Deep Learning on 1-D Biosignals: a Taxonomy-based Survey

Nagarajan Ganapathy; Ramakrishnan Swaminathan; Thomas M. Deserno

doi:10.1055/s-0038-1667083

Yearbook of Medical Informatics, Table of Contents

CC BY-NC-ND 4.0 · Yearb Med Inform 2018; 27(01): 098-109
DOI: 10.1055/s-0038-1667083

Section 4: Sensor, Signal and Imaging Informatics

Survey

Georg Thieme Verlag KG Stuttgart

Deep Learning on 1-D Biosignals: a Taxonomy-based Survey

Authors

Nagarajan Ganapathy

¹Peter L. Reichertz Institute for Medical Informatics, University of Braunschweig — Institute of Technology and Hannover Medical School, Braunschweig, Germany

²Indian Institute of Technology Madras, Chennai, India
Ramakrishnan Swaminathan

²Indian Institute of Technology Madras, Chennai, India
Thomas M. Deserno

¹Peter L. Reichertz Institute for Medical Informatics, University of Braunschweig — Institute of Technology and Hannover Medical School, Braunschweig, Germany

Abstract

Summary

Objectives: Deep learning models such as convolutional neural networks (CNNs) have been applied successfully to medical imaging, but biomedical signal analysis has yet to fully benefit from this novel approach. Our survey aims at (i) reviewing deep learning techniques for biosignal analysis in computer- aided diagnosis; and (ii) deriving a taxonomy for organizing the growing number of applications in the field.

Methods: A comprehensive literature research was performed using PubMed, Scopus, and ACM. Deep learning models were classified with respect to the (i) origin, (ii) dimension, and (iii) type of the biosignal as input to the deep learning model; (iv) the goal of the application; (v) the size and (vi) type of ground truth data; (vii) the type and (viii) schedule of learning the network; and (ix) the topology of the model.

Results: Between January 2010 and December 2017, a total 71 papers were published on the topic. The majority (n = 36) of papers are on electrocariography (ECG) signals. Most applications (n = 25) aim at detection of patterns, while only a few (n = 6) at predection of events. Out of 36 ECG-based works, many (n = 17) relate to multi-lead ECG. Other biosignals that have been identified in the survey are electromyography, phonocardiography, photoplethysmography, electrooculography, continuous glucose monitoring, acoustic respiratory signal, blood pressure, and electrodermal activity signal, while ballistocardiography or seismocardiography have yet to be analyzed using deep learning techniques. In supervised and unsupervised applications, CNNs and restricted Boltzmann machines are the most and least frequently used, (n = 34) and (n = 15), respectively.

Conclusion: Our key-code classification of relevant papers was used to cluster the approaches that have been published to date and demonstrated a large variability of research with respect to data, application, and network topology. Future research is expected to focus on the standardization of deep learning architectures and on the optimization of the network parameters to increase performance and robustness. Furthermore, application-driven approaches and updated training data from mobile recordings are needed.

Keywords

Neural network - electrocardiography - electromyography - phonocardiography - photoplethysmography

