|
|
|
| Wearable ECG: History, Key Technologies and Future Challenges |
| Liu Chengyu1#*, Yang Meicheng1, Di Jianan1, Xing Yantao1, Li Yuwen1, Li Jianqing1,2 |
1(State Key Laboratory of Bioelectronics, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China)
2(School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing 211166, China) |
|
|
|
|
Abstract With the rapid development of Internet of things (IoT), big data, cloud computing, artificial intelligence (AI) and other advanced technologies, dynamic ECG monitoring has made remarkable progress towards the direction of wearable, intelligent and convenient in recent years. Wearable ECG device can facilitate the individualized, real-time, long-term and continuous monitoring of ECG data, providing an important carrier and technical means for the new mode of smart healthcare. This paper firstly summarized the basic concept and development history of wearable ECG, and then reviewed the related key technologies and typical wearable ECG devices. Finally, the perspectives and challenges of wearable ECG are analyzed.
|
|
Received: 25 August 2019
|
|
|
|
Corresponding Authors:
E-mail: chengyu@seu.edu.cn
|
|
|
|
[1] 陈伟伟, 高润霖, 刘力生, 等. 《中国心血管病报告 2017》概要 [J]. 中国循环杂志, 2018, 33(1): 1-8.
[2] 全国老龄办. 中国人口老龄化发展趋势预测研究报告 [J]. 中国妇运,2007(2):17-20.
[3] 陈伟伟, 高润霖, 刘力生, 等. 《中国心血管病报告 2014》概要 [J]. 中国循环杂志, 2015, 30(7): 617-622.
[4] Topol EJ. High-performance medicine: The convergence of human and artificial intelligence [J]. Nat Med, 2019, 25(1): 44-56.
[5] Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare [J]. Nat Med, 2019, 25(1): 24-29.
[6] Attia ZI, Kapa S, Lopez-Jimenez F, et al. Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram [J]. Nat Med, 2019, 25(1): 70-74.
[7] Hannun AY, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network [J]. Nat Med, 2019, 25(1): 65-69.
[8] Liu Chengyu, Zhang Xiangyu, Zhao Lina, et al. Signal quality assessment and lightweight qrs detection for wearable ecg smartvest system [J]. IEEE Internet Things J, 2019, 6(2): 1363-1374.
[9] Mehta NJ, Khan IA. Cardiology′s 10 greatest discoveries of the 20th century [J]. Tex Heart Inst J, 2002, 29(3): 164-171.
[10] Waller AD. A demonstration on man of electromotive changes accompanying the heart′s beat [J]. J Physiol, 1887, 8(5): 229-234.
[11] Moises RR, Christian C, Joseph V. Einthoven′s string galvanometer: the first electrocardiograph [J]. Tex Heart Inst J, 2008, 35(2): 174-178.
[12] Holter NJ. New method for heart studies: Continuous electrocardiography of active subjects over long periods is now practical. [J]. Science, 1961, 134(3486): 1214-1220.
[13] Nygårds ME, Hulting J. An automated system for ECG monitoring [J]. Comput Biomed Res, 1979, 12(2): 181-202.
[14] Gopalsamy C, Park S, Rajamanickam R, et al. The wearable motherboard: The first generation of adaptive and responsive textile structures (ARTS) for medical applications [J]. Virtual Real, 1999, 4(3): 152-168.
[15] Chi YM, Jung TP, Cauwenberghs G. Dry-contact and noncontact biopotential electrodes: methodological review [J]. IEEE Rev Biomed Eng, 2010, 3: 106-119.
[16] Matthews R, McDonald NJ, Hervieux P, et al. A wearable physiological sensor suite for unobtrusive monitoring of physiological and cognitive state [C] //Conference Proceedings of IEEE EMBS. Lyon:IEEE,2007: 5276-5281.
[17] Lin Ke, Wang Xinan, Zhang Xing, et al. An FPC based flexible dry electrode with stacked double-micro-domes array for wearable biopotential recording system [J]. Microsyst Technol, 2016, 23(5): 1443-1451.
[18] Kang BC, Ha TJ. Wearable carbon nanotube based dry-electrodes for electrophysiological sensors [J]. Jpn J Appl Phys, 2018, 57(5S): 05gd02.
