QRS feature extraction using linear prediction

ECG signal feature extraction trends in methods and applications

Signal analysis is a domain which is an amalgamation of different processes coming together to form robust pipelines for the automation of data analysis. When applied to the medical world, physiological signals are used. It is becoming increasingly common in today's day and age to be working with very large datasets, on the scale of having thousands of features. This is largely due to the fact that the acquisition of biomedical signals can be taken over multi-hour timeframes, which is another challenge to solve in and of itself. This paper will focus on the electrocardiogram (ECG) signal specifically, and common feature extraction techniques used for digital health and artificial intelligence (AI) applications. Feature extraction is a vital step of biomedical signal analysis. The basic goal of feature extraction is for signal dimensionality reduction and data compaction. In simple terms, this would allow one to represent data with a smaller subset of features; these features could then later be leveraged to be used more efficiently for machine learning and deep learning models for applications, such as classification, detection, and automated applications. In addition, the redundant data in the overall dataset is filtered out as the data is reduced during feature extraction. In this review, we cover ECG signal processing and feature extraction in the time domain, frequency domain, time-frequency domain, decomposition, and sparse domain. We also provide pseudocode for the methods discussed so that they can be replicated by practitioners and researchers in their specific areas of biomedical work. Furthermore, we discuss deep features, and machine learning integration, to complete the overall pipeline design for signal analysis. Finally, we discuss future work that can be innovated upon in the feature extraction domain for ECG signal analysis.

Deep convolutional neural networks based ECG beats classification to diagnose cardiovascular conditions

Medical practitioners need to understand the critical features of ECG beats to diagnose and identify cardiovascular conditions accurately. This would be greatly facilitated by identifying the significant features of frequency components in temporal ECG wave-forms using computational methods. In this study, we have proposed a novel ECG beat classifier based on a customized VGG16-based Convolution Neural Network (CNN) that uses the time-frequency representation of temporal ECG, and a method to identify the contribution of interpretable ECG frequencies when classifying based on the SHapley Additive exPlanations (SHAP) values. We applied our model to the MIT-BIH arrhythmia dataset to classify the ECG beats and to characterise of the beats frequencies. This model was evaluated with two advanced time-frequency analysis methods. Our results indicated that for 2-4 classes our proposed model achieves a classification accuracy of 100% and for 5 classes it achieves a classification accuracy of 99.90%. We have also tested the proposed model using premature ventricular contraction beats from the American Heart Association (AHA) database and normal beats from Lobachevsky University Electrocardiography database (LUDB) and obtained a classification accuracy of 99.91% for the 5-classes case. In addition, SHAP value increased the interpretability of the ECG frequency features. Thus, this model could be applicable to the automation of the cardiovascular diagnosis system and could be used by clinicians.

Energy-Efficient ECG Signal Compression for User Data Input in Cyber-Physical Systems by Leveraging Empirical Mode Decomposition

Human physiological data are naturalistic and objective user data inputs for a great number of cyber-physical systems (CPS). Electrocardiogram (ECG) as a widely used physiological golden indicator for certain human state and disease diagnosis is often used as user data input for various CPS such as medical CPS and human–machine interaction. Wireless transmission and wearable technology enable long-term continuous ECG data acquisition for human–CPS interaction; however, these emerging technologies bring challenges of storing and wireless transmitting huge amounts of ECG data, leading to energy efficiency issue of wearable sensors. ECG signal compression technique provides a promising solution for these challenges by decreasing ECG data size. In this study, we develop the first scheme of leveraging empirical mode decomposition (EMD) on ECG signals for sparse feature modeling and compression and further propose a new ECG signal compression framework based on EMD constructed feature dictionary. The proposed method features in compressing ECG signals using a very limited number of feature bases with low computation cost, which significantly improves the compression performance and energy efficiency. Our method is validated with the ECG data from MIT-BIH arrhythmia database and compared with existing methods. The results show that our method achieves the compression ratio (CR) of up to 164 with the root mean square error (RMSE) of 3.48% and the average CR of 88.08 with the RMSE of 5.66%, which is more than twice of the average CR of the state-of-the-art methods with similar recovering error rate of around 5%. For diagnostic distortion perspective, our method achieves high QRS detection performance with the sensitivity (SE) of 99.8% and the specificity (SP) of 99.6%, which shows that our ECG compression method can preserve almost all the QRS features and have no impact on the diagnosis process. In addition, the energy consumption of our method is only 30% of that of other methods when compared under the same recovering error rate.

