Shoushui Wei

Determination of Sample Entropy and Fuzzy Measure Entropy Parameters for Distinguishing Congestive Heart Failure from Normal Sinus Rhythm Subjects

Entropy provides a valuable tool for quantifying the regularity of physiological time series and provides important insights for understanding the underlying mechanisms of the cardiovascular system. Before any entropy calculation, certain common parameters need to be initialized: embedding dimension m, tolerance threshold r and time series length N. However, no specific guideline exists on how to determine the appropriate parameter values for distinguishing congestive heart failure (CHF) from normal sinus rhythm (NSR) subjects in clinical application. In the present study, a thorough analysis on the selection of appropriate values of m, r and N for sample entropy (SampEn) and recently proposed fuzzy measure entropy (FuzzyMEn) is presented for distinguishing two group subjects. 44 long-term NRS and 29 long-term CHF RR interval recordings from http://www.physionet.org were used as the non-pathological and pathological data respectively. Extreme (>2 s) and abnormal heartbeat RR intervals were firstly removed from each RR recording and then the recording was segmented with a non-overlapping segment length N of 300 and 1000, respectively. SampEn and FuzzyMEn were performed for each RR segment under different parameter combinations: m of 1, 2, 3 and 4, and r of 0.10, 0.15, 0.20 and 0.25 respectively. The statistical significance between NSR and CHF groups under each combination of m, r and N was observed. The results demonstrated that the selection of m, r and N plays a critical role in determining the SampEn and FuzzyMEn outputs. Compared with SampEn, FuzzyMEn shows a better regularity when selecting the parameters m and r. In addition, FuzzyMEn shows a better relative consistency for distinguishing the two groups, that is, the results of FuzzyMEn in the NSR group were consistently lower than those in the CHF group while SampEn were not. The selections of m of 2 and 3 and r of 0.10 and 0.15 for SampEn and the selections of m of 1 and 2 whenever r (herein, rL = rG = r) are for FuzzyMEn (in addition to setting nL = 3 and nG = 2) were recommended to yield the fine classification results for the NSR and CHF groups.

ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrix

We propose a systematic ECG quality classification method based on a kernel support vector machine (KSVM) and genetic algorithm (GA) to determine whether ECGs collected via mobile phone are acceptable or not. This method includes mainly three modules, i.e., lead-fall detection, feature extraction, and intelligent classification. First, lead-fall detection is executed to make the initial classification. Then the power spectrum, baseline drifts, amplitude difference, and other time-domain features for ECGs are analyzed and quantified to form the feature matrix. Finally, the feature matrix is assessed using KSVM and GA to determine the ECG quality classification results. A Gaussian radial basis function (GRBF) is employed as the kernel function of KSVM and its performance is compared with that of the Mexican hat wavelet function (MHWF). GA is used to determine the optimal parameters of the KSVM classifier and its performance is compared with that of the grid search (GS) method. The performance of the proposed method was tested on a database from PhysioNet/Computing in Cardiology Challenge 2011, which includes 1500 12-lead ECG recordings. True positive (TP), false positive (FP), and classification accuracy were used as the assessment indices. For training database set A (1000 recordings), the optimal results were obtained using the combination of lead-fall, GA, and GRBF methods, and the corresponding results were: TP 92.89%, FP 5.68%, and classification accuracy 94.00%. For test database set B (500 recordings), the optimal results were also obtained using the combination of lead-fall, GA, and GRBF methods, and the classification accuracy was 91.80%.

Modelling Arterial Pressure Waveforms Using Gaussian Functions and Two-Stage Particle Swarm Optimizer

Changes of arterial pressure waveform characteristics have been accepted as risk indicators of cardiovascular diseases. Waveform modelling using Gaussian functions has been used to decompose arterial pressure pulses into different numbers of subwaves and hence quantify waveform characteristics. However, the fitting accuracy and computation efficiency of current modelling approaches need to be improved. This study aimed to develop a novel two-stage particle swarm optimizer (TSPSO) to determine optimal parameters of Gaussian functions. The evaluation was performed on carotid and radial artery pressure waveforms (CAPW and RAPW) which were simultaneously recorded from twenty normal volunteers. The fitting accuracy and calculation efficiency of our TSPSO were compared with three published optimization methods: the Nelder-Mead, the modified PSO (MPSO), and the dynamic multiswarm particle swarm optimizer (DMS-PSO). The results showed that TSPSO achieved the best fitting accuracy with a mean absolute error (MAE) of 1.1% for CAPW and 1.0% for RAPW, in comparison with 4.2% and 4.1% for Nelder-Mead, 2.0% and 1.9% for MPSO, and 1.2% and 1.1% for DMS-PSO. In addition, to achieve target MAE of 2.0%, the computation time of TSPSO was only 1.5u2009s, which was only 20% and 30% of that for MPSO and DMS-PSO, respectively.