Full Text

References

References
1 Silipo R, Marchesi C. Artificial neural networks for automatic ECG analysis. IEEE Trans Signal Process 1998; 46 (05) 1417-25
2 Bajaj V, Pachori RB. Automatic classification of sleep stages based on the time-frequency image of EEG signals. Comput Methods Programs Biomed 2013; 112 (03) 320-8
3 Karthick PA, Ramakrishnan S. Surface electromyography based muscle fatigue progression analysis using modified B distribution time – frequency features. Biomed Signal Process Control 2016; 26: 42-51
4 Alian AA, Shelley KH. Photoplethysmography. Best Pract Res Clin Anaesthesiol 2014; 28 (04) 395-406
5 Zink MD, Brüser C, Stüben BO, Napp A, Stöhr R, Leonhardt S. et al. Unobtrusive nocturnal heartbeat monitoring by a ballistocardiographic sensor in patients with sleep disordered breathing. Sci Rep 2017; 7 (01) 13175
6 Längkvist M, Karlsson L, Loutfi A. A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognit Lett 2014; 42 (01) 11-24
7 Deserno TM, Marx N. Computational Electrocardiography: revisiting holter ECG monitoring. Methods Inf Med 2016; 55 (04) 305-11
8 Movahedi F, Coyle JL, Sejdic E. Deep belief networks for electroencephalography: a review of recent contributions and future outlooks. IEEE J Biomed Health Inform 2018; 22 (03) 642-52
9 Esfandiari N, Babavalian MR, Moghadam AME, Tabar VK. Knowledge discovery in medicine: current issue and future trend. Expert Syst Appl 2014; 41 (09) 4434-63
10 Bengio Y, Georgios NY, Martinez HP. Learning deep physiological models of affect. IEEE Comput Intell Mag 2013; 8 (02) 20-33
11 Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. . Brief Bioinform 2017
12 Zhou FY, Jin LP, Dong J. Premature ventricular contraction detection combining deep neural networks and rules inference. Artif Intell Med 2017; 79: 42-51
13 Koelstra S, Muhl C, Soleymani M, Jong-Seok L, Yazdani A, Ebrahimi T. et al. DEAP: a database for emotion analysis using physiological signals. IEEE Trans Affect Comput 2012; 3 (01) 18-31
14 Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 2013; 35 (08) 1798-828
15 Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M. et al. A survey on deep learning in medical image analysis. Med Image Anal 2017; 42: 60-88
16 Schmidhuber J. Deep learning in neural networks: an overview. Neural Networks 2015; 61: 85-117
17 Suzuki K. Overview of deep learning in medical imaging. Radiol Phys Technol 2017; 10 (03) 257-73
18 Faust O, Acharya UR, Tamura T. Formal design methods for reliable computer-aided diagnosis: a review. IEEE Rev Biomed Eng 2012; 5: 15-28
19 Kiranyaz S, Ince T, Gabbouj M. Personalized monitoring and advance warning system for cardiac arrhythmias. Sci Rep 2017; 7 (01) 1-8
20 Luo J, Wu M, Gopukumar D, Zhao Y. Big data application in biomedical research and health care: a literature review. Biomed Inform Insights 2016; 8: 1-10
21 Critchley HD, Garfinkel SN. The influence of physiological signals on cognition. Curr Opin Behav Sci 2018; 19: 13-8
22 Degoulet P, Fieschi M. Introduction to clinical informatics. New York: Springer Publications; 2012
23 Zhang Q, Chen X, Zhan Q, Yang T, Xia S. Respiration- based emotion recognition with deep learning. Comput Ind 2017; 92: 84-90
24 Peng L, Hou Z, Chen Y, Wang W, Tong L, Li P. Combined use of sEMG and accelerometer in hand motion classification considering forearm rotation. Proc IEEE EMBC; 2013. p. 4227–30
25 Kiranyaz S, Ince T, Gabbouj M. Personalized ECG classification. In: In Multidimensional Particle Swarm Optimization for Machine Learning and Pattern Recognition. Berlin, Springer; 2014: 231–58