ECG Signal Denoising and Features Extraction Using Unbiased FIR Smoothing

Methods of the electrocardiography (ECG) signal features extraction are required to detect heart abnormalities and different kinds of diseases. However, different artefacts and measurement noise often hinder providing accurate features extraction. One of the standard techniques developed for ECG signals employs linear prediction. Referring to the fact that prediction is not required for ECG signal processing, smoothing can be more efficient. In this paper, we employ the p-shift unbiased finite impulse response (UFIR) filter, which becomes smooth by p < 0. We develop this filter to have an adaptive averaging horizon: optimal for slow ECG behaviours and minimal for fast excursions. It is shown that the adaptive UFIR algorithm developed in such a way provides better denoising and suboptimal features extraction in terms of the output signal-noise ratio (SNR). The algorithm is developed to detect durations and amplitudes of the P-wave, QRS-complex, and T-wave in the standard ECG signal map. Better performance of the algorithm designed is demonstrated in a comparison with the standard linear predictor, UFIR filter, and UFIR predictive filter based on real ECG data associated with normal heartbeats.

Improving Remote Health Monitoring: A Low-Complexity ECG Compression Approach

Recent advances in mobile technology have created a shift towards using battery-driven devices in remote monitoring settings and smart homes. Clinicians are carrying out diagnostic and screening procedures based on the electrocardiogram (ECG) signals collected remotely for outpatients who need continuous monitoring. High-speed transmission and analysis of large recorded ECG signals are essential, especially with the increased use of battery-powered devices. Exploring low-power alternative compression methodologies that have high efficiency and that enable ECG signal collection, transmission, and analysis in a smart home or remote location is required. Compression algorithms based on adaptive linear predictors and decimation by a factor B / K are evaluated based on compression ratio (CR), percentage root-mean-square difference (PRD), and heartbeat detection accuracy of the reconstructed ECG signal. With two databases (153 subjects), the new algorithm demonstrates the highest compression performance ( CR = 6 and PRD = 1.88 ) and overall detection accuracy (99.90% sensitivity, 99.56% positive predictivity) over both databases. The proposed algorithm presents an advantage for the real-time transmission of ECG signals using a faster and more efficient method, which meets the growing demand for more efficient remote health monitoring.

From Pacemaker to Wearable: Techniques for ECG Detection Systems

With the alarming rise in the deaths due to cardiovascular diseases (CVD), present medical research scenario places notable importance on techniques and methods to detect CVDs. As adduced by world health organization, technological proceeds in the field of cardiac function assessment have become the nucleus and heart of all leading research studies in CVDs in which electrocardiogram (ECG) analysis is the most functional and convenient tool used to test the range of heart-related irregularities. Most of the approaches present in the literature of ECG signal analysis consider noise removal, rhythm-based analysis, and heartbeat detection to improve the performance of a cardiac pacemaker. Advancements achieved in the field of ECG segments detection and beat classification have a limited evaluation and still require clinical approvals. In this paper, approaches on techniques to implement on-chip ECG detector for a cardiac pacemaker system are discussed. Moreover, different challenges regarding the ECG signal morphology analysis deriving from medical literature is extensively reviewed. It is found that robustness to noise, wavelet parameter choice, numerical efficiency, and detection performance are essential performance indicators required by a state-of-the-art ECG detector. Furthermore, many algorithms described in the existing literature are not verified using ECG data from the standard databases. Some ECG detection algorithms show very high detection performance with the total number of detected QRS complexes. However, the high detection performance of the algorithm is verified using only a few datasets. Finally, gaps in current advancements and testing are identified, and the primary challenge remains to be implementing bullseye test for morphology analysis evaluation.