Performance analysis of multiscale entropy for the assessment of ECG signal quality

This study explored the performance of multiscale entropy (MSE) for the assessment of mobile ECG signal quality, aiming to provide a reasonable application guideline. Firstly, the MSE for the typical noises, that is, high frequency (HF) noise, low frequency (LF) noise, and power-line (PL) noise, was analyzed.The sensitivity of MSE to the signal to noise ratio (SNR) of the synthetic artificial ECG plus different noises was further investigated. The results showed that the MSE values could reflect content level of various noises contained in the ECG signals. For the synthetic ECG plus LF noise, the MSE was sensitive to SNR within higher range of scale factor. However, for the synthetic ECG plus HF noise, the MSE was sensitive to SNR within lower range of scale factor. Thus, a recommended scale factor range within 5 to 10 was given. Finally, the results were verified on the real ECG signals, which were derived from MIT-BIH Arrhythmia Database and Noise Stress Test Database. In all, MSE could effectively assess the noise level on the real ECG signals, and this study provided a valuable reference for applying MSE method to the practical signal quality assessment of mobile ECG.

Life-threatening false alarm rejection in ICU: using the rule-based and multi-channel information fusion method

False alarm (FA) rates as high as 86% have been reported in intensive care unit monitors. High FA rates decrease quality of care by slowing staff response times while increasing patient burdens and stresses. In this study, we proposed a rule-based and multi-channel information fusion method for accurately classifying the true or false alarms for five life-threatening arrhythmias: asystole (ASY), extreme bradycardia (EBR), extreme tachycardia (ETC), ventricular tachycardia (VTA) and ventricular flutter/fibrillation (VFB). The proposed method consisted of five steps: (1) signal pre-processing, (2) feature detection and validation, (3) true/false alarm determination for each channel, (4) real-time true/false alarm determination and (5) retrospective true/false alarm determination (if needed). Up to four signal channels, that is, two electrocardiogram signals, one arterial blood pressure and/or one photoplethysmogram signal were included in the analysis. Two events were set for the method validation: event 1 for real-time and event 2 for retrospective alarm classification. The results showed that 100% true positive ratio (i.e. sensitivity) on the training set were obtained for ASY, EBR, ETC and VFB types, and 94% for VTA type, accompanied by the corresponding true negative ratio (i.e. specificity) results of 93%, 81%, 78%, 85% and 50% respectively, resulting in the score values of 96.50, 90.70, 88.89, 92.31 and 64.90, as well as with a final score of 80.57 for event 1 and 79.12 for event 2. For the test set, the proposed method obtained the score of 88.73 for ASY, 77.78 for EBR, 89.92 for ETC, 67.74 for VFB and 61.04 for VTA types, with the final score of 71.68 for event 1 and 75.91 for event 2.

Multivariable Fuzzy Measure Entropy Analysis for Heart Rate Variability and Heart Sound Amplitude Variability

Simultaneously analyzing multivariate time series provides an insight into underlying interaction mechanisms of cardiovascular system and has recently become an increasing focus of interest. In this study, we proposed a new multivariate entropy measure, named multivariate fuzzy measure entropy (mvFME), for the analysis of multivariate cardiovascular time series. The performances of mvFME, and its two sub-components: the local multivariate fuzzy entropy (mvFEL) and global multivariate fuzzy entropy (mvFEG), as well as the commonly used multivariate sample entropy (mvSE), were tested on both simulation and cardiovascular multivariate time series. Simulation results on multivariate coupled Gaussian signals showed that the statistical stability of mvFME is better than mvSE, but its computation time is higher than mvSE. Then, mvSE and mvFME were applied to the multivariate cardiovascular signal analysis of R wave peak (RR) interval, and first (S1) and second (S2) heart sound amplitude series from three positions of heart sound signal collections, under two different physiological states: rest state and after stair climbing state. The results showed that, compared with rest state, for univariate time series analysis, after stair climbing state has significantly lower mvSE and mvFME values for both RR interval and S1 amplitude series, whereas not for S2 amplitude series. For bivariate time series analysis, all mvSE and mvFME report significantly lower values for after stair climbing. For trivariate time series analysis, only mvFME has the discrimination ability for the two physiological states, whereas mvSE does not. In summary, the new proposed mvFME method shows better statistical stability and better discrimination ability for multivariate time series analysis than the traditional mvSE method.

A novel encoding Lempel-Ziv complexity algorithm for quantifying the irregularity of physiological time series

BACKGROUND AND OBJECTIVEnThe Lempel-Ziv (LZ) complexity and its variants have been extensively used to analyze the irregularity of physiological time series. To date, these measures cannot explicitly discern between the irregularity and the chaotic characteristics of physiological time series. Our study compared the performance of an encoding LZ (ELZ) complexity algorithm, a novel variant of the LZ complexity algorithm, with those of the classic LZ (CLZ) and multistate LZ (MLZ) complexity algorithms.nnnMETHODS AND RESULTSnSimulation experiments on Gaussian noise, logistic chaotic, and periodic time series showed that only the ELZ algorithm monotonically declined with the reduction in irregularity in time series, whereas the CLZ and MLZ approaches yielded overlapped values for chaotic time series and time series mixed with Gaussian noise, demonstrating the accuracy of the proposed ELZ algorithm in capturing the irregularity, rather than the complexity, of physiological time series. In addition, the effect of sequence length on the ELZ algorithm was more stable compared with those on CLZ and MLZ, especially when the sequence length was longer than 300. A sensitivity analysis for all three LZ algorithms revealed that both the MLZ and the ELZ algorithms could respond to the change in time sequences, whereas the CLZ approach could not. Cardiac interbeat (RR) interval time series from the MIT-BIH database were also evaluated, and the results showed that the ELZ algorithm could accurately measure the inherent irregularity of the RR interval time series, as indicated by lower LZ values yielded from a congestive heart failure group versus those yielded from a normal sinus rhythm group (pu2009<u20090.01).

