基于语义挖掘的室性心动过速及心室纤颤检测

Detection of Ventricular Tachycardia and Ventricular Fibrillation Based on Semantic Mining

针对现有的诊断系统不能准确区分室性心动过速(VT)和心室纤颤(VF)的问题,提出一种基于巴特沃斯通带滤波器的语义挖掘方法。利用巴特沃斯带通滤波器消除心电图信号的噪声,将心电图(ECG)标准化为长达4 s、值为整个信号段中最大的小段,并将标准化的ECG信号转化为二进制脉冲;在二进制脉冲上实施语义挖掘,从而识别出正常窦性节律、VT、VF三者发作之间的区别。实验结果表明,该方法不仅可以区分正常节奏与VT、VF发作,且不出现错误检测,同时可以区分VT与VF发作,识别率分别高达94.1%和95.2%,可作为致命性疾病诊断的检测工具。

Aiming at the problem that existing diagnosis systems can not distinguish Ventricular Tachycardia（VT） and Ventricular Fibrillation （VF）, a Semantic Mining（SM） method based on Bart walter stone band filter is proposed. Bart walter stone band filter is used to remove noise of electrocardiogram signal. Electrocardiogram（ECG） signal is normalized to a subparagraph with four seconds and the maximum value and is transferred to binary pulse. Semantic mining is carried out on the binary pulse to recognize discrimination of normal sinus rhythm, VT and VF. Experimental results show that proposed semantic mining technique is capable of completely discriminating between normal rhythms and VT and VF episodes without any false detections as well as distinguishing VT and VF episodes from one another with a recognition sensitivity of 94.1%and 95.2%for VT and VF, respectively, which supports a powerful detection tool for diagnosis of lethal diseases.