摘要
阵发性房颤是一种最为常见的心律失常,发作时心电图主要表现为RR间期绝对不规则以及P波缺失。已有阵发性房颤的自动检测方法仅依赖于心电信号的时域信息,从而使得检测准确率不高。鉴于小波相干分析可以同时展现信号的时域和频域信息,文中提出了一种基于小波相干分析的阵发性房颤自动检测方法。首先,对所有的心电信号预处理;其次,对模板与待测心电信号分别进行小波相干分析得到其小波相干图;进而,计算小波相干值均值、比率和交叉小波相位角方差构成房颤心电特征;最后,将上述特征结合超限学习机完成阵发性房颤的自动检测。文中通过MIT-BIH房颤数据集验证所提算法的有效性与可行性,数值实验结果达到准确率97. 81%,敏感性98. 54%,特异性98. 61%。
Paroxysmal atrial fibrillation( PAF) is a kind of typical arrhythmia,whose characteristics appearing on electrocardiogram( ECG) are two points: RR interval irregularity and P wave absence. Most existing automatic PAF detection methods only rely on the time domain information of ECG signal,so as to bring the low accuracy. In view of that the wavelet coherence analysis can display signal information in both time and frequency domain,this paper proposes an automatic PAF detection method using ECGs based on wavelet coherence analysis. Firstly,ECG signals are preprocessed where denoising,segmenting and template selection are included. Secondly,wavelet coherent maps between the template ECG and the present ECG are drawn according to the wavelet coherence analysis. And then,the mean value of wavelet coherence,the ratio and the variance of cross wavelet phase angle are calculated to be the extracted features. Finally,the features were fed into extreme learning machine( ELM) to achieve the automatic detection of PAF. Performance of the proposed method is verified on MIT-BIH atrial fibrillation database in simulations. The accuracy,sensitivity and specificity of the method reach 97. 81%,98. 54%,and 98. 61%.
引文
[1]NACCARELLI G V,VARKER H,LIN J,et al.Increasing prevalence of atrial fibrillation and flutter in the united states[J].American Journal of Cardiology,2009,104(11):1534-1539.
[2]KAUFMAN E S,WALDO A L.The impact of asymptomatic atrial fibrillation[J].Journal of the American College of Cardiology,2004,43(1):53-54.
[3]MOODY G B,MARK R G.A new method for detection of AF episodes[J].Computers in Cardiology,1997,24:77-80.
[4]DUVERNEY D,GASPOZ J M,PICHOT V,et al.High accuracy of automatic detection of atrial fibrillation using wavelet transform of heart rate intervals[J].Pace-Pacing and Clinical Electroph-ysiology,2002,25(4):457-462.
[5]TATENO K,CLASS L.A method for detection of atrial fibrillation using Rr intervals[J].Computers in Cardiology,2000,27:391-394.
[6]KRAHN A D,MANFREDA J,TATE R B,et al.The nat-url history of atrial fibrillation incidence,risk factors,and prognosis in the manitoba follow-up study[J].American Journal of Medicine,1995,98(5):476-484.
[7]黄超.动态心电图中房颤自动检测算法研究及其临床应用[D].杭州:浙江大学,2013.
[8]ANDRIKOPOULOS G K,DILAVERS P E,RICHTERD J,et al.Increased variance of P wave duration on the electroc-ardiogram distinguishes patient with paroxysmal AF[J].Pacing&Clinical Electrophysiol Pace,2000,23(7):1127-1132.
[9]HARRIS F J.The discrete fourier transform applied to time domain signal processing[J].Communications Magazine IEEE,1982,20(3):13-22.
[10]AVARGEL Y,COHEN I.System identification in the short-time fourier transform domain with crossband filtering[J].IEEE Transactions on Audio Speech&Language Processing,2007,15(4):1305-1319.
[11]ORTIGOSA N,GALBIS A,FERNANDEZ C,et al.Atrial fibrillation classification method for patients with different pharmacological or surgical therapies[C]∥Computing in Cardiology Conference.IEEE,2013:875-878.
[12]白鹏飞,王利,易子川.一种心电图P波提取算法[J].中国医学物理学杂志,2013,30(2):4032-4035.
[13]宋志平,尹继尧,薛艳,等.全球及各地震区带强震活动周期特征[J].地球物理学报,2013,56:188-1876.
[14]GRINSTED A,MOORE J C,JEVREJEVA S.Application of the cross wavetlet transform and wavelet coherence to geophysical time series[J].Nonliner Process Geophys,2004,11:561-566.
[15]MADDEN R A.Further evidence of traveling planetary waves[J].J Atmos Sci,1978,35(9):1605-1618.
[16]刘哲.基于小波相干分析的脑网络构建与分析方法[D].哈尔滨:哈尔滨工业大学,2015.
[17]TORRENCE C,COMPO G P.A practical guide to wavelet analysis[J].Bulletin of the American Meteorological Society,1998,79(1):61-78.
[18]洪灿梅,刘爱莲,刘名扬,等.FIR滤波器与IIR滤波器去噪效果对比研究[J].微型机与应用,2015(21):67-69.
[19]QUIROGA R Q.Single-trial event-related potentials with wavelet denoising:Method and applications[J].International Congress,2005,1278(2):429-432.
[20]HUANG G B,ZHU Q Y,SIEW C K.Extreme learning machine:Theory and applications[J].Neurocomputing,2006,70(1):489-501.
[21]DASH S,CHON K H,LU S,et al.Automatic real time detection of atrial fibrillation[J].Annals of Biomedical Engineering,2009,37(9):1701-1709.
[22]任丛.基于RR间期与稀疏分解的房颤检测方法研究[D].保定:河北大学,2015.