26 Maestri R, Pinna GD, Porta A, Balocchi R, Sassi R, Signorini MG. et al. Assessing nonlinear properties of heart rate variability from short-term recordings: are these measurements reliable?. Physiol Meas 2007; 28 (09) 1067-77
27 Karthick PA, Venugopal G, Ramakrishnan S. Analysis of muscle fatigue progression using cyclostationary property of surface electromyography signals. J Med Syst 2016; 40 (01) 28
28 Allen J. Photoplethysmography and its application in clinical physiological measurement. Physiol Meas 2007; 28 (03) R1
29 Inan OT, Migeotte P, Park K, Etemadi M, Tavakolian K, Casanella R. et al. Ballistocardiography and seismocardiography: a review of recent advances. IEEE J Biomed Health Inform 2015; 19 (04) 1414-27
30 Zhang Q, Zhou D, Zeng X. Heartid: a multiresolution convolutional neural network for ECG-based biometric human identification in smart health applications. IEEE Access 2017; 5: 11805-16
31 Dong H, Supratak A, Pan W, Wu C, Matthews PM, Guo Y. Mixed neural network approach for temporal sleep stage classification. IEEE Trans Neural Syst Rehabil Eng 2017; 26: 324-33
32 Huigen E, Peper A, Grimbergen CA. Investigation into the origin of the noise of surface electrodes. Med Biol Eng Comput 2002; 40 (03) 332-8
33 Kashif M, Jonas S, Deserno T. Deterioration of R-wave detection in pathology and noise: a comprehensive analysis using simultaneous truth and performance level estimation. IEEE Trans Biomed Eng 2017; 64 (09) 2163-75
34 Deng L, Yu D. Deep learning: methods and applications Found Trends^® . Signal Process 2013; 7 (3–4): 197-387
35 Bengio Y. Learning deep architectures for AI. Found Trends^® . Mach Learn 2009; 2 (01) 1-27
36 Wang HZ, Wang GB, Li GQ, Peng JC, Liu YT. Deep belief network based deterministic and probabilistic wind speed forecasting approach. 2016; 182: 80-93
37 Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets. Neural Comput 2006; 18 (07) 1527-54
38 Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS. Deep learning for visual understanding: a review. Neurocomputing 2016; 187: 27-48
39 Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. . Comput Biol Med 2017
40 Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Proc NIPS; 2012. p. 1097–105
41 Sutskever I, Martens J, Hinton GE. Generating text with recurrent neural networks. Proc ICML; 2011. p. 1017–24
42 Deng L. A tutorial survey of architectures, algorithms, and applications for deep learning. APSIPA Trans Signal Inf Process 2014; 3: E2
43 Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput 1997; 9 (08) 1735-80
44 Al Rahhal MM, Bazi Y, Alhichri H, Alajlan N, Melgani F, Yager RR. Deep learning approach for active classification of electrocardiogram signals. Inf Sci (Ny) 2016; 345: 340-54
45 Lei X, Zhang Y, Lu Z. Deep learning feature representation for electrocardiogram identification. Proc DSP; 2016
46 Acharya UR, Fujita H, Oh SL, Hagiwara Y, Tan JH, Adam M. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf Sci (Ny) 2017; 415: 190-8
47 Šarlija M, Jurišiæ F, Popoviæ S. A convolutional neural network based approach to QRS detection. Proc IEEE ISPA; 2017. p. 121–5
48 Acharya UR, Fujita H, Lih OS, Adam M, Tan JH, Chua CK. Automated detection of coronary artery disease using different durations of ECG segments with convolutional neural network. Knowledge-Based Syst 2017; 132: 62-71
49 Acharya UR, Fujita H, Lih OS, Hagiwara Y, Tan JH, Adam M. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inf Sci (Ny) 2017; 405: 81-90
50 Gogna A, Majumdar A, Ward R, Gogna A, Ward R. Semi-supervised stacked label consistent autoencoder for reconstruction and analysis of biomedical signals. IEEE Trans Biomed Eng 2017; 64 (09) 2196-205
