Neural-network-based adaptive matched filtering for QRS detection

We have developed an adaptive matched filtering algorithm based upon an artificial neural network (ANN) for QRS detection. We use an ANN adaptive whitening filter to model the lower frequencies of the ECG which are inherently nonlinear and nonstationary. The residual signal which contains mostly higher frequency QRS complex energy is then passed through a linear matched filter to detect the location of the QRS complex. We developed an algorithm to adaptively update the matched filter template from the detected QRS complex in the ECG signal itself so that the template can be customized to an individual subject. This ANN whitening filter is very effective at removing the time-varying, nonlinear noise characteristic of ECG signals. Using this novel approach, the detection rate for a very noisy patient record in the MIT/BIH arrhythmia database is 99.5%, which compares favorably to the 97.5% obtained using a linear adaptive whitening filter and the 96.5% achieved with a bandpass filtering method.     

On detecting the presence of fetal R-wave using the moving averagedmagnitude difference algorithm

An efficient algorithm detecting the presence of a fetal QRS complex is presented. The proposed fetal QRS detection method computes the averaged magnitude of the difference between the fetal ECG signal and the reference signal to detect the fetal QRS event. The detected fetal QRS complexes are exponentially averaged to generate the template signal which can track the slowly varying shape of the fetal ECG signal. As an effort to obtain improved detection performances, two approaches of normalizing the fetal ECG signal and the template are considered.     

QRS slopes for detection and characterization of myocardial ischemia.

In this study, the upward I(US) and downward I(DS) slopes of the QRS complex are proposed as indices for quantifying ischemia-induced electrocardiogram (ECG) changes. Using ECG recordings acquired before and during percutaneous transluminal coronary angioplasty (PTCA), it is found that the QRS slopes are considerably less steep during artery occlusion, in particular for I(DS). With respect to ischemia detection, the slope indices outperform the often used high-frequency index (defined as the root mean square (rms) of the bandpass-filtered QRS signal for the frequency band 150-250 Hz) as the mean relative factors of change are much larger for I(US) and I(DS) than for the high-frequency index (6.9 and 7.3 versus 3.7). The superior performance of the slope indices is equally valid when other frequency bands of the high-frequency index are investigated (the optimum one is found to be 125-175 Hz). Employing a simulation model in which the slopes of a template QRS are altered by different techniques, it is found that the slope changes observed during PTCA are mostly due to a widening of the QRS complex or a decrease of its amplitudes, but not a reduction of its high-frequency content or a combination of this and the previous effects. It is concluded that QRS slope information can be used as an adjunct to the conventional ST segment analysis in the monitoring of myocardial ischemia.     

An approach to cardiac arrhythmia analysis using hidden Markov models

This paper describes a new approach to ECG arrhythmia analysis based on "hidden Markov modeling" (HMM), a technique successfully used since the mid-1970's to model speech waveforms for automatic speech recognition. Many ventricular arrhythmias can be classified by detecting and analyzing QRS complexes and determining R-R intervals. Classification of supraventricular arrhythmias, however, often requires detection of the P wave in addition to the QRS complex. The hidden Markov modeling approach combines structural and statistical knowledge of the ECG signal in a single parametric model. Model parameters are estimated from training data using an iterative, maximum likelihood reestimation algorithm. Initial results suggest that this approach may provide improved supraventricular arrhythmia analysis through accurate representation of the entire beat including the P wave.     

Estimation of QRS complex power spectra for design of a QRS filter

We present power spectral analysis of ECG waveforms as well as isolated QRS complexes and episodes of noise and artifact. The power spectral analysis shows that the QRS complex could be separated from other interfering signals. A bandpass filter that maximizes the signal (QRS complex)-to-noise (T-waves, 60 Hz, EMG, etc.) ratio would be of use in many ECG monitoring instruments. We calculate the coherence function and, from that, the signal-to-noise ratio. Upon carrying out this analysis on experimentaly obtained ECG data, we observe that a bandpass filter with a center frequency of 17 Hz and a Q of 5 yields the best signal-to-noise ratio.     

基于生成对抗网络的动态心电信号QRS波检测

心电信号分析是预防心血管疾病的重要举措,QRS波的精确检测不仅是心电信号处理的关键步骤且对心率计算和异常情况分析具有重要作用.针对动态心电信号存在信号质量差或异常节奏波形导致常用QRS波检测方法精度较低的问题,本文提出了 一种基于生成对抗网络新型QRS波检测算法.该算法以Pix2Pix网络为基础,生成网络采用U-Net...     

