基于经验模态分解与独立成分分析的心肺复苏伪迹自适应滤除算法  

Adaptive Cardiopulmonary Resuscitation Artifacts Elimination Algorithm Based on Empirical Mode Decomposition and Independent Component Analysis

作　　者：余明[1] 陈锋[1] 张广[1] 李良喆 王春晨[1] 王丹[1] 詹宁波[1] 顾彪[1] 吴太虎[1] YU Ming CHEN Feng ZHANG Guang LI Liangzhe WANG Chunchen WANG Dan ZHAN Ningbo GU Biao WU Taihu(Institute of Medical Equipment, Academy of Military Medical Science, Tianjin 300161, China)

机构地区：[1]军事医学科学院卫生装备研究所,天津300161

出　　处：《生物医学工程学杂志》2016年第5期834-841,共8页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助项目(81501551)

摘　　要：心肺复苏(CPR)过程中实施的胸外按压引起的伪迹会严重降低除颤节律辨识的可靠性。本文提出了一种无需参考信号的CPR伪迹自适应滤除算法。结合经验模态分解(EMD)和独立成分分析(ICA),将真正的心电节律信号从受CPR伪迹干扰的心电信号中分离出来。为评估算法的效果,构建了一个用于除颤节律辨识的反向传播神经网络。采集了1 484例受CPR伪迹干扰的猪的心电信号用于实验。实验结果表明,该算法可以在很大程度上抑制CPR伪迹的影响,从而显著提高CPR过程中除颤节律辨识的准确性。Artifacts produced by chest compression during cardiopulmonary resuscitation （CPR） seriously affect the reliability of shoekable rhythm detection algorithms. In this paper, we proposed an adaptive CPR artifacts elimination algorithm without needing any reference channels. The clean electrocardiogram （ECG） signals can be extracted from the corrupted ECG signals by incorporating empirical mode decomposition （EMD） and independent component analy sis （ICA）. For evaluating the performance of the proposed algorithm, a back propagation neural network was con- structed to implement the shockahle rhythm detection. A total of 1 484 corrupted ECG samples collected from pigs were included in the analysis. The results of the experiments indicated that this method would greatly reduce the effects of the CPR artifacts and thereby increase the accuracy of the shockable rhythm detection algorithm.

关 键 词：心肺复苏 经验模态分解 独立成分分析 反向传播神经网络 

分 类 号：R459.7[医药卫生—急诊医学]