51 Muduli PR, Gunukula RR, Mukherjee A. A deep learning approach to fetal-ECG signal reconstruction. Proc IEEE NCC; 2016. p. 1–6
52 Xiong P, Wang H, Liu M, Zhou S, Hou Z, Liu X. ECG signal enhancement based on improved denoising auto-encoder. Eng Appl Artif Intell 2016; 52: 194-202
53 Xiong P, Wang H, Liu M, Lin F, Hou Z, Liu X. A stacked contractive denoising auto-encoder for ECG signal denoising. Physiol Meas 2016; 37 (12) 2214-22
54 Jindal V, Birjandtalab J, Pouyan MB, Nourani M. An adaptive deep learning approach for PPG-based identification. Proc IEEE EMBC; 2016. p. 6401–4
55 Yin W, Yang X, Zhang L, Oki E. ECG monitoring system integrated with ir-uwb radar based on cnn. IEEE Access 2016; 4: 6344-51
56 Liu W, Zhang M, Zhang Y, Liao Y, Huang Q, Chang S. et al. Real-time multilead convolutional neural network for myocardial infarction detection. . IEEE J Biomed Health Inform 2017
57 Shashikumar SP, Shah AJ, Li Q, Clifford GD, Nemati S. A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology. Proc IEEE EMBC; 2017. p. 141–4
58 Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adam M, Gertych A. et al. A deep convolutional neural network model to classify heartbeats. Comput Biol Med 2017; 89: 389-96
59 Zubair M, Kim J, Yoon C. An automated ECG beat classification system using convolutional neural networks. Proc ICITCS; 2016
60 Kiranyaz S, Ince T, Gabbouj M. Real-time patient- specific ECG classification by 1-d convolutional neural networks. IEEE Trans Biomed Eng 2016; 63 (03) 664-75
61 Pourbabaee B, Roshtkhari MJ, Khorasani K. Deep convolutional neural networks and learning ECG features for screening paroxysmal atrial fibrillation patients. IEEE Trans Syst Man, Cybern Syst 2017; 99: 1-10
62 Salloum R, Kuo CCJ. ECG-based biometrics using recurrent neural networks. Proc IEEE ICASSP; 2017
63 Qiu Y, Xiao F, Shen H. Elimination of power line interference from ECG signals using recurrent neural networks. Proc IEEE EMBC; 2017
64 Jin L, Dong J. Classification of normal and abnormal ECG records using lead convolutional neural network and rule inference. Sci China Inf Sci 2017; 60 (07) 1-3
65 Ryu H, Park J, Shin H. Classification of heart sound recordings using convolution neural network. Proc CinC; 2016. p. 1153–6
66 San PP, Ling SH, Nguyen HT. Deep learning framework for detection of hypoglycemic episodes in children with type 1 diabetes. Proc IEEE EMBC; 2016. p. 3503-6
67 Thomae C, Dominik A. Using deep gated rnn with a convolutional front end for end:to:end classification of heart sound. Proc CinC; 2016. p. 625–8
68 Taji B, Chan ADC, Shirmohammadi S. False alarm reduction in atrial fibrillation detection using deep belief networks. IEEE Trans Instrum Meas 2017; 67 (05) 1124-31
69 Majumdar A, Ward R. Robust greedy deep dictionary learning for ECG arrhythmia classification. Proc IJCNN; 2017. p. 4400-7
70 Wu Z, Ding X, Zhang G. A novel method for classification of ECG arrhythmias using deep belief networks. . Int J Comput Intell Appl 2016 ; 15(4).
71 Taji B, Chan ADC, Shirmohammadi S. Classifying measured electrocardiogram signal quality using deep belief networks. Proc IEEE I2MTC; 2017. p. 1–6
72 Chen W, Liu G, Su S, Jiang Q, Fellow I, Nguyen H. et al. A CHF detection method based on deep learning with RR intervals. Proc IEEE EMBC; 2017. p. 3369–72
73 Sch C, Dominik A. Can electrocardiogram classification be applied to phonocardiogram data – an analysis using recurrent neural networks. Proc CinC; 2016. p. 581–4
