Suppr超能文献

相量变换在单导联心电图基准点自动描绘中的应用。

Application of the phasor transform for automatic delineation of single-lead ECG fiducial points.

机构信息

Innovation in Bioengineering Research Group, University of Castilla La Mancha, Spain.

出版信息

Physiol Meas. 2010 Nov;31(11):1467-85. doi: 10.1088/0967-3334/31/11/005. Epub 2010 Sep 24.

Abstract

This work introduces a new single-lead ECG delineator based on phasor transform. The method is characterized by its robustness, low computational cost and mathematical simplicity. It converts each instantaneous ECG sample into a phasor, and can precisely manage P and T waves, which are of notably lower amplitude than the QRS complex. The method has been validated making use of synthesized and real ECG sets, including the MIT-BIH arrhythmia, QT, European ST-T and TWA Challenge 2008 databases. Experiments with the synthesized recordings reported precise detection and delineation performances in a wide variety of ECGs, with signal-to-noise ratios of 10 dB and above. For real ECGs, the QRS detection was characterized by an average sensitivity of 99.81% and positive predictivity of 99.89%, for all the analyzed databases (more than one million beats). Regarding delineation, the maximum localization error between automatic and manual annotations was lower than 6 ms and its standard deviation was in agreement with the accepted tolerances for expert physicians in the onset and offset identification for QRS, P and T waves. Furthermore, after revising and reannotating some ECG recordings by expert cardiologists, the delineation error decreased notably, becoming lower than 3.5 ms, on average, and reducing by a half its standard deviation. This new proposed strategy outperforms the results provided by other well-known delineation algorithms and, moreover, presents a notably lower computational cost.

摘要

本工作介绍了一种基于相量变换的新型单导联 ECG 描绘器。该方法的特点是鲁棒性强、计算成本低、数学方法简单。它将每个瞬时 ECG 样本转换为一个相量,并能精确地管理 P 波和 T 波,这两个波的幅度明显低于 QRS 复合体。该方法已经利用合成和真实的 ECG 数据集进行了验证,包括 MIT-BIH 心律失常、QT、欧洲 ST-T 和 TWA 挑战 2008 数据库。利用合成记录进行的实验表明,该方法在各种 ECG 中具有精确的检测和描绘性能,信噪比在 10 dB 及以上。对于真实的 ECG,QRS 检测的平均灵敏度为 99.81%,阳性预测值为 99.89%,所有分析的数据库(超过一百万次心跳)都是如此。在描绘方面,自动标注和手动标注之间的最大定位误差小于 6 ms,其标准差与专家医生在 QRS、P 和 T 波的起始和结束识别方面的可接受公差一致。此外,在专家心脏病学家对一些 ECG 记录进行修订和重新标注后,描绘误差明显降低,平均低于 3.5 ms,其标准差降低了一半。这种新提出的策略优于其他著名的描绘算法的结果,而且计算成本显著降低。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验