Detection of healthy and pathological heartbeat dynamics in ECG signals using multivariate recurrence networks with multiple scale factors

doi:10.1088/1674-1056/acb422

中国物理B ›› 2023, Vol. 32 ›› Issue (10): 100501-100501.doi: 10.1088/1674-1056/acb422

Detection of healthy and pathological heartbeat dynamics in ECG signals using multivariate recurrence networks with multiple scale factors

Lu Ma(马璐)^1,2, Meihui Chen(陈梅辉)³, Aijun He(何爱军)⁴, Deqiang Cheng(程德强)¹, and Xiaodong Yang(杨小冬)^3,†

1 School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China;
2 Suzhou Vocational and Technical College, Suzhou 234000, China;
3 School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China;
4 School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China

收稿日期:2022-09-14 修回日期:2023-01-04 接受日期:2023-01-18 出版日期:2023-09-21 发布日期:2023-09-27
通讯作者: Xiaodong Yang E-mail:xyang@cumt.edu.cn
基金资助:
Project supported by the Xuzhou Key Research and Development Program (Social Development) (Grant No. KC21304) and the National Natural Science Foundation of China (Grant No. 61876186).

Detection of healthy and pathological heartbeat dynamics in ECG signals using multivariate recurrence networks with multiple scale factors

Lu Ma(马璐)^1,2, Meihui Chen(陈梅辉)³, Aijun He(何爱军)⁴, Deqiang Cheng(程德强)¹, and Xiaodong Yang(杨小冬)^3,†

1 School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China;
2 Suzhou Vocational and Technical College, Suzhou 234000, China;
3 School of Computer Science and Technology, China University of Mining and Technology, Xuzhou 221116, China;
4 School of Electronic Science and Engineering, Nanjing University, Nanjing 210023, China

Received:2022-09-14 Revised:2023-01-04 Accepted:2023-01-18 Online:2023-09-21 Published:2023-09-27
Contact: Xiaodong Yang E-mail:xyang@cumt.edu.cn
Supported by:
Project supported by the Xuzhou Key Research and Development Program (Social Development) (Grant No. KC21304) and the National Natural Science Foundation of China (Grant No. 61876186).

摘要/Abstract

摘要： The electrocardiogram (ECG) is one of the physiological signals applied in medical clinics to determine health status. The physiological complexity of the cardiac system is related to age, disease, etc. For the investigation of the effects of age and cardiovascular disease on the cardiac system, we then construct multivariate recurrence networks with multiple scale factors from multivariate time series. We propose a new concept of cross-clustering coefficient entropy to construct a weighted network, and calculate the average weighted path length and the graph energy of the weighted network to quantitatively probe the topological properties. The obtained results suggest that these two network measures show distinct changes between different subjects. This is because, with aging or cardiovascular disease, a reduction in the conductivity or structural changes in the myocardium of the heart contributes to a reduction in the complexity of the cardiac system. Consequently, the complexity of the cardiac system is reduced. After that, the support vector machine (SVM) classifier is adopted to evaluate the performance of the proposed approach. Accuracy of 94.1% and 95.58% between healthy and myocardial infarction is achieved on two datasets. Therefore, this method can be adopted for the development of a noninvasive and low-cost clinical prognostic system to identify heart-related diseases and detect hidden state changes in the cardiac system.

关键词: electrocardiogram signals, multivariate recurrence networks, cross-clustering coefficient entropy, multiscale analysis

Abstract: The electrocardiogram (ECG) is one of the physiological signals applied in medical clinics to determine health status. The physiological complexity of the cardiac system is related to age, disease, etc. For the investigation of the effects of age and cardiovascular disease on the cardiac system, we then construct multivariate recurrence networks with multiple scale factors from multivariate time series. We propose a new concept of cross-clustering coefficient entropy to construct a weighted network, and calculate the average weighted path length and the graph energy of the weighted network to quantitatively probe the topological properties. The obtained results suggest that these two network measures show distinct changes between different subjects. This is because, with aging or cardiovascular disease, a reduction in the conductivity or structural changes in the myocardium of the heart contributes to a reduction in the complexity of the cardiac system. Consequently, the complexity of the cardiac system is reduced. After that, the support vector machine (SVM) classifier is adopted to evaluate the performance of the proposed approach. Accuracy of 94.1% and 95.58% between healthy and myocardial infarction is achieved on two datasets. Therefore, this method can be adopted for the development of a noninvasive and low-cost clinical prognostic system to identify heart-related diseases and detect hidden state changes in the cardiac system.