74 Pathinarupothi RK, Vinaykumar R, Rangan E, Gopalakrishnan E, Soman KP. Instantaneous heart rate as a robust feature for sleep apnea severity detection using deep learning. Proc IEEE EMBC 2017. p. 293–6
75 Luo K, Li J, Wang Z, Cuschieri A. Patient-specific deep architectural model for ECG classification. . J Healthc Eng 2017
76 Zhu X, Zheng WL, Lu BL, Chen X, Chen S, Wang C. EOG-based drowsiness detection using convolutional neural networks. Proc IJCNN; 2014. p. 128–34
77 Yao Z, Zhu Z, Chen Y. Atrial fibrillation detection by multi-scale convolutional neural networks. Proc IEEE ICIF; 2017. p. 1–6
78 Su Y, Sun S, Ozturk Y, Tian M. Measurement of upper limb muscle fatigue using deep belief networks. . J Mech Med Biol 2016 ; 16(8).
79 Mohebbi A, Arad TB, Johansen AR, Bengtsson H, Fraccaro M, M⊘rup M. A deep learning approach to adherence detection for type 2 diabetics. Proc IEEE EMBC; 2017. p. 2896–9
80 Jun TJ, Park HJ, Minh NH, Kim D, Kim YH. Premature ventricular contraction beat detection with deep neural networks. Proc ICMLA; 2016. p. 859–64
81 Atzori M, Cognolato M, Müller H, Wininger M, Samuel Smith L, Kleinhans A. Deep learning with convolutional neural networks applied to electromyography data: a resource for the classification of movements for prosthetic hands. Front Neurorobot 2016; 10: 9
82 Potes C, Parvaneh S, Rahman A, Conroy B. Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. Proc IEEE CinC; 2016. p. 621–4
83 Zheng G, Ji S, Dai M, Sun Y. ECG based identification by deep learning.Proc CCBR; 2017. p. 503–10
84 Shim HM, An H, Lee S, Lee EH, Min HK, Lee S. EMG pattern classification by split and merge deep belief network. Symmetry (Basel) 2016; 8 (12) 148
85 Shim H, Lee S. Multi-channel electromyography pattern classification using deep belief networks for enhanced user experience. J Cent South Univ 2015; 22 (05) 1801-8
86 Chen TE, Yang SI, Ho LT, Tsai KH, Chen YH, Chang YF. , et al. S1 and s2 heart sound recognition using deep neural networks. IEEE Trans Biomed Eng 2017; 64 (02) 372-80
87 Yang T, Yu L, Jin Q, Wu L, He B. Localization of origins of premature ventricular contraction by means of convolutional neural network from 12-lead ECG. . IEEE Trans Biomed Eng 2017
88 Xia P, Hu J, Peng Y. EMG-based estimation of limb movement using deep learning with recurrent convolutional neural networks. Artif Organs 2018; 42 (05) E67-E77
89 Sunjing Lifu K, Weilian W Songshaoshuai. Heart sound signals based on cnn classification research. Proc ICBBS; 2017. p. 44–8
90 Ribas Ripoll VJ, Wojdel A, Romero E, Ramos P, Brugada J. ECG assessment based on neural networks with pretraining. Appl Soft Comput J 2016; 49: 399-406
91 Sengur A, Akbulut Y, Guo Y, Bajaj V. Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm. Heal Inf Sci Syst 2017; 5 (01) 9
92 Maknickas V, Maknickas A. Recognition of normal – abnormal phonocardiographic signals using deep convolutional neural networks and mel-frequency spectral coefficients. Physiol Meas 2017; 38 (08) 1671-84
93 Xia Y, Wulan N, Wang K, Zhang H. Detecting atrial fibrillation by deep convolutional neural networks. Comput Biol Med 2018; 93: 84-92
94 Isin A, Ozdalili S. Cardiac arrhythmia detection using deep learning. Procedia Comput Sci 2017; 120: 268-75
95 Cote-Allard U, Fall CL, Campeau-Lecours A, Gosselin C, Laviolette F, Gosselin B. Transfer learning for sEMG hand gestures recognition using convolutional neural networks.Proc IEEE SMC; 2017. p. 1663–8
96 Lee S, Chang JH. Deep learning ensemble with asymptotic techniques for oscillometric blood pressure estimation. Comput Methods Programs Biomed 2017; 151: 1-13
