Feature extraction based on time-singularity multifractal spectrum distribution in intracardiac atrial fibrillation signals

TecnoLogicas Pub Date : 2017-09-04 DOI:10.22430/22565337.716
R. D. Urda-Benitez, A. E. Castro-Ospina, A. Orozco-Duque
{"title":"Feature extraction based on time-singularity multifractal spectrum distribution in intracardiac atrial fibrillation signals","authors":"R. D. Urda-Benitez, A. E. Castro-Ospina, A. Orozco-Duque","doi":"10.22430/22565337.716","DOIUrl":null,"url":null,"abstract":"Non-linear analysis of electrograms (EGM) has been proposed as a tool to detect critical conduction sites (e.g., rotors vortex, multiple wavefronts) in atrial fibrillation (AF). Likewise, studies have shown that multifractal analysis is useful to detect critical activity in EGM signals. However, the multifractal spectrum does not consider the temporal information. There is a new mathematical formalism to overcome this limitation: the time-singularity multifractal spectrum distribution (TS-MFSD), which involves the time variation of the spectrum. In this manuscript, we describe the methodology to compute the TS-MFSD from EGM signals. Moreover, we propose a methodology to extract features from time-singularity spectrum and from singularity energy spectrum (SES). We tested the features in an EGM database labeled by experts as: non-fragmented, discrete fragmented potentials, disorganized activity, and continuous activity. We tested the area under the receiver operating characteristic (ROC) curve. The proposed features achieve an area under the ROC curve of 95.17% when detecting signals with continuous activity. These results outperform those reported using multifractal analysis. To our knowledge, this is the first work that report the use of TS-MFSD in biomedical signals and our findings suggest that time-singularity has the potential to be used in the study of non-stationary behavior of EGM signals in AF.","PeriodicalId":30469,"journal":{"name":"TecnoLogicas","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2017-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"TecnoLogicas","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.22430/22565337.716","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Non-linear analysis of electrograms (EGM) has been proposed as a tool to detect critical conduction sites (e.g., rotors vortex, multiple wavefronts) in atrial fibrillation (AF). Likewise, studies have shown that multifractal analysis is useful to detect critical activity in EGM signals. However, the multifractal spectrum does not consider the temporal information. There is a new mathematical formalism to overcome this limitation: the time-singularity multifractal spectrum distribution (TS-MFSD), which involves the time variation of the spectrum. In this manuscript, we describe the methodology to compute the TS-MFSD from EGM signals. Moreover, we propose a methodology to extract features from time-singularity spectrum and from singularity energy spectrum (SES). We tested the features in an EGM database labeled by experts as: non-fragmented, discrete fragmented potentials, disorganized activity, and continuous activity. We tested the area under the receiver operating characteristic (ROC) curve. The proposed features achieve an area under the ROC curve of 95.17% when detecting signals with continuous activity. These results outperform those reported using multifractal analysis. To our knowledge, this is the first work that report the use of TS-MFSD in biomedical signals and our findings suggest that time-singularity has the potential to be used in the study of non-stationary behavior of EGM signals in AF.
基于时间奇点多重分形谱分布的心内房颤信号特征提取
非线性电图分析(EGM)已被提出作为检测心房颤动(AF)关键传导部位(如旋涡、多波前)的工具。同样,研究表明多重分形分析对于检测EGM信号中的关键活动是有用的。然而,多重分形谱不考虑时间信息。有一种新的数学形式可以克服这一限制:时间奇点多重分形谱分布(TS-MFSD),它涉及到谱的时间变化。在本文中,我们描述了从EGM信号计算TS-MFSD的方法。此外,我们还提出了一种从时间奇异谱和奇异能量谱(SES)中提取特征的方法。我们在EGM数据库中测试了由专家标记的特征:非碎片化、离散碎片化电位、无组织活动和连续活动。我们测试了受试者工作特征曲线下的面积。在检测连续活动的信号时,所提出的特征在ROC曲线下的面积达到95.17%。这些结果优于使用多重分形分析报告的结果。据我们所知,这是首次报道TS-MFSD在生物医学信号中的应用,我们的研究结果表明,时间奇点有可能用于研究AF中EGM信号的非平稳行为。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
30
审稿时长
28 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信