[19] Chlaihawi AA, Narakathu BB, Emamian S, et al. Development of printed and flexible dry ECG electrodes [J]. Sensing and Bio-Sensing Research, 2018, 20: 9-15.
[20] Wang K, Parekh U, Pailla T, et al. Stretchable dry electrodes with concentric ring geometry for enhancing spatial resolution in electrophysiology [J]. Adv Healthc Mater, 2017, 6(19): 1700552.
[21] Ameri SK, Ho R, Jang H, et al. Graphene electronic tattoo sensors [J]. ACS Nano, 2017, 11(8): 7634-7641.
[22] Zhang Shiming, Cicoira F. Flexible self-powered biosensors [J]. Nature, 2018, 561: 466-467.
[23] Rattfält L. Smartware electrodes for ECG measurements: Design, evaluation and signal processing [D]. Linköping: Linköping University, 2013.
[24] Xia Henian, Garcia GA, Bains J, et al. Matrix of regularity for improving the quality of ECGs [J]. Physiol Meas, 2012, 33(9): 1535-1548.
[25] 李延军, 唐晓英, 许志, 等. 一种基于波形特征的12导联心电信号质量的估计方法 [J]. 航天医学与医学工程, 2015, 28(6): 419-426.
[26] Liu Chengyu, Li Peng, Zhao Lina, et al. Real-time signal quality assessment for ECGs collected using mobile phones [C] //Computing in Cardiology. Hangzhou: IEEE, 2011: 357-360.
[27] Zhang Yatao, Wei Shoushui,Dr Maria C, et al. Using Lempel-Zip complexity to assess ECG signal quality [J]. J Med Biol Eng, 2016, 36(5): 625-634.
[28] Zhao Zhidong, Zhang Yefei. SQI quality evaluation mechanism of single-lead ECG signal based on simple heuristic fusion and fuzzy comprehensive evaluation [J]. Front Physiol, 2018, 9: 727.
[29] Li Qiao, Rajagopalan C, Clifford GD. A machine learning approach to multi-level ECG signal quality classification [J]. Comput Methods Programs Biomed, 2014, 117(3): 435-447.
[30] Clifford GD, Behar J, Li Qiao, et al. Signal quality indices and data fusion for determining clinical acceptability of electrocardiograms [J]. Physiol Meas, 2012, 33(9): 1419-1433.
[31] Zhao Zhongyao, Liu Chengyu, Li Yaowei, et al. Noise rejection for wearable ECGs using modified frequency slice wavelet transform and convolutional neural networks [J]. IEEE Access, 2019, 7(1): 34060-34067.
[32] Liu Feifei, Liu Chengyu, Zhao Lina, et al. Dynamic ECG signal quality evaluation based on the generalized bSQI index [J]. IEEE Access, 2018, 6(1): 41892-41902.
[33] Clifford GD, Azuaje F, McSharry PE. Advanced methods and tools for ECG data analysis [M]. London: Artech House, 2006: 1-366.
[34] Singh M, Manocha A. Optimal selection of wavelet function and decomposition level for removal of ECG signal artifacts [J]. J Med Imaging Health Inform, 2015, 5(1): 138-146.
[35] Wang Zhaoyang, Zhu Junjiang, Yan Tianhong, et al. A new modified wavelet-based ECG denoising [J]. Comput Assist Surg, 2019, 24:174-183.
[36] Zou Qingyun, Wang Guoqiu. Optimal model for 4-band biorthogonal wavelets bases for fast calculation [J]. J Inequal Appl, 2017, 2017(1): 1-10.
[37] Wang Dawei, Zhang Xi. A new class of Hilbert pairs of almost symmetric orthogonal wavelet bases [J]. IEICE Trans Fundamentals, 2016, 99: 884-891.
[38] 张金玲, 郑鑫. 平稳小波变换和新阈值函数用于心电信号去噪 [J]. 北京邮电大学学报, 2017, 40(1): 28-31.
[39] 郑敏敏, 高小榕, 谢海鹤. 心电信号小波去噪的改进算法研究 [J]. 中国生物医学工程学报, 2017, 36(1): 114-118.