97 Wei W, Wong Y, Du Y, Hu Y, Kankanhalli M, Geng W. A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface. . Pattern Recognit Lett 2017
98 Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, Jimenez-Moreno G. Deep neural networks for the recognition and classification of heart murmurs using neuromorphic auditory sensors. IEEE Trans Biomed Circuits Syst 2018; 12 (01) 24-34
99 Rubin J, Abreu R, Ganguli A, Nelaturi S, Matei I, Sricharan K. Classifying heart sound recordings using deep convolutional neural networks and mel:frequency cepstral coefficients. Proc CinC; 2016. p. 813–6
100 Nilanon T, Yao J, Hao J, Purushotham S, Liu Y. Normal / abnormal heart sound recordings classification using convolutional neural network. Proc CinC; 2016. p. 585–8
101 Belo D, Rodrigues J, Vaz JR, Pezarat-Correia P, Gamboa H. Biosignals learning and synthesis using deep neural networks. Biomed Eng Online 2017; 16 (01) 115
102 Zhang J, Wu Y, Bai J, Chen F. Automatic sleep stage classification based on sparse deep belief net and combination of multiple classifiers. Trans Inst Meas Control 2016; 38 (04) 435-51
103 Chow C. Deepbufs: deep learned biometric user feedback system. Proc ACM DIS 2017. p. 150–4
104 Yin Z, Wang Y, Zhang W, Liu L, Zhang J, Han F. et al. Physiological feature based emotion recognition via an ensemble deep autoencoder with parsimonious structure. IFAC-PapersOn- Line 2017; 50 (01) 6940-5
105 Yin Z, Zhao M, Wang Y, Yang J, Zhang J. Recognition of emotions using multimodal physiological signals and an ensemble deep learning model. Comput Methods Programs Biomed 2017; 140: 93-110
106 Kim H, Lee SB, Son Y, Czosnyka M, Kim DJ. Hemodynamic instability and cardiovascular events after traumatic brain injury predict outcome after artifact removal with deep belief network analysis. . J Neurosurg Anesthesiol 2017
107 Pan F, He P, Liu C, Li T, Murray A, Zheng D. Variation of the korotkoff stethoscope sounds during blood pressure measurement: analysis using a convolutional neural network. IEEE J Biomed Heal Informatics 2017; 21 (06) 1593-8
108 Lee S, Chang JH. Deep belief networks ensemble for blood pressure estimation. IEEE Access 2017; 5: 9962-72
109 Lee S, Chang JH. Oscillometric blood pressure estimation based on deep learning. IEEE Trans Ind Inform 2017; 13 (02) 461-72
110 Moody GB, Mark RG. The impact of the mit-bih arrhythmia database. IEEE Eng Med Biol Mag 2001; 20 (03) 45-50
111 Jin L, Dong J. Ensemble deep learning for biomedical time series classification. . Comput Intell Neurosci 2016
112 Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG. et al. PhysioBank, physiotoolkit, and physionet components of a new research resource for complex physiologic signals. Circulation 2000; 101 (23) E215-E220
113 Greenwald SD, Patil RS, Mark RG. Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information. Biomed Instrum Technol 1992; 26 (02) 124-32
114 Bousseljot R, Kreiseler D, Schnabel A. Nutzung der EKG-signaldatenbank cardiodat der ptb über das internet. Biomed Tech Eng 2009; 40 (s1): 317-8
115 Iyengar N, Peng CK, Morin R, Goldberger AL, Lipsitz LA. Age-related alterations in the fractal scaling of cardiac interbeat interval dynamics. Am J Physiol Integr Comp Physiol 1996; 271 (04) R1078-R1084
116 Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ. et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas 2016; 37 (12) 2181-213
117 Moody GB, Goldberger A, McClennen S. Predicting the onset of paroxysmal atrial fibrillation: Proc IEEE CinC; 2001. p. 113–6

Supplementary Material

Supplementary Material (PDF) (opens in new window)