A Construction Method of Personalized ECG Template and Its Application in Premature Ventricular Contraction Recognition for ECG Mobile Phones

Premature ventricular contraction (PVC) is the most frequent arrhythmia encountered. PVC may occur in health subjects, which is not imminently life-threatening but may require therapy to prevent further problems. So the timely PVC recognition becomes very important for the analy- sis of electrocardiogram (ECG), especially for the remote ECG monitoring using mobile phones. In this paper, a construction method of personalized ECG template and a succeeding PVC recognition method based on template matching were studied. Firstly, we selected 43 ECG recordings from the MIT-BIH arrhythmia database. All recordings were divided into two datasets (DS1 for training and DS2 for testing) and each data- set approximately contains the same proportion of PVC beats. Subsequently, for each recording (30 min length) in DS1, the first 5 min recordings were used to construct the personalized ECG template and the last 25 min recordings were used for the R-wave peaks detection and PVC recognition, where the tem- plate matching method were used. The validity of the proposed methods was tested using DS2. The results showed that: 1) high beat detection accuracy was achieved for both PVC beats and non-PVC beats; 2) the sensitivity and specificity of PVC recognition were 99.11% and 99.96% for the first 5 min re- cordings respectively, 99.17% and 99.43% for the last 25 min recordings respectively. All the proposed methods can be real- time performed and it shows promising for the application of ECG mobile phones.

Comparison of time-domain, frequency-domain and non-linear analysis for distinguishing congestive heart failure patients from normal sinus rhythm subjects

Abstract It is known that patients with congestive heart failure have reduced ability to modulate heart rate in comparison with normal subjects. However, the characteristics of these changes is not well understood. This study therefore investigated the characteristic features of heart rate changes to assess how they differed between both groups. Fifty-two normal sinus rhythm subjects and 18 congestive heart failure patients from the PhysioNet database were studied. Nine common heart rate indices were studied: three time-domain indices (MEAN RR interval, standard deviation of successive RR SDNN, and square root of mean squared differences of successive RR RMSSD), three frequency-domain indices (normalized low-frequency power LFn, normalized high-frequency power HFn, and their ratio LF/HF), and three non-linear indices (vector length index VLI, vector angle index VAI and sample entropy SampEn). Two 5-min segments from every subject, neither of which had any ectopic beat, were analyzed. The statistical differences between the two clinical groups for the first and second segments, and their average were determined for all nine indices. Results showed that there was no significant difference between the two 5-min RR interval segments for any technique. All frequency-domain and non-linear indices, but only one time-domain index (SDNN), were significantly different between subject groups. However, some indices were much more sensitive to the clinical differences than others; with the best performing techniques, one non-linear index VLI and one time domain index SDNN, followed by all three frequency indices of LFn, HFn and LF/HF, and finally two of the other non-linear indices VAI and SampEn. A simple RBF SVM-based classification algorithm gave a good performance for classifying the CHF and NSR subjects. And the mean Se, Sp and Acc of SVM classifier from 10 folds were 91.31%, 90.04% and 90.95% respectively. We have shown that there are characteristic differences in heart rate changes between congestive heart failure and normal sinus rhythm, suggesting characteristic rhythm differences.

A signal quality assessment method for mobile ECG using multiple features and fuzzy support vector machine

A signal quality assessment method for mobile ECG based on fuzzy support vector machines (FSVM) and multi-feature was proposed to help users to determine whether the ECG recordings collected using mobile phone are acceptable or not. The proposed method mainly included two modules: feature extraction and an intelligent classification approach, i.e. a FSVM classifier. First, 27 features derived from the baseline drift, the high or low amplitude, and the power spectrum of ECG were quantized and extracted to serve as the inputs of FSVM classifier. Then grid search (GS) was employed to optimize the parameters (σ, C) for FSVM classifier. Finally, the performance of FSVM classifier was verified by comparing with the results of a kernel SVM (KSVM) classifier. Results showed that for 1,000 training mobile ECG recordings from the set A in PhysioNet/Computing in Cardiology Challenge 2011 database, the proposed FSVM classifier yielded a classification accuracy of 94.50% (vs. 93.90% for the KSVM classifier). For the 500 test mobile ECG recordings from the set B database, classification accuracies were 91.40% for the KSVM classifier vs. 92.00% for the FSVM classifier.