Key words: electrocardiogram signals, multivariate recurrence networks, cross-clustering coefficient entropy, multiscale analysis

中图分类号: (Computational methods in statistical physics and nonlinear dynamics)

05.10.-a

87.18.-h (Biological complexity) 87.85.Ng (Biological signal processing) 87.19.X- (Diseases)

Lu Ma(马璐), Meihui Chen(陈梅辉), Aijun He(何爱军), Deqiang Cheng(程德强), and Xiaodong Yang(杨小冬). Detection of healthy and pathological heartbeat dynamics in ECG signals using multivariate recurrence networks with multiple scale factors[J]. 中国物理B, 2023, 32(10): 100501-100501.

参考文献

[1] Zou Y, Donner R V, Marwan N, Donges J F and Kurths J 2019 Physics Reports 787 1
[2] Wolf A, Swift J B, Swinney H L and Vastano J A 1985 Physica D 16 285
[3] Rosenstein M T, Collins J J and Luca C 1993 Phys D 65 117
[4] Deryaübeyli E 2010 Expert Syst. Appl. 37 1192
[5] Richman J S and Randall M J 2000 Am. J. Physiol.: Heart Circ. Physiol. 278 H2039
[6] Bandt C and Pompe B 2002 Phys. Rev. Lett. 88 174102
[7] Shannon and C E 2014 Bell Syst. Tech. J. 30 50
[8] Mishra A K and Raghav S 2010 Biomed. Signal Process. Control 5 114
[9] Burrough and P. A 1981 Nature 294 240
[10] Paumgartner D, Losa G A and Weibel E R 2011 J. Microsc. 121 51
[11] Albert R and Barabási A L 2002 Rev. Mod. Phys. 74 47
[12] Zhang J and Small M 2006 Phys. Rev. Lett. 96 238701
[13] Zhang J, Luo X, Nakamura T, Sun J and Small M 2007 Phys. Rev. E 75 016218
[14] Xu X, Jie Z and Small M 2008 Proc. Natl. Acad. Sci. USA 105 19601
[15] Lacasa L, Luque B, Ballesteros F, Luque J and Nuno J C 2008 Proc. Natil. Acad. Sci. USA 105 4972
[16] Marwan N, Romano M C, Thiel M and Kurths J 2007 Phys. Rep. 438 237
[17] Marwan N, Donges J F, Zou Y, Donner R V and Kurths J 2009 Phys. Lett. A 373 4246
[18] Sun X R, Small M, Zhao Y and Xue X P 2014 Chaos 24 024402
[19] Marwan N and Kurths J 2015 Chaos 25 097609
[20] Lekscha J and Donner R V 2020 NPGeo 27 261
[21] Kachhara S and Ambika G 2019 Europhys. Lett. 127 60004
[22] Ramírezávila G M, Gapelyuk A, Marwan N, Walther T, Stepan H, Kurths J and Wessel N 2013 Philos Trans. A Math. Phys. Eng. 371 20110623
[23] Subramaniyam N P and Hyttinen J 2014 Phys. Lett. A 378 3464
[24] Subramaniyam N P and Hyttinen J 2013 International IEEE/EMBS Conference on Neural Engineering 605
[25] Gao Z K, Zhang X W, Jin N D, Donner R V, Marwan N and Kurths J 2013 Europhys. Lett. 103 50004
[26] Gao Z K, Dang W D, Yang Y X and Cai Q 2017 Chaos 27 035809
[27] Feldhoff J H, Donner R V, Donges J F, Marwan N and Kurths J 2012 EGU General Assembly 14 EGU2012-5450
[28] Zhang N, Wei N and Li K 2020 Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2020 3788
[29] Kachhara S and Ambika G 2020 Chaos 30 123106
[30] Eroglu D, Marwan N, Stebich M and Kurths J 2018 Phys. Rev. E 97 012312
[31] Xu H, Wang M and Yang W 2020 Complexity 2020 5841609
[32] Takens F 1981 Detecting strange attractors in turbulence (Berlin Heidelberg: Springer)