Identification and annotation of multiple periodic pulse trains using dominant frequency and graph search: Applications in atrial fibrillation rotor detection

Biological signals, such as intracardiac electrograms during atrial fibrillation (AF), can contain multiple periodic components or peaks. We propose a method for identifying individual periodic peak trains in signals containing multiple such periodic sequences. We use dominant frequency-based periodicity detection along with a graph search algorithm to identify the most dominant periodic activation set or peaks of interest. We then remove these peaks and iterate until all periodic sequences are identified. The proposed method is tested on simulated AF intra-cardiac electrograms with periodic activation trains of three distinct frequencies corrupted by noise and complex aperiodic signal features. The method is shown to have high accuracy (up to 100% sensitivity and 100% specificity) in detecting the three individual periodic peak trains. The method has application in biomedical signal analysis, such as detecting the periodic activations of a rotor, amidst other periodic activations during AF.

Classification of ECG heartbeats using nonlinear decomposition methods and support vector machine

Classifying electrocardiogram (ECG) heartbeats for arrhythmic risk prediction is a challenging task due to minute variations in the amplitude, duration and morphology of the ECG signal. In this paper, we propose two feature extraction approaches to classify five types of heartbeats: normal, premature ventricular contraction, atrial premature contraction, left bundle branch block and right bundle branch block. In the first approach, ECG beats are decomposed into intrinsic mode functions (IMFs) using ensemble empirical mode decomposition (EEMD). Later four parameters, namely the sample entropy, coefficient of variation, singular values, and band power of IMFs are extracted as features. In the second approach, the same features are computed from IMFs extracted using an empirical mode decomposition (EMD) algorithm. The features obtained from the two approaches are independently fed to the sequential minimal optimization-support vector machine (SMO-SVM) for classification. We used two arrhythmia databases for our evaluation: MIT-BIH and INCART. We compare the proposed approaches with existing methods using the performance measures given by the average values of (i) specificity, (ii) sensitivity, and (iii) accuracy. The first approach demonstrates significant performance with 98.01% sensitivity, 99.49% specificity, and 99.20% accuracy for the MIT-BIH database and 95.15% sensitivity, 98.37% specificity, and 97.57% accuracy for the INCART database.

QRS complex detection in ECG signals using locally adaptive weighted total variation denoising

The QRS complex is the most prominent feature in the electrocardiogram (ECG), therefore, its detection is required for delineation of other waves and segments in the ECG and derivation of additional clinically useful information. QRS detection is complicated by factors like varying QRS morphologies, noise, artefacts and interference from tall and pointed P- and T-waves. In this paper, we propose a novel technique for QRS detection by preprocessing the ECG using weighted total variation (WTV) denoising. A local estimate of noise in the signal block under consideration is used to determine the regularization parameter in WTV minimization, which determines the amount of smoothing applied. This makes the denoising locally adaptive. The weights are chosen so as to give preference to preservation of QRS complexes over P- and T-waves while smoothing. Thus, the technique can simultaneously reduce the higher frequency noise as well as the lower frequency interference from P- and T-waves, in spite of the fact that they have overlapping spectra with the QRS complexes. The proposed method is evaluated on the MIT-BIH arrhythmia database and gives improved detection accuracy over established and state-of-the-art techniques. The technique has low computational load, therefore, it can be used for fast offline QRS detection in long duration ECG records, as well as real-time QRS detection in block-by-block processing mode. The average values of sensitivity, positive predictivity and detection error rate are 99.90%, 99.88% and 0.23%, for the offline implementation, respectively, and 99.86%, 99.85% and 0.29%, for the real-time mode, respectively.

