Morse Complexes from Grayscale Digital Images , 2022 .

[32]  Philip de Chazal,et al.  A Patient-Adapting Heartbeat Classifier Using ECG Morphology and Heartbeat Interval Features , 2006, IEEE Transactions on Biomedical Engineering.

[33]  Juha Röning,et al.  Efficient Algorithm for Calculating Similarity between Trajectories Containing an Increasing Dimension , 2006, Artificial Intelligence and Applications.

[34]  Dimitrios I. Fotiadis,et al.  An arrhythmia classification system based on the RR-interval signal , 2005, Artif. Intell. Medicine.

[35]  Shankar Muthu Krishnan,et al.  ECG signal conditioning by morphological filtering , 2002, Comput. Biol. Medicine.

[36]  Gregor Jerse,et al.  Tracking features in image sequences using discrete Morse functions , 2010 .

[37]  Thomas Lewiner,et al.  Applications of Forman's discrete Morse theory to topology visualization and mesh compression , 2004, IEEE Transactions on Visualization and Computer Graphics.

[38]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[39]  Mohammad Bagher Shamsollahi,et al.  Robust Detection of Premature Ventricular Contractions Using a Wave-Based Bayesian Framework , 2010, IEEE Transactions on Biomedical Engineering.

[40]  Xiyu Liu,et al.  A graph clustering technique based on discrete Morse theory , 2011, 2011 6th International Conference on Pervasive Computing and Applications.