[33] Marwan N 2011 Int. J. Bifurc. Chaos 21 1003
[34] Matassini L, Kantz H, Holyst J and Hegger R 2002 Phys. Rev. E 65 021102
[35] Thiel M, Romano M C, Kurths J, Meucci R, Allaria E and Arecchi F T 2002 Physica D 171 138
[36] Marwan N, Carmen Romano M, Thiel M and Kurths J 2007 Phys. Rep. 438 237
[37] Schinkel S, Dimigen O and Marwan N 2008 Eur. Phys. J. Spec. Top. 164 45
[38] Kraemer K H, Donner R V, Heitzig J and Marwan N 2018 Chaos 28 085720
[39] Marwan N and Kurths J 2002 Phys. Lett. A 302 299
[40] Kraemer K H and Marwan N 2019 Phys. Lett. A 383 125977
[41] Barrat A, Barthelemy M, Pastor-Satorras R and Vespignani A 2004 Proc. Natl. Acad. Sci. USA 101 3747
[42] Boccaletti S, Latora V, Moreno Y, Chavez M and Hwang D U 2006 Phys. Rep. 424 175
[43] Balakrishnan R 2004 Linear Algebra Appl. 387 287
[44] Xu X J, Wu Z X and Wang Y 2005 Int. J. Mod. Phys. C 17 521
[45] Wang J, Ning X, Ma Q, Bian C and Chen Y 2005 Phys. Rev. E 71 062902
[46] Abboud S, Belhassen B, Miller H I, Sadeh D and Laniado S 1986 J. Electrocardiol. 19 371
[47] Leinveber P, Halamek J and Jurak P 2016 J. Electrocardiol. 49 902
[48] Garvey J L 2006 Emerg. Med. Clin. North Am. 24 209
[49] Kligfield P, Gettes L, Bailey J, Childers R, Deal B, Hancock E, Herpen G, Kors J, Macfarlane P, Mirvis D, Pahlm O, Rautaharju P and Wagner G 2007 Heart Rhythm 4 394
[50] Bailey J J, Berson A S, Garson A, Jr., Horan L G, Macfarlane P W, Mortara D W and Zywietz C 1990 Circulation 81 730
[51] Kossmann C E, Brody D A, Burch G E, Hecht H H, Johnston F D, Kay C, Lepeschkin E, Pipberger H V, Pipberger H V, Baule G, Berson A S, Briller S A, Geselowitz D B, Horan L G and Schmitt O H 1967 Circulation 35 583
[52] Goldberger A L, Amaral L A, Glass L, Hausdorff J M, Ivanov P C, Mark R G, Mietus J E, Moody G B, Peng C K and Stanley H E 2000 Circulation 101 E215
[53] Costa M, Goldberger A L and Peng C K 2002 Phys. Rev. Lett. 89 068102
[54] Lipsitz L A and Goldberger A L 1992 JAMA 267 1806
[55] Vaillancourt D E, Sosnoff J J and Newell K M 2004 J. Appl. Physiol. 97 454
[56] Valenza G, Citi L and Barbieri R 2014 PLoS One 9 e105622
[57] Yang X, Wang Z, He A and Wang J 2020 Physica A 559 125021
[58] Yang M J 2005 Conf. Proc. IEEE Eng. Med. Biol. Soc. 2005 4630
[59] Eriksson P, Wilhelmsen L and Rosengren A 2005 Eur. Heart J. 26 2300
[60] Dohare A K, Kumar V and Kumar R 2018 Appl. Soft Comput. 64 138
[61] Sadhukhan D, Pal S and Mitra M 2018 IEEE Trans. Instrum. Meas. 67 2303
[62] Liu J, Zhang C, Ristaniemi T and Cong F 2019 Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2019 1496
[63] Kayikcioglu İ, Akdeniz F, Köse C and Kayikcioglu T 2020 Comput. Electr. Eng. 84 106621
[64] Ma Z Y, Yang X D, He A J, Ma L and Wang J 2022 Acta Phys. Sin. 71 050501 (in Chinese)
[65] Hammad M and Wang K 2017 Proceedings of the 2017 International Conference on Biometrics Engineering and Application pp. 39-44