Efficient ECG Compression and QRS Detection for E-Health Applications

Current medical screening and diagnostic procedures have shifted toward recording longer electrocardiogram (ECG) signals, which have traditionally been processed on personal computers (PCs) with high-speed multi-core processors and efficient memory processing. Battery-driven devices are now more commonly used for the same purpose and thus exploring highly efficient, low-power alternatives for local ECG signal collection and processing is essential for efficient and convenient clinical use. Several ECG compression methods have been reported in the current literature with limited discussion on the performance of the compressed and the reconstructed ECG signals in terms of the QRS complex detection accuracy. This paper proposes and evaluates different compression methods based not only on the compression ratio (CR) and percentage root-mean-square difference (PRD), but also based on the accuracy of QRS detection. In this paper, we have developed a lossy method (Methods III) and compared them to the most current lossless and lossy ECG compression methods (Method I and Method II, respectively). The proposed lossy compression method (Method III) achieves CR of 4.5×, PRD of 0.53, as well as an overall sensitivity of 99.78% and positive predictivity of 99.92% are achieved (when coupled with an existing QRS detection algorithm) on the MIT-BIH Arrhythmia database and an overall sensitivity of 99.90% and positive predictivity of 99.84% on the QT database.

QRS detection using adaptive filters: A comparative study

Electrocardiogram (ECG) is one of the most important physiological signals of human body, which contains important clinical information about the heart. Monitoring of ECG signal is done through QRS detection. In this paper, an improved QRS detection algorithm, based on adaptive filtering principle, has been designed. Enumeration of the effectiveness of various LMS variants used in adaptive filtering based QRS detection algorithm has been done through fidelity parameters like sensitivity and positive predictivity. Whole family of LMS algorithm has been implemented for comparison. Sign-sign LMS, sign error LMS, basic LMS and normalized LMS are re-implemented, while variable leaky LMS, variable step-size LMS, leaky LMS, recursive least squares (RLS), and fractional LMS are novel combination presented in this paper. After analysis of the obtained results, performance of leaky-LMS algorithm is found to be the best with sensitivity, positive predictivity, and processing time of 99.68%, 99.84%, and 0.45s respectively. Reported results are tested and evaluated over MIT/BIH arrhythmia database. Presented study also concludes that the performance of most of the variants gets affected due to low SNR but the Leaky LMS performs better even under heavy noise conditions.

A joint QRS detection and data compression scheme for wearable sensors

This paper presents a novel electrocardiogram (ECG) processing technique for joint data compression and QRS detection in a wireless wearable sensor. The proposed algorithm is aimed at lowering the average complexity per task by sharing the computational load among multiple essential signal-processing tasks needed for wearable devices. The compression algorithm, which is based on an adaptive linear data prediction scheme, achieves a lossless bit compression ratio of 2.286x. The QRS detection algorithm achieves a sensitivity (Se) of 99.64% and positive prediction (+P) of 99.81% when tested with the MIT/BIH Arrhythmia database. Lower overall complexity and good performance renders the proposed technique suitable for wearable/ambulatory ECG devices.

Sequential Markov chain Monte Carlo filter with simultaneous model selection for electrocardiogram signal modeling

Constructing statistical models of electrocardiogram (ECG) signals, whose parameters can be used for automated disease classification, is of great importance in precluding manual annotation and providing prompt diagnosis of cardiac diseases. ECG signals consist of several segments with different morphologies (namely the P wave, QRS complex and the T wave) in a single heart beat, which can vary across individuals and diseases. Also, existing statistical ECG models exhibit a reliance upon obtaining a priori information from the ECG data by using preprocessing algorithms to initialize the filter parameters, or to define the user-specified model parameters. In this paper, we propose an ECG modeling technique using the sequential Markov chain Monte Carlo (SMCMC) filter that can perform simultaneous model selection, by adaptively choosing from different representations depending upon the nature of the data. Our results demonstrate the ability of the algorithm to track various types of ECG morphologies, including intermittently occurring ECG beats. In addition, we use the estimated model parameters as the feature set to classify between ECG signals with normal sinus rhythm and four different types of arrhythmia.

