针对阵发性房颤(PAF)发作持续时间较短难以捕捉,且现有识别算法抗噪性能较差易导致误检、漏检等问题,本研究提出一种基于积分均值模式分解(IMMD)和固有模态函数样本熵(IMFSE)的PAF识别方法.首先,对时长为20 min的心率变异性(HRV)信号片段进行IMMD分解得到一系列固有模态函数(IMF)分量,并计算IMFSE;然后,通过对IMFSE结果进行统计分析选取PAF识别的特征量;最后,利用支持向量机与交叉验证完成PAF识别.从PAF Prediction Challenge Database(AFPDB)数据库提供的正常受试者、PAF发作与远离PAF发作受试者心电信号中,分别获取25段时长为20 min的HRV信号片段,构成正常组、PAF发作组与PAF未发作组.通过对这75段HRV信号片段的实验发现:利用本方法进行PAF识别,识别准确率、敏感性、特异性分别可达到94%、96%、92%.所提出的PAF识别算法为进一步地快速准确自动检测PAF提供了参考,在可穿戴设备的长期自动检测识别PAF方面具有较大的应用前景.
In order to solve the problem that the short duration of paroxysmal atrial fibrillation(PAF)can easily lead to false detection and missed detection,an identification algorithm based on integral mean mode decomposition(IMMD)and sample entropy of intrinsic mode function(IMFSE)was proposed in this paper.In this work,heart rate variability(HRV)signal fragments with a duration of 20 minutes were subjected to IMMD to obtain a series of intrinsic mode functions(IMFs).Then,the IMFSE was calculated,and next,the feature of PAF identification was extracted by statistical analysis of the IMFSE results.Finally,PAF identification was achieved by support vector machine and cross-validation.The PAF Prediction Challenge Database(AFPDB)provides ECG signals of normal subjects,patients with PAF attacks and patients far away from PAF attacks.From these signals,25 HRV signal segments with a duration of 20 minutes were obtained,which constituted normal group,PAF attack group and PAF non-attack group.The performance of the proposed method in identification PAF episodes was evaluated with these 75 signals.Our proposed method obtained the values of 94%,96%and 92%for the evaluation criteria of correct rate,sensitivity,and specificity,respectively.The experimental results showed that the PAF identification algorithm proposed in this paper provided a method basis for further automatic detection of PAF,and had a great application prospect in the long-term automatic detection and identification of PAF in wearable devices.