Computer analysis of the electrocardiogram during esophageal pacingcardiac stress

It has been estimated that 15 to 30% of patients with suspected or known coronary artery disease are unable to perform an adequate exercise stress test due to a variety of reasons such as obesity, poor physical condition, claudication, etc. Transesophageal atrial pacing has been proposed as a noninvasive alternative for inducing cardiac stress in patients who cannot exercise. Although computer analysis is commonly employed to analyze the electrocardiogram (ECG) during the conventional exercise stress test, the surface ECG recorded during transesophageal atrial pacing is contaminated with large pacing artifacts which confound beat identification by standard computer software. We report the development of a robust signal processing algorithm for interpretation of the surface ECG during transesophageal atrial pacing stress. The algorithm employs novel schemes using both linear and nonlinear transformations to detect and differentiate between the pacing artifact and QRS complex even in difficult situations where the pacing artifact is in proximity to or superimposed on the QRS complex. The algorithm uses sophisticated logic for automatic recognition of sustained capture. It subsequently calculates beat-by-beat and average (over five beats) ST segment amplitude and slope. The algorithm also reports the instantaneous heart rate, RR interval, pace-to-R interval, R-wave amplitude, and estimated sinus node recovery time upon loss of sustained capture. The limitations of present exercise ECG computer methods in processing the ECG during transesophageal atrial pacing stress are evaluated and significantly improved performance by our algorithm is demonstrated.     

Applications of adaptive filtering to ECG analysis: noisecancellation and arrhythmia detection

Several adaptive filter structures are proposed for noise cancellation and arrhythmia detection. The adaptive filter essentially minimizes the mean-squared error between a primary input, which is the noisy ECG, and a reference input, which is either noise that is correlated in some way with the noise in the primary input or a signal that is correlated only with ECG in the primary input. Different filter structures are presented to eliminate the diverse forms of noise: baseline wander, 60 Hz power line interference, muscle noise, and motion artifact. An adaptive recurrent filter structure is proposed for acquiring the impulse response of the normal QRS complex. The primary input of the filter is the ECG signal to be analyzed, while the reference input is an impulse train coincident with the QRS complexes. This method is applied to several arrhythmia detection problems: detection of P-waves, premature ventricular complexes, and recognition of conduction block, atrial fibrillation, and paced rhythm.     

QRS feature extraction using linear prediction

This communication proposes a method called linear prediction (a high performant technique in digital speech processing) for analyzing digital ECG signals. There are several significant properties indicating that ECG signals have an important feature in the residual error signal obtained after processing by Durbin's linear prediction algorithm. This communication also indicates that the prediction order need not be more than two for fast arrhythmia detection. The ECG signal classification puts an emphasis on the residual error signal. For each ECG's QRS complex, the feature for recognition is obtained from a nonlinear transformation which transforms every residual error signal to a set of three states pulse-code train relative to the original ECG signal. The pulse-code train has the advantage of easy implementation in digital hardware circuits to achieve automated ECG diagnosis. The algorithm performs very well in feature extraction in arrhythmia detection. Using this method, our studies indicate that the PVC (premature ventricular contraction) detection has at least a 92 percent sensitivity for MIT/BIH arrhythmia database.     

Wavelet transform-based QRS complex detector

In this paper, we describe a QRS complex detector based on the dyadic wavelet transform (Dy WT) which is robust to time-varying QRS complex morphology and to noise. We design a spline wavelet that is suitable for QRS detection. The scales of this wavelet are chosen based on the spectral characteristics of the electrocardiogram (ECG) signal. We illustrate the performance of the Dy WT-based QRS detector by considering problematic ECG signals from the American Heart Association (AHA) data base. Seventy hours of data was considered. We also compare the performance of Dy WT-based QRS detector with detectors based on Okada, Hamilton-Tompkins, and multiplication of the backward difference algorithms. From the comparison, results we observed that although no one algorithm exhibited superior performance in all situations, the Dy WT-based detector compared well with the standard techniques. For multiform premature ventricular contractions, bigeminy, and couplets tapes, the Dy WT-based detector exhibited excellent performance.     

基于小波和扩展卡尔曼的心电检测

文中将小波变换和扩展卡尔曼滤波器相结合,利用小波变换多尺度多分辨的特点,将心电信号进行分解。然后对心电信号在各尺度上进行扩展卡尔曼滤波。最后在扩展卡尔曼滤波的输出结果上进行QRS波形检测。文中方法经MIT-BIH心电数据库检验,QRS波Se（探测灵敏度）在99.40%以上,同时,QRS＋P（正探测率）在99.39%以上,提高了心电信号检测的正确率。     

Extraction of fetal electrocardiogram using adaptive neuro-fuzzy inference systems

In this paper, we investigate the use of adaptive neuro-fuzzy inference systems (ANFIS) for fetal electrocardiogram (FECG) extraction from two ECG signals recorded at the thoracic and abdominal areas of the mother's skin. The thoracic ECG is assumed to be almost completely maternal (MECG) while the abdominal ECG is considered to be composite as it contains both the mother's and the fetus' ECG signals. The maternal component in the abdominal ECG signal is a nonlinearly transformed version of the MECG. We use an ANFIS network to identify this nonlinear relationship, and to align the MECG signal with the maternal component in the abdominal ECG signal. Thus, we extract the FECG component by subtracting the aligned version of the MECG signal from the abdominal ECG signal. We validate our technique on both real and synthetic ECG signals. Our results demonstrate the effectiveness of the proposed technique in extracting the FECG component from abdominal signals of very low maternal to fetal signal-to-noise ratios. The results also show that the technique is capable of extracting the FECG even when it is totally embedded within the maternal QRS complex.     