Detection of healthy and pathological heartbeat dynamics in ECG signals using multivariate recurrence networks with multiple scale factors

Detection of healthy and pathological heartbeat dynamics in ECG signals using multivariate recurrence networks with multiple scale factors

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	Wen-Wei Ye(叶文伟), Lin-Cong Chen(陈林聪), Zi Yuan(原子), Jia-Min Qian(钱佳敏), and Jian-Qiao Sun(孙建桥). Semi-analytical steady-state response prediction for multi-dimensional quasi-Hamiltonian systems[J]. 中国物理B, 2023, 32(6): 60506-060506.
[2]	Linghongzhi Lu(陆凌弘志), Yang Li(李扬), and Xianbin Liu(刘先斌). Detecting physical laws from data of stochastic dynamical systems perturbed by non-Gaussian α-stable Lévy noise[J]. 中国物理B, 2023, 32(5): 50501-050501.
[3]	Yun-Yun Yang(杨云云), Biao Feng(冯彪), Liao Zhang(张辽), Shu-Hong Xue(薛舒红), Xin-Lin Xie(谢新林), and Jian-Rong Wang(王建荣). Robustness measurement of scale-free networks based on motif entropy[J]. 中国物理B, 2022, 31(8): 80201-080201.
[4]	Yong Huang(黄勇) and Yang Li(李扬). Data-driven modeling of a four-dimensional stochastic projectile system[J]. 中国物理B, 2022, 31(7): 70501-070501.
[5]	Meili Liu(刘美丽), Xiaogang Qi(齐小刚), and Hao Pan(潘浩). Multifractal analysis of the software evolution in software networks[J]. 中国物理B, 2022, 31(3): 30501-030501.
[6]	Ru-Qi Li(李汝琦), Yu-Rong Song(宋玉蓉), and Guo-Ping Jiang(蒋国平). Prediction of epidemics dynamics on networks with partial differential equations: A case study for COVID-19 in China[J]. 中国物理B, 2021, 30(12): 120202-120202.
[7]	Dongli Duan(段东立), Tao Chai(柴涛), Xixi Wu(武茜茜), Chengxing Wu(吴成星), Shubin Si(司书宾), and Genqing Bian(边根庆). Identification of unstable individuals in dynamic networks[J]. 中国物理B, 2021, 30(9): 90501-090501.
[8]	Xiaodong Liu(柳晓东) and Lipo Mo(莫立坡). Consensus problems on networks with free protocol[J]. 中国物理B, 2021, 30(7): 70701-070701.
[9]	Jian-Long Wang(王剑龙), Xiao-Lei Leng(冷小磊), and Xian-Bin Liu(刘先斌). Stationary response of colored noise excited vibro-impact system[J]. 中国物理B, 2021, 30(6): 60501-060501.
[10]	Zi-Wei Yuan(袁紫薇), Chang-Chun Lv(吕长春), Shu-Bin Si(司书宾), and Dong-Li Duan(段东立). Dynamical robustness of networks based on betweenness against multi-node attack[J]. 中国物理B, 2021, 30(5): 50501-050501.
[11]	. [J]. 中国物理B, 2021, 30(3): 38901-.
[12]	陈侠, 尹立远, 刘永泰, 刘皓. Hybrid-triggered consensus for multi-agent systems with time-delays, uncertain switching topologies, and stochastic cyber-attacks[J]. 中国物理B, 2019, 28(9): 90701-090701.
[13]	方木云, 周灿灿, 黄鑫, 李晓, 周建平. H_∞ couple-group consensus of stochastic multi-agent systems with fixed and Markovian switching communication topologies[J]. 中国物理B, 2019, 28(1): 10703-010703.
[14]	刘晓, 王进法, 景薇, Menno de Jong, Jeroen S Tummers, 赵海. Evolution of the Internet AS-level topology:From nodes and edges to components[J]. 中国物理B, 2018, 27(12): 120501-120501.
[15]	徐伟, 王亮, 冯进钤, 乔艳, 韩平. Some new advance on the research of stochastic non-smooth systems[J]. 中国物理B, 2018, 27(11): 110503-110503.