Hidden Markov model-based heartbeat detector using electrocardiogram and arterial pressure signals

다국어 초록 (Multilingual Abstract)

The automatic detection of a heartbeat is commonly performed by detecting the QRS complex in the electrocardiogram(ECG), however, various noise sources and missing data can jeopardize the reliability of the ECG. Therefore, there is agrowing interest in combining the information from many physiological signals to accurately detect heartbeats. To this end,hidden Markov models (HMMs) are used in this work to jointly exploit the information from ECG, arterial blood pressure(ABP) and pulmonary arterial pressure (PAP) signals in order to conceive a heartbeat detector. After preprocessing the physiologicalsignals, a sliding window is used to extract an observation sequence to be passed through two HMMs (previouslytrained on a training dataset) in order to obtain the log-likelihoods of observation and signals a detection if the diff erenceof log-likelihoods exceeds an adaptive threshold. Several HMM-based heartbeat detectors were conceived to exploit theinformation from the ECG, ABP and PAP signals from the MIT-BIH Arrhythmia, PhysioNet Computing in CardiologyChallenge 2014, and MGH/MF Waveform databases. A grid search methodology was used to optimize the duration of theobservation sequence and a multiplicative factor to form the adaptive threshold. Using the optimal parameters found ona training database through 10-fold cross-validation, sensitivity and positive predictivity above 99% were obtained on theMIT-BIH Arrhythmia and PhysioNet Computing in Cardiology Challenge 2014 databases, while they are above 95% in theMGH/MF waveform database using ECG and ABP signals. Our detector approach showed detection performances comparablewith the literature in the three databases.

참고문헌 (Reference)

1 Park S, "Wearable sensors" Academic Press 3-27, 2021

2 Yiran Yang, "Wearable and flexible electronics for continuous molecular monitoring" Royal Society of Chemistry (RSC) 48 (48): 1465-1491, 2019

3 Michael Klum, "Wearable Cardiorespiratory Monitoring Employing a Multimodal Digital Patch Stethoscope: Estimation of ECG, PEP, LVET and Respiration Using a 55 mm Single-Lead ECG and Phonocardiogram" MDPI AG 20 (20): 2033-, 2020

4 Monroy NF, "VIII Latin American Conference on Biomedical Engineering and XLII National Conference on Biomedical Engineering" Springer 208-217, 2019

5 A. G. Ramakrishnan, "Threshold-Independent QRS Detection Using the Dynamic Plosion Index" Institute of Electrical and Electronics Engineers (IEEE) 21 (21): 554-558, 2014

6 Charles E. Leiserson, "There’s plenty of room at the Top: What will drive computer performance after Moore’s law?" American Association for the Advancement of Science (AAAS) 368 (368): 2020

7 Welch J, "The massachusetts general hospital-marquette foundation hemodynamic and electrocardiographic database-comprehensive collection of critical care waveforms" 7 (7): 96-97, 1991

8 G.B. Moody, "The impact of the MIT-BIH Arrhythmia Database" Institute of Electrical and Electronics Engineers (IEEE) 20 (20): 45-50, 2001

9 Instituto Nacional de Salud, "Segundo informe ONS observatorio nacional de salud: mortalidad 1998-2011 y situación de salud en los municipios de frontera terrestre en colombia"

10 Hayes MH, "Schaum’s outline of theory and problems of digital signal processing" Mc Graw Hill 1999

11 Zahra Rezaei Khavas, "Robust heartbeat detection using multimodal recordings and ECG quality assessment with signal amplitudes dispersion" Elsevier BV 163 : 169-182, 2018

12 Jeon T, "Robust detection of heartbeats using association models from blood pressure and eeg signals" 15 (15): 7-, 2016

13 Pangerc U, "Robust detection of heart beats in multimodal records using slope-and peak-sensitive band-pass filters" 36 (36): 1645-, 2015

14 Silva I, "Robust detection of heart beats in multimodal data" 36 (36): 1629-, 2015

15 Ding Q, "Robust QRS peak detection by multimodal information fusion of ECG and blood pressure signals" 37 (37): N84-, 2016

16 Michael R. Schwob, "Robust Multimodal Heartbeat Detection Using Hybrid Neural Networks" Institute of Electrical and Electronics Engineers (IEEE) 8 : 82201-82214, 2020

17 B. S. Chandra, "Robust Heartbeat Detection From Multimodal Data via CNN-Based Generalizable Information Fusion" Institute of Electrical and Electronics Engineers (IEEE) 66 (66): 710-717, 2019

18 S.R. Seydnejad, "Real-time heart rate variability extraction using the Kaiser window" Institute of Electrical and Electronics Engineers (IEEE) 44 (44): 990-1005, 1997

19 Chen H, "Probabilistic model-based approach for heart beat detection" 37 (37): 1404-, 2016

20 Zia T, "Probabilistic data fusion model for heart beat detection from multimodal physiological data" 25 (25): 449-460, 2017

21 Silvio Barra, "PhysioUnicaDB: a dataset of EEG and ECG simultaneously acquired" Elsevier BV 126 : 119-122, 2019

22 Goldberger AL, "PhysioBank, PhysioToolkit, and PhysioNet : components of a new research resource for complex physiologic signals" 101 (101): e215-e220, 2000

23 Sulistyaningsih PP, "Performance comparison of Blackman, Bartlett, Hanning, and Kaiser window for radar digital signal processing" IEEE 391-394, 2019

24 Ledezma CA, "Optimal data fusion for the improvement of qrs complex detection in multi-channel ECG recordings" 57 (57): 1673-1681, 2019