基于小波变换的QRS波群检测

提出了一种基于小波多分辨分析的算法,对心电信号进行特征提取和识别。通过小波变换对常规心电图信号进行分解去噪和特征提取,并利用动态自适应阈值和删除多检点,补偿漏检点对QRS波检测进行优化。实验结果表明该方法在QRS波形不失真的情况下,提高了一部分MIT-BIH数据库信号中QRS波识别的准确率,并且对于较低准确率的心电信号的原因进行了分析。     

Criteria for Optimal Averaging of Cardiac Signals

The averaging process is modeled as a linear system whose low-pass filter characteristics are determined by the degree in temporal misalignment of signals. Assuming the errors in temporal alignment of successive cardiac cycles are random, then the model transfer function is equivalent to the probability density function. The response of the model to a step input is equivalent to the probability distribution function, which can be readily quantified. To validate the model, a high resolution ECG amplifier and QRS recognition system was constructed that synchronizes a step input with a point on the QRS. Design criteria for optimal amplification, filtering, and triggering of the ECG are determined. Test of the model reveals a close correspondence between observed and predicted step responses. From the average step response, the recording fidelity of any average can be determined-rapidly while the alignment is adjusted for optimal precision. Using ECG signals from patients, our model system demonstrates that alignment errors can both add and subtract signal components. Methods for estimating the extent of signal distortion induced by averaging as well as criteria for minimizing it are presented.     

Nonstationary harmonic modeling for ECG removal in surface EMG signals

We present a compact approach for mitigating the presence of electrocardiograms (ECG) in surface electromyographic (EMG) signals by means of time-variant harmonic modeling of the cardiac artifact. Heart rate and QRS complex variability, which often account for amplitude and frequency time variations of the ECG, are simultaneously captured by a set of third-order constant-coefficient polynomials modulating a stationary harmonic basis in the analysis window. Such a characterization allows us to significantly suppress ECG from the mixture by preserving most of the EMG signal content at low frequencies (less than 20?Hz). Moreover, the resulting model is linear in parameters and the least-squares solution to the corresponding linear system of equations efficiently provides model parameter estimates. The comparative results suggest that the proposed method outperforms two reference methods in terms of the EMG preservation at low frequencies.     

基于形态滤波的心电信号基线矫正算法

基线矫正是心电(ECG)信号预处理中的一个重要步骤.本文提出了一个基于形态滤波的ECG信号基线矫正算法.首先,对原始输入ECG信号进行基于相同结构元素的形态开闭-闭开滤波,抑制其中的QRS波群;然后,采用两个不同宽度的结构元素,对去除QRS波群后的ECG信号进行广义形态开-闭滤波,分离出基线漂移信号;最后,用原始ECG信号减去估计出的基漂信号,得到经过基线矫正的ECG信号.仿真实验与实际应用结果表明,本文方法不仅可以有效去除ECG信号中的基漂干扰,而且较好地保持了ECG信号的原有特征形态,处理效果明显优于以往算法.     

Detection of ECG characteristic points using wavelet transforms

An algorithm based on wavelet transforms (WT's) has been developed for detecting ECG characteristic points. With the multiscale feature of WT's, the QRS complex can be distinguished from high P or T waves, noise, baseline drift, and artifacts. The relation between the characteristic points of ECG signal and those of modulus maximum pairs of its WT's is illustrated. By using this method, the detection rate of QRS complexes is above 99.8% for the MIT/BIH database and the P and T waves can also be detected, even with serious base line drift and noise     

A new technique for line interference monitoring and reduction inbiopotential amplifiers

It has been reported that power line frequency must be accurately known if line interference is to be accurately subtracted from the output of a bipotential amplifier. In this paper, hardware developed to record the common mode line frequency signal on the body simultaneously with the ECG lead signals of a 15-channel computerized cardiograph is described. This interference reference signal and its quadrature, obtained by software, are linearly combined to be subtracted from any one of the channels to reduce line interference to below the quantization level of the 12 b A/D converter. Coefficients of the linear combination are estimated using linear regression which is applied to the relatively isoelectric regions of the data, excluding the QRS complexes. Since the interference reference signal is available in real time, simultaneously with the ECG signals, another software approach is also adopted in which an adaptive interference reduction algorithm is used to cope with varying interference. A recursive least squares algorithm with forgetting factor is used to update the coefficients. This updating mechanism is gated by the output of a software QRS detector. Results regarding the performance of both the off-line and the adaptive algorithms are given, and the effects of nonisoelectric portions of the ECG lead signals on the estimation of the coefficients are quantified.     

High-Frequency Electrocardiogram Analyzer

We have developed a microprocessor-based analyzer for processing the high-frequency electrocardiogram. It has a signal band-width of 500 Hz, five times that of the standard clinical ECG. The device is programmed to isolate QRS complexes, to compute their first derivatives, and to dilate the time base so that the high frequency ECG's and their derivatives can be recorded on a restricted-bandwidth hard copy device such as a strip chart recorder or ECG machine. Also, the analyzer interfaces directly to a laboratory computer system for additional signal processing.