A comparison of entropy approaches for AF discrimination.

A comparison of entropy approaches for AF discrimination.
复制标题

AF 判别熵方法的比较

DOI:
10.1088/1361-6579/aacc48
复制
发表时间:
2018-07-06
影响因子:
3.2
通讯作者:
Clifford GD
Clifford GD
中科院分区:
工程技术3区
文献类型:
--
作者:
Liu C;Oster J;Reinertsen E;Li Q;Zhao L;Nemati S;Clifford GD

文献摘要

参考文献

被引文献

相似文献

本研究的重点是比较单熵测量的心室反应分析为基础的房颤检测。为了提高基于熵的AF检测器的性能,我们开发了一种归一化模糊熵,一种新的度量:1)使用模糊函数确定向量相似性,2)用密度估计代替熵近似的概率估计,3)利用灵活的距离阈值参数,以及4)通过减去平均RR区间的自然对数值来调整心率。使用MIT-BIH心房颤动(AF)数据库对基于的AF检测器进行训练,并在MIT-BIH正常窦性心律(NSR)和MIT-BIH心律失常数据库上进行测试。在三个标准窗口大小上,将基于AF检测器与基于其他三个熵测度的AF检测器进行比较:样本熵()、模糊测度熵()和样本熵系数()。对于AF和非AF节律的分类,在12拍、30拍和60拍窗长的受者工作特征曲线(AUC)下面积最高,分别为92.72%、95.27%和96.76%。在所有窗口大小上,这比次优技术的性能更高,其auc分别为91.12%,91.86%和90.55%。并导致所有窗口大小的auc都较低(低于90%)。在所有其他测试统计数据,包括约登指数,敏感性,特异性,准确性,阳性预测和阴性预测方面也提供了优越的性能。综上所述,我们证明可以用来准确地从RR区间时间序列中识别AF。此外,较长的窗口长度(最多一分钟)提高了所有基于熵的AF检测器的性能,除了该方法。
This study focused on the comparison of single entropy measures for the ventricular response analysis-based AF detection. To enhance the performance of entropy-based AF detectors, we developed a normalized fuzzy entropy, , a novel metric that: 1) uses a fuzzy function to determine vector similarity, 2) replaces probability estimation with density estimation for entropy approximation, 3) utilizes a flexible distance threshold parameter, and 4) adjusts for heart rate by subtracting the natural log value of the mean RR interval. An AF detector based on was trained using the MIT-BIH Atrial Fibrillation (AF) database, and tested on the MIT-BIH Normal Sinus Rhythm (NSR) and MIT-BIH Arrhythmia databases. The -based AF detector was compared to AF detectors based on three other entropy measures: sample entropy (), fuzzy measure entropy () and coefficient of sample entropy (), over three standard window sizes. For classifying AF and non-AF rhythms, achieved the highest area under receiver operating characteristic curve (AUC) values of 92.72%, 95.27% and 96.76% for 12-, 30- and 60-beat window lengths respectively. This was higher than the performance of the next best technique, , over all windows sizes, which provided respective AUCs of 91.12%, 91.86% and 90.55%. and resulted in lower AUCs (below 90%) over all window sizes. also provided superior performance for all other tested statistics, including the Youden index, sensitivity, specificity, accuracy, positive predictivity and negative predictivity. In conclusion, we show can be used to accurately identify AF from RR interval time series. Furthermore, longer window lengths (up to one minute) increase the performance of all entropy-based AF detectors under evaluation except the method.
DOI: 10.1160/th07-08-0508
发表时间: 2008-02-01
影响因子: 6.7
作者:
Hughes, Michael;Lip, Gregory Y. H.
通讯作者: Lip, Gregory Y. H.
DOI: 10.1016/j.cmpb.2016.04.009
发表时间: 2016-07-01
影响因子: 6.1
作者:
Garcia, Manuel;Rodenas, Juan;Rieta, Jose J.
通讯作者: Rieta, Jose J.
DOI: 10.1155/2012/245213
发表时间: 2012
影响因子: --
作者:
Alcaraz R;Rieta JJ
通讯作者: Rieta JJ
一种使用多个参数的心电图中实时心房颤动检测的新方法
DOI: 10.1111/anec.12111
发表时间: 2014-05-01
影响因子: 1.9
作者:
Du, Xiaochuan;Rao, Nini;Chen, Xu
通讯作者: Chen, Xu
DOI: 10.1056/nejmoa1105575
发表时间: 2012-01-12
影响因子: 158.5
作者:
Healey, Jeff S.;Connolly, Stuart J.;Hohnloser, Stefan H.
通讯作者: Hohnloser, Stefan H.