Safdarian Naser, Dabanloo Nader Jafarnia, Matini Seyed Ali, Nasrabadi Ali Motie
Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Interventional and Consultant Cardiologist, Mehr General Hospital, Tehran, Iran.
J Med Signals Sens. 2013 Jul;3(3):129-38.
In this study, a method for determining the location and extent of myocardial infarction using Body Surface Potential Map data of PhysioNet challenge 2007 database is presented. This data is related to four patients with myocardial infarction. We used two patients as training set to determine rules and two other patients as testing set of the proposed model. First, T-wave amplitude, T-wave integral, Q-wave amplitude and R-wave amplitude as four features of ECG signals were extracted. Then we defined several rules and proper thresholds for localization and determining the extent of myocardial infarction. To determine the precise location and extent of myocardial infarction, 17-segment standard model of left ventricle was used. Finally, overall accuracy of this method was shown with SO, CED and EPD parameters. We obtained 1.16, 1 and 5.3952 for SO, CED and EPD, respectively, in our test data. Two main advantages of this method are simplicity and high accuracy.
在本研究中，提出了一种利用PhysioNet 2007挑战赛数据库的体表电位图数据来确定心肌梗死位置和范围的方法。该数据与四名心肌梗死患者相关。我们将两名患者作为训练集来确定规则，另外两名患者作为所提模型的测试集。首先，提取心电图信号的四个特征，即T波振幅、T波积分、Q波振幅和R波振幅。然后我们定义了几条规则以及用于定位和确定心肌梗死范围的合适阈值。为了确定心肌梗死的精确位置和范围，采用了左心室17节段标准模型。最后，用SO、CED和EPD参数展示了该方法的总体准确性。在我们的测试数据中，SO、CED和EPD分别为1.16、1和5.3952。该方法的两个主要优点是简单性和高精度。
