基于心电动力学离散特征与SVM模型的AMI早期筛查研究

Study on Early Screening of AMI Based on Discrete Characteristics of ECG Dynamics and SVM Model

目的以急性心肌梗死(AMI)患者和健康人的心电动力学(CDG)数据为基础,研究一种新早期筛查模型用以评估健康人群和AMI患者。方法训练集包括1500例AMI患者和1500名健康个体。在2000人中验证了SVM模型。测试无或有轻度症状的AMI患者的心电(ECG)信号,获取ECG信号的CDG数据,分析CDG数据的离散度特征,并基于支持向量机(SVM)建立早期筛查模型以评估健康人群和AMI患者。结果AMI患者CDG数据的离散度特征的定量值与健康个体存在显著差异,AMI患者的CDG数据比正常人的CDG数据混乱,支持向量机模型用于AMI诊断的准确性较高。结论基于心电动力学离散特征与SVM模型的AMI早期筛查方法的应用可以有效区分AMI患者和健康个体,该方法为AMI的早期筛查提供了辅助方法。

Objective Based on the cardiodynamicsgram(CDG)data of acute myocardial infarct(AMI)patients and healthy people,a new early screening model was proposed to evaluate healthy people and AMI patients.Methods The training set included 1500 patients with AMI and 1500 healthy individuals.The SVM models were validated in 2000 individuals.ECG signal of AMI patients without or with mild symptoms was tested to obtain the CDG data of the ECG signal.The dispersion characteristics of CDG data from patients with AMI without or with mild symptoms were extracted,and then support vector machines(SVM)were used to construct an early screening model to screen and evaluate ECG signals in healthy population and patients with AMI.Results The quantitative values of the dispersion characteristics of patients with AMI were significantly different from those of healthy individuals.The CDG data of patients with AMI was more disordered than that of normal individuals.The accuracy of SVM model for AMI diagnosis was 84.05%.The average time consumed to analyze a patient by this model was 2 minutes.Conclusion The application of AMI early screening method based on the dispersion characteristics of CDG data and SVM model can effectively distinguish between patients with AMI and healthy individuals.This method provide an ancillary method of early screening of AMI.