Heart detection and diagnosis based on ECG and EPCG relationships

A new design of a system for preliminary detection of defective hearts is proposed which is composed of two subsystems, in which one is based on the relationship between the electrocardiogram (ECG) and phonocardiogram (PCG) signals. The relationship between both signals is determined as an impulse response (h(n)) of a system, where the decision is made based on the linear predictive coding coefficients of a heart's impulse response. The other subsystem uses a phase space approach, in which the mean squared error between the distance vectors of the phase space of the normal heart and abnormal heart is judged by the likelihood ratio test (Λ) value, on which the decision is made. The advantage of the proposed system is that a heart's diagnosis system based on the ECG and EPCG signals can lead to high performance heart diagnostics.

Analysis of unpredictable components within QRS complex using a finite-impulse-response prediction model for the diagnosis of patients with ventricular tachycardia

This study proposes a finite-impulse-response (FIR) prediction model to analyze the unpredictable intra-QRS potentials (UIQP) for identifying ventricular tachycardia patients with high-risk ventricular arrhythmias. The simulation study shows that a QRS complex including abnormal intra-QRS potentials (AIQP) has a higher UIQP and UIQP-to-QRS ratio in comparison with one without AIQP. The clinical results demonstrate that the mean UIQP-to-QRS ratios of VT patients in leads X, Y and Z were significantly larger than those of the normal subjects, and the linear and logical combination of UIQP-to-QRS ratios and ventricular late potential parameters can enhance diagnosis performance for VT patients.

Long-term ECG signal feature extraction

This paper proposes a cepstrum coefficient method applying the dynamic time warping technique to extract the feature vectors from long-term ECG signals. Utilizing this method, one can identify the characteristics hidden in an ECG signal; and then classify the signal as well as diagnose the abnormalities. To evaluate this method, the Normal and PACED BEAT data from the MIT/BIH database are used. The results show that the proposed method successfully extracts the corresponding feature vectors, distinguishes the difference and classifies both signals.

ECG Beat Classification Using Mirrored Gauss Model

Accurate electrocardiogram (ECG) beat classification is essential for automated detection of arrhythmias. A novel classification algorithm of the ECG beats, applying Mirrored Gauss Model (MGM) had been proposed in this paper. The MGM has strong morphological representation ability for QRS complex waves using curve fitting. With the MGM, the width of QRS complex wave could be extracted and applied to ECG beat classification easily, effectively and automatically. It was proved by experiment carrying out using all of ECG records in MIT-BIH Arrhythmia Database that the MGM is a promising algorithm for ECG beat classification. The whole classification accuracy is 93.93% for normal beats and 93.94% for premature ventricular contraction (PVC) beats.

Code excited linear prediction codec for electrocardiogram

In this paper we propose a CELP ECG codec for medical telemetry. The encoding algorithm is based on CODE-EXCITED LINEAR PREDICTION (CELP). The general framework proposed is: QRS detection, calculation of LPC parameter, generation of residual error signal, codebook generation, MSE (mean square error) search. The codebook is generated for residual error. The indices of the codebook and corresponding LPC parameters are transmitted where the minimum MSE occurs. A replica of the transmitter codebook is present at the receiver. Corresponding to the received index value residual error coefficients are retrieved from the receiver codebook. The ECG signal is reconstructed from the retrieved code word.

Modeling QRS Complex in dECG

It is proposed to model the derivative of electrocardiogram (ECG) signal, which we refer to as dECG, instead of the ECG signal. It is shown that the QRS complex in the dECG signal can be represented in the frequency domain by an all-pole model of appropriate order, the coefficients of the model being determined using the covariance method of linear prediction applied over an analysis interval that includes the QRS complex and that is centered about the R-peak. Modeling of dECG, instead of ECG, gives a better spectral representation of the QRS complex.