[40] Singh P, Pradhan G, Syed S. Denoising of ECG signal by non-local estimation of approximation coefficients in DWT [J]. Biocybern Biomed Eng, 2017, 37(3): 599-610.
[41] Jenkala W, Latifa R, Toumanaria A, et al. An efficient algorithm of ECG signal denoising using the adaptive dual threshold filter and the discrete wavelet transform [J]. Biocybern Biomed Eng, 2016, 36: 499-508.
[42] Manuel BV, Weng B, Barner KE. ECG signal denoising and baseline wander correction based on the empirical mode decomposition [J]. Comput Biol Med, 2008, 38(1): 1-13.
[43] Su ML, Chuang KS. An ECG signal enhancement based on improved EMD [J]. Prog Electromagn Res Symp, 2013: 940-943.
[44] Ferdi Y, Herbeuval JP, Charef A, et al. R wave detection using fractional digital differentiation [J]. ITBM-RBM, 2003, 24(5): 273-280.
[45] 黄家洺, 郑日荣, 曾绳涛. 心电信号特征检测算法研究 [J]. 机电工程技术, 2013 (8): 106-110.
[46] Wei Wei, Zhang Chunxia, Lin Wei. A QRS wave detection algorithm based on complex wavelet transform [J]. AMM, 2013, 239: 1284-1288.
[47] Xiang Yande, Lin Zhidao, Meng Jianyi. Automatic QRS complex detection using two-level convolutional neural network [J]. Biomed Eng Online, 2018, 17(1): 1-17.
[48] Yochuma M, Renaudb C, Jacquir S. Automatic detection of P, QRS and T patterns in 12 leads ECG signal based on CWT [J]. Biomed Signal Process Control, 2016, 25: 46-52.
[49] Bayasi N, Tekeste T, Saleh H, et al. Adaptive technique for P and T wave delineation in electrocardiogram signals [C] // Conference Proceedings of IEEE EMBS. Chicago: IEEE, 2014: 90-93.
[50] Akhbari M, Shamsollahi MB, Sayadi O, et al. ECG segmentation and fiducial point extraction using multi hidden Markov model [J]. Comput Biol Med, 2016, 79(1): 21-29.
[51] Zhang Qinghua, Manriquez AI, Medigue C, et al. An algorithm for robust and efficient location of T-wave ends in electrocardiograms [J]. IEEE Trans Biomed Eng, 2006, 53: 2544-2552.
[52] Suarez-Leon AA, Varon C, Willems R, et al. T-wave end detection using neural networks and support vector machines [J]. Comput Biol Med, 2018, 96: 116-127.
[53] Song Jinzhong, Yan Hong, Xiao Zhijun, et al. A robust and effecient algorithm for ST-T complex detection in electrocardigrams [J]. J Mech Med Biol, 2011, 11: 1103-1111.
[54] Shang Haixia, Wei Shoushui, Liu Feifei, et al. An improved sliding window area method for T wave detection [J]. Comput Math Methods Med, 2019, 2019(1): 1-10.
[55] Xu Mingfang, Wei Shoushui, Qin Xiuwen, et al. Rule-based method for morphological classification of ST segment in ECG signals [J]. J Med Biol Eng, 2015, 35(12): 816-823.
[56] Mihandoost S, Amirani MC. Electrocardiogram recognition using spectral correlation function [C] //The 24th Iranian Conference on Electrical Engineering. Shiraz: IEEE, 2016: 277-282.
[57] Kumar M, Pachori RB, Acharya UR. Characterization of coronary artery disease using flexible analytic wavelet transform applied on ECG signals [J]. Biomed Signal Process Control, 2017, 31: 301-308.
[58] Rajesh K, Dhuli R. Classification of ECG heartbeats using nonlinear decomposition methods and support vector machine [J]. Comput Biol Med, 2017, 87(8): 271-284.
[59] Li Hongqiang, Liang Huan, Miao Chunjiao, et al. Novel ECG signal classification based on KICA nonlinear feature extraction [J]. Circuits Syst Signal Process, 2015, 35(4): 1187-1197.
[60] Hassan W, Saleem S, Habib A, et al. Classification of normal and arrhythmic ECG using wavelet transform based template-matching technique [J]. J Pak Med Assoc, 2017, 67(6): 843-847.
