Automatic arrhythmia detection based on time and time–frequency analysis of heart rate variability
Introduction
Arrhythmia is a collective term for any cardiac rhythm that deviates from normal sinus rhythm. Arrhythmia may be due to a disturbance in impulse formation or conduction, or both, but it is not always an irregular heart activity [1]. Respiratory sinus arrhythmia is a natural periodic variation in RR-intervals, corresponding to respiratory activity. Impulse formation may be sinus or ectopic, the rhythm regular or irregular and the heart rate fast, normal or slow [2], [3]. Therefore, the detection of abnormal cardiac rhythms and automatic discrimination from the normal heart activity became an important task for clinical reasons. Most of the studies address the detection and identification of life threatening arrhythmias and specifically ventricular and atrial fibrillation and ventricular tachycardia. Various detection algorithms have been proposed, such as the sequential hypothesis testing [4], the multiway sequential hypothesis testing [5], the threshold-crossing intervals [6], the auto-correlation function [6], the VF-filter [6] and algorithms based on neural-networks [7], [8], [9]. Time–frequency (t–f) analysis [10] and wavelet analysis [11], [12] have also been used. Recent approaches utilize complexity measure [13] and multifractal analysis combined with a fuzzy Kohonen neural network [14].
Heart rate variability (HRV) refers to the beat-to-beat heart rate alterations. HRV believed to be a good marker of the individual's health condition and heart diseases [15]. Therefore, HRV analysis became a critical tool in cardiology for the diagnosis of heart diseases. Time domain analysis of RR-intervals includes calculation of several common statistical indices [16], [17] and graphical representation of the RR-interval duration signal [18], [19]. Frequency analysis provides the power spectrum density (PSD) of the RR-interval duration signal using Fourier transform and autoregressive techniques [20], [21], [22], [23], [24], [25]. t–f analysis is based on the use of short time Fourier transform (STFT), time–frequency distributions (TFDs) and wavelet analysis [10], [11], [12] of the RR-interval duration signal. Other approaches for the HRV analysis include methods from nonlinear mathematics and chaos theory, such as fractal [26], [27] and approximate entropy [27] analysis.
More specifically in the t–f analysis Wigner-Ville (WV) distribution [28], [29] and improved forms of WV, such as pseudo Wigner-Ville (PWV) [30], [31], [32], [33] and smoothed pseudo Wigner-Ville (SPWV) [34], [35], [36], discrete Fourier transform and selective discrete Fourier transform [37], [38], [39], [40], cone shaped kernel distribution [10], Choi-Williams distribution [41] and other exponential distributions [42] have been used.
In this paper we explore time and t–f analysis of the RR-interval duration signal in order to detect arrhythmic segments in ECGs [43]. Selected features from the time domain and t–f analysis are extracted. Several combinations of those features are used for training a set of neural networks. The decision is finally obtained using decision rules.
Section snippets
Materials and methods
Our analysis is carried out in four stages. First a preprocessing procedure is used to extract the tachograms from the ECGs. The tachograms are segmented into small segments. Each segment contains 32 RR-intervals. In the second stage time domain or t–f methods are applied to extract the corresponding features. In the third stage the extracted features are used for training a set of neural networks. In the forth stage detection of arrhythmic segments is carried out using decision rules which are
Results
The corresponding sensitivity and specificity for arrhythmic segment detection for each neural network are computed. The results for sensitivity and specificity, for the 63 neural networks trained with time feature combinations and the 19 neural networks trained with t–f features, are reported in Table 4a and b, respectively. The results for a single neural network are not satisfactory (average sensitivity and specificity: 74 and 72% for neural networks trained with time features and 74 and 78%
Discussion–conclusions
We have developed an automatic procedure for the detection of arrhythmias using heart rate features. The outcome of the method is the classification of the ECG signal segments as “normal” or “arrhythmic”. The method is based on time analysis and t–f analysis features. If time features are chosen their combination lead us to 63 neural networks. If t–f analysis is followed then we result into 19 neural networks. We have proven that a single neural network does not offer satisfactory results in
Acknowledgements
The authors are grateful to Professor D. Sideris, Professor A. Likas and Professor N. Galatsanos for useful comments and suggestions.
References (55)
- et al.
Predicting coronary disease risk based on short-term RR-interval measurements: a neural network approach
Artif. Intell. Med.
(1999) - et al.
Real time spectral analysis of HRV signals: an interactive and user-friendly PC system
Comput. Methods Programs Biomed.
(1998) - et al.
Postural tachycardia syndrome: time frequency mapping
J. Auton. Nerv. Syst.
(1996) - et al.
Time–frequency mapping of R–R interval during complex partial seizures of temporal lobe origin
J. Auton. Nerv. Syst.
(1999) - et al.
Time–frequency spectral analysis of heart rate variability during induction of general anaesthesia
Br. J. Anaesth.
(1997) - et al.
Time–frequency distribution of heart rate variability below 0.05 Hz by Wigner-Ville spectral analysis in congestive heart failure patients
Med. Eng. Phys.
(1997) - et al.
Time–frequency analysis of transient signals-application to cardiovascular control
Physica A
(1998) - et al.
Time–frequency analysis of the RT and RR variability to stratify hypertrophic cardiomyopathy patients
Comput. Biomed. Res.
(2000) - et al.
Arrhythmia—a Guide to Clinical Electrocardiology
(1991) - et al.
Clinical Electrocardiography
(1977)