Detection of the QRS complex by linear prediction

The electrocardiogram (ECG) represents the electrical activity of the heart. It is characterized by its recurrent or periodic behaviour with each beat. Each recurrence is composed of a wave sequence consisting of P, QRS and T-waves, where the most characteristic wave set is the QRS complex. In this paper, we have developed an algorithm for detection of the QRS complex. The algorithm consists of several steps: signal-to-noise enhancement, linear prediction for ECG signal analysis, nonlinear transform, moving window integrator, centre-clipping transformation and QRS detection. Linear prediction determines the coefficients of a forward linear predictor by minimizing the prediction error by a least-square approach. The residual error signal obtained after processing by the linear prediction algorithm has very significant properties which will be used to localize and detect QRS complexes. The detection algorithm is tested on ECG signals from the universal MIT-BIH arrhythmia database and compared with the Pan and Tompkins QRS detection method. The results we obtain show that our method performs better than this method. Our algorithm results in fewer false positives and fewer false negatives.

Cardiac arrhythmia classification using autoregressive modeling

BACKGROUND

Computer-assisted arrhythmia recognition is critical for the management of cardiac disorders. Various techniques have been utilized to classify arrhythmias. Generally, these techniques classify two or three arrhythmias or have significantly large processing times. A simpler autoregressive modeling (AR) technique is proposed to classify normal sinus rhythm (NSR) and various cardiac arrhythmias including atrial premature contraction (APC), premature ventricular contraction (PVC), superventricular tachycardia (SVT), ventricular tachycardia (VT) and ventricular fibrillation (VF).

METHODS

AR Modeling was performed on ECG data from normal sinus rhythm as well as various arrhythmias. The AR coefficients were computed using Burg's algorithm. The AR coefficients were classified using a generalized linear model (GLM) based algorithm in various stages.

RESULTS

AR modeling results showed that an order of four was sufficient for modeling the ECG signals. The accuracy of detecting NSR, APC, PVC, SVT, VT and VF were 93.2% to 100% using the GLM based classification algorithm.

CONCLUSION

The results show that AR modeling is useful for the classification of cardiac arrhythmias, with reasonably high accuracies. Further validation of the proposed technique will yield acceptable results for clinical implementation.

A new interpretation of nonlinear energy operator and its efficacy in spike detection

Nonlinear energy operator (NEO) gives the estimate of energy content of a linear oscillator. This has been used to quantify the AM-FM modulating signals present in a sinusoid. In this paper, we give a new interpretation of NEO and extend its use in stochastic signals. We show that NEO accentuates the high-frequency content. This instantaneous nature of NEO and its very low computational burden make it an ideal tool for spike detection. The efficacy of the proposed method has been tested with simulated signals as well as with real electroencephalograms (EEG's).

Designing better adaptive sampling algorithms for ECG Holter systems

Let psi be any adaptive sampling algorithm that can run in real time on a tapeless multichannel electrocardiogram (ECG) Holter system. Simple methods which can significantly improve psi's fidelity are described and their results are compared in this paper. It is shown that by adding some simple tests to psi, the signals reconstructed by psi can be improved as much as 5.45 dB. It is also shown that under the same data rate, a good data compressor with slowly sampled input ECG is preferable to a bad data compressor with highly sampled input ECG.

Spike detection in biomedical signals using midprediction filter

Spikes such as QRS complex in ECG, epileptic seizures in EEG, fine crackles in vesicular sound and glottal closure instants in voiced sound are of diagnostic importance. Various methods of spike detection use the amplitude and frequency characteristics of the spikes. Because of the high frequency content, the spikes appear in the error signal when a linear prediction filtering scheme is used. The authors use the method of midprediction filtering for the detection of the spikes. In this method, the present sample is predicted as a weighted average of p recent past and p immediate future samples. The symmetrical nature of midprediction causes the spikes to appear in the error signal with their original basewidths. This can help in improving the reliability of spike detection, as both the amplitude and the duration of the spike can be considered as decision making parameters. It is observed that the high frequency gain of the midprediction filter is higher compared to the high frequency gain of the LPC or endprediction filter. As a result, this method works better than linear prediction for the detection of spikes.