[61] Park J, Kang K. PcHD: Personalized classification of heartbeat types using a decision tree [J]. Comput Biol Med, 2014, 54: 79-88.
[62] Zhou Qunyi, Liu Xing, Duan Huilong. Notice of retraction: ECG beat classification based on mirrored gauss model and cluster template [C] //The 1st International Conference on Bioinformatics and Biomedical Engineering. Wuhan: IEEE, 2007: 675-678.
[63] Wang Liang, Zhang Yinlong, Tan Jindong, et al. A novel approach to ECG classification based upon two-layered HMMs in body sensor networks [J]. Sensors, 2014, 14(4): 5994-6011.
[64] Khafif SH, Brawany MA. Artificial neural network-based automated ECG signal classifier [J]. ISRN Biomed Eng, 2013, 9(1): 1-6.
[65] Wang Guijin, Zhang Chenshuang, Liu Yongpan, et al. A global and updatable ECG beat classification system based on recurrent neural networks and active learning [J]. Information Sciences, 2018(6):062.
[66] Acharya UR, Oh SL, Hagiwara Y, et al. A deep convolutional neural network model to classify heartbeats [J]. Comput Biol Med, 2017, 89: 389-396.
[67] 高兴姣, 李智, 陈珊珊, 等. 基于近邻保持嵌入算法的心律失常心拍分类 [J]. 生物医学工程学杂志, 2017, 34(1): 1-6.
[68] Kajino H, Tsuboi Y, Sato I, et al. Learning from crowds and experts [J]. Trans Jpn Soc Artif Intell, 2012, 28(3): 243-248.
[69] Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm [J]. J R Stat Soc Series B Stat Methodol, 1977, 39(1): 1-38.
[70] Dawid AP, Skene AM. Maximum likelihood estimation of observer Error-rates using the EM algorithm [J]. J R Stat Soc Ser C Appl Stat, 1979, 28(1): 20-28.
[71] Raykar VC, Yu Shipeng, Zhao LH, et al. Learning from crowds [J]. J Mach Learn Res, 2010, 11(4): 1297-1322.
[72] Kara YE, Genc G, Aran O, et al. Modeling annotator behaviors for crowd labeling [J]. Neurocomputing, 2015, 160(7): 141-156.
[73] Zhu Tingting, Johnson AE, Behar J, et al. Crowd-sourced annotation of ecg signals using contextual information [J]. Ann Biomed Eng, 2014, 42(4): 871-884.
[74] Zhu Tingting, Dunkley N, Behar J, et al. Fusing continuous-valued medical labels using a bayesian model [J]. Ann Biomed Eng, 2015, 43(12): 2892-2902.
[75] Zhang Ping, Obradovic Z. Learning from inconsistent and unreliable annotators by a Gaussian mixture model and Bayesian information criterion [C] //Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin: Springer, 2011: 553-568.
[76] Zhang Ping, Cao Weidan, Obradovic Z. Learning by aggregating experts and filtering novices: A solution to crowdsourcing problems in bioinformatics [J]. BMC Bioinformatics, 2013, 14(Suppl 12): S5.
[77] Yan Yan, Rosales R, Fung G, et al. Modeling annotator expertise: Learning when everybody knows a bit of something [J]. Proc Mach Learn Res, 2010, 9: 932-939.
[78] 韩世鹏, Omisore OM, 王磊. 关于穿戴式人体传感器网络的研究思考 [J]. 中国科学院院刊, 2017, 32(12): 1322-1329.
[79] IEC 60601-2-51, Medical electrical equipment - Part 2-51: Particular requirements for safety, including essential performance, of recording and analysing single channel and multichannel electrocardiographs [S].
[80] Bumgarner JM, Lambert CT, Hussein AA, et al. Smartwatch algorithm for automated detection of atrial fibrillation [J]. J Am Coll Cardiol, 2018, 71(21): 2381-2388.
[81] Ip JE. Wearable devices for cardiac rhythm diagnosis and management [J]. JAMA, 2019, 321(4): 337-338.
[82] Gates B. MIT technology review partners with Bill Gates to present 10 breakthrough technologies of 2019 [EB/OL]. https://www.technologyreview.com/lists/technologies/2019, 2019-02-27/2019-08-25. |
|
|
|
