Jankowski Stanislaw, Szymanski Zbigniew, Piatkowska-Janko Ewa, Oreziak Artur
From Institute of Electronic Systems, Warsaw University of Technology, Warsaw, Poland.
Anadolu Kardiyol Derg. 2007 Jul;7 Suppl 1:112-5.
We present the improved method of recognition of sustained ventricular tachycardia (SVT) based on new filtering technique (FIR), extended signal-averaged electrocardiography (SAECG) description by 9 parameters and the application of support vector machine (SVM) classifier.
The dataset consisted of 376 patients (100 patients with sustained ventricular tachycardia after myocardial infarction (MI) labelled as class SVT+, 176 patients without sustained ventricular tachycardia after MI and 77 healthy persons, 50% of data were left for validation. The analysis of SAECG was performed by 2 types of filtration: low pass four-pole IIR Butterworth filter and FIR filter with Kaiser window. We calculated 3 commonly used SAECG parameters: hfQRS (ms), RMS40 (microV), LAS<40 microV(ms) and 6 new parameters: LAS<25 microV(ms) - duration of the low amplitude <25 microV signals at the end of QRS complex; RMS QRS(microV) - root mean square voltage of the filtered QRS complex; pRMS(microV) - root mean square voltage of the first 40 ms of filtered QRS complex; pLAS(ms) - duration of the low amplitude <40 microV signals in front of QRS complex; RMS t1(microV) - root mean square voltage of the last 10 ms the filtered QRS complex; RMS t2(microV) - root mean square voltage of the last 20 ms the filtered QRS complex. For the recognition of SVT+ class patients we used the SVM with the Gaussian kernel.
The results confirmed good generalization of obtained models. The recognition score (calculated as correct classification/total number of patients) of SVT+patients on data set containing 3 standard parameters (Butterworth filter) is 92.55%. The same score was obtained for data set containing 9 parameters (Butterworth filter). The best score (95.21%) was obtained for data set based on 9 parameters and FIR filter.
Our approach improved risk stratification up to 95% based on SAECG due to the application of FIR filter, 6 new parameters and efficient statistical classifier, the support vector machine.
我们提出一种改进的持续性室性心动过速（SVT）识别方法，该方法基于新的滤波技术（FIR）、通过9个参数扩展信号平均心电图（SAECG）描述以及支持向量机（SVM）分类器的应用。
数据集包括376名患者（100名心肌梗死（MI）后发生持续性室性心动过速的患者标记为SVT +类，176名MI后无持续性室性心动过速的患者和77名健康人，50%的数据留作验证。SAECG分析通过2种滤波类型进行：低通四极IIR巴特沃斯滤波器和带凯泽窗的FIR滤波器。我们计算了3个常用的SAECG参数：hfQRS（毫秒）、RMS40（微伏）、LAS<40微伏（毫秒）以及6个新参数：LAS<25微伏（毫秒）——QRS波群末端低振幅<25微伏信号的持续时间；RMS QRS（微伏）——滤波后QRS波群的均方根电压；pRMS（微伏）——滤波后QRS波群前40毫秒的均方根电压；pLAS（毫秒）——QRS波群前低振幅<40微伏信号的持续时间；RMS t₁（微伏）——滤波后QRS波群最后10毫秒的均方根电压；RMS t₂（微伏）——滤波后QRS波群最后20毫秒的均方根电压。对于SVT +类患者的识别，我们使用了带高斯核的SVM。
结果证实了所获模型具有良好的泛化能力。在包含3个标准参数（巴特沃斯滤波器）的数据集上，SVT +患者的识别分数（计算为正确分类/患者总数）为92.55%。在包含9个参数（巴特沃斯滤波器）的数据集上也获得了相同的分数。基于9个参数和FIR滤波器的数据集获得了最佳分数（95.21%）。
由于应用了FIR滤波器、6个新参数和高效的统计分类器——支持向量机，我们的方法基于SAECG将风险分层提高到了95%。
Zotero 插件