Classification of cardiac arrhythmias using fuzzy ARTMAP

We have investigated the QRS complex, extracted from electrocardiogram (ECG) data, using fuzzy adaptive resonance theory mapping (ARTMAP) to classify cardiac arrhythmias. Two different conditions have been analyzed: normal and abnormal premature ventricular contraction (PVC). Based on MIT/BIH database annotations, cardiac beats for normal and abnormal QRS complexes were extracted from this database, scaled, and Hamming windowed, after bandpass filtering, to yield a sequence of 100 samples for each ORS segment. From each of these sequences, two linear predictive coding (LPC) coefficients were generated using Burg's maximum entropy method. The two LPC coefficients, along with the mean-square value of the QRS complex segment, were utilized as features for each condition to train and test a fuzzy ARTMAP neural network for classification of normal and abnormal PVC conditions. The test results show that the fuzzy ARTMAP neural network can classify cardiac arrhythmias with greater than 99% specificity and 97% sensitivity.

A dynamic Fourier series for the compression of ECG using FFT and adaptive coefficient estimation

In this article, a new ECG data compression technique is proposed. The method relies on modelling quasi-periodic ECG signals as a dynamic Fourier series. Fourier coefficients are continuously estimated using either an FFT algorithm or the adaptive least mean square algorithm. Results from simulated normal and pathological ECGs are presented and discussed. The merits of each of the above two methods are also illustrated. Furthermore, a comparison with other compression techniques is also discussed.

Arrhythmia recognition strategies and hardware decisions for the implantable cardioverter-defibrillator--a review

The avoidance of inappropriate shocks from the implantable cardioverter-defibrillator (ICD), together with its need to apply antitachycardia pacing to either atria or ventricles, demands considerable sophistication in the design of algorithms to interpret electrical or other cardiac signals in real-time. Methods based on rate and using single short-gap bipolar leads lack discrimination. Right ventricular electrogram morphology algorithms offer improvement but no universal algorithm exists; however, for any given patient an optimum algorithm of this type might be found. One improvement would be to provide atrial information in addition, by employing more than one electrode or a long-gap single bipolar lead. Alternatively, transducer signals could be included, once their efficacy and reliability have been improved. A different approach would be to use the much more sophisticated algorithms at present being tried with surface electrocardiograms. Integrated Circuit technology is reaching the point where this could be done but the requirement for exceptionally high reliability means that special system structures, such as a Memory Intensive Computer Architecture, may be required. When decisions on these approaches are to be made, it must also be remembered that ICDs will soon be implanted and programmed as a routine rather than a highly specialized procedure.

ECG data compression using adaptive Fourier coefficients estimation

In this article, a new ECG data compression technique is proposed. The method relies on modelling quasi-periodic ECG signals as a dynamic Fourier series. Fourier coefficients are continuously estimated using the adaptive least-mean-square algorithm. Results from simulated normal and pathological ECGs are presented and discussed. A comparison with other compression techniques is also discussed.

Ventricular beat classifier using fractal number clustering

A two-stage ventricular beat 'associative' classification procedure is described. The first stage separates typical beats from extrasystoles on the basis of area and polarity rules. At the second stage, the extrasystoles are classified in self-organised cluster formations of adjacent shape parameter values. This approach avoids the use of threshold values for discrimination between ectopic beats of different shapes, which could be critical in borderline cases. A pattern shape feature conventionally called a 'fractal number', in combination with a polarity attribute, was found to be a good criterion for waveform evaluation. An additional advantage of this pattern classification method is its good computational efficiency, which affords the opportunity to implement it in real-time systems.