25 Altuve M, "Online apnea-bradycardia detection based on hidden semi-Markov models" 53 (53): 1-13, 2015

26 Kaiser JF, "Nonrecursive digital filter design using the i＼_0-sinh window function" 20-23, 1974

27 Javier Tejedor, "Multiple Physiological Signals Fusion Techniques for Improving Heartbeat Detection: A Review" MDPI AG 19 (19): 4708-, 2019

28 Johnson AE, "Multimodal heart beat detection using signal quality indices" 36 (36): 1665-, 2015

29 Meryem Regouid, "Multimodal biometric system for ECG, ear and iris recognition based on local descriptors" Springer Science and Business Media LLC 78 (78): 22509-22535, 2019

30 Kaylie Welykholowa, "Multimodal Photoplethysmography-Based Approaches for Improved Detection of Hypertension" MDPI AG 9 (9): 1203-, 2020

31 Altuve M, "Multiclass classification of metabolic conditions using fasting plasma levels of glucose and insulin" 1-10, 2021

32 Dumont J, "Modelling temporal evolution of cardiac electrophysiological features using hidden semi-Markov models" IEEE 165-168, 2008

33 M.J.F. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition" Elsevier BV 12 (12): 75-98, 1998

34 Welch LR, "Hidden markov models and the Baum-Welch algorithm" 53 (53): 10-13, 2003

35 Murphy, K, "Hidden markov model (HMM) toolbox for Matlab"

36 Marti UV, "Hidden Markov models: applications in computer vision" World Scientific 65-90, 2001

37 Monroy, N.F., "Hidden Markov model-based heartbeat detector using different transformations of ECG and ABP signals" 11330 : 211-219, 2020

38 Omkar Singh, "Heartbeat detection in multimodal physiological signals using signal quality assessment based on sample entropy" Springer Science and Business Media LLC 40 (40): 917-923, 2017

39 Mollakazemi MJ, "Heart beat detection using a multimodal data coupling method" 36 (36): 1729-, 2015

40 Pimentel MA, "Heart beat detection in multimodal physiological data using a hidden semi-Markov model and signal quality indices" 36 (36): 1717-, 2015

41 De Cooman T, "Heart beat detection in multimodal data using automatic relevant signal detection" 36 (36): 1691-, 2015

42 Jianying Hu, "HMM based online handwriting recognition" Institute of Electrical and Electronics Engineers (IEEE) 18 (18): 1039-1045, 1996

43 Elgendi M, "Frequency bands effects on QRS detection" 428-431, 2010

44 Mohamed Elgendi, "Fast QRS Detection with an Optimized Knowledge-Based Method: Evaluation on 11 Standard ECG Databases" Public Library of Science (PLoS) 8 (8): e73557-, 2013

45 Mozaffarian D, "Executive summary : Heart disease and stroke statistics-2016update : A report from the american heart association" 133 (133): 447-454, 2016

46 Nitish V. Thakor, "Estimation of QRS Complex Power Spectra for Design of a QRS Filter" Institute of Electrical and Electronics Engineers (IEEE) BME-31 (BME-31): 702-706, 1984

47 A. Viterbi, "Error bounds for convolutional codes and an asymptotically optimum decoding algorithm" Institute of Electrical and Electronics Engineers (IEEE) 13 (13): 260-269, 1967

48 Ashish Kumar, "Efficient QRS complex detection algorithm based on Fast Fourier Transform" 대한의용생체공학회 9 (9): 145-151, 2019

49 Hernández AI, "ECG Signal Processing. Classification and Interpretation: A Comprehensive Framework of Computational Intelligence" Springer 237-273, 2012

50 Qiong Yu, "ECG R-wave peaks marking with simultaneously recorded continuous blood pressure" Public Library of Science (PLoS) 14 (14): e0214443-, 2019

51 Rahul J, "Dynamic thresholding based efficient qrs complex detection with low computational overhead" 67 (67): 519-, 2021

52 Oppenheim AV, "Discrete-time signal processing" Pearson 2010

53 Lakhwani R, "Design and comparison of digital filters for removal of baseline wandering from ECG signal" IEEE 186-191, 2013

54 Vivek Singh, "Comparative study of FIR and IIR filters for the removal of 50 Hz noise from EEG signal" Inderscience Publishers 22 (22): 250-257, 2016

55 Soo-Yeon Han, "Classification of pilots’ mental states using a multimodal deep learning network" Elsevier BV 40 (40): 324-336, 2020

56 Mehmet Eyuboglu, "Characteristics of Circadian Blood Pressure Pattern of Hypertensive Patients According to Localization of Fragmented QRS on Electrocardiography" Springer Science and Business Media LLC 28 (28): 57-62, 2021

57 Xiang Y, "Automatic qrs complex detection using two-level convolutional neural network" 17 (17): 1-17, 2018

58 Llamedo M, "Assessment of automatic strategies for combining qrs detections by multiple algorithms in multiple leads" 40 (40): 114002-, 2019

59 Mollakazemi MJ, "Applying quality index criterion for flexible multi-detection of heartbeat using features of multimodal data" IEEE 1065-1068, 2016

60 Monroy NF, "Analysis of the observation sequence duration of hidden markov models for QRS complex detection in single-lead ECG recordings" IEEE 45 : 1-4, 2018

61 Zong W, "An open-source algorithm to detect onset of arterial blood pressure pulses" IEEE 259-262, 2003

62 Nayak C, "An efficient and robust digital fractional order differentiator based ecg pre-processor design for qrs detection" 13 (13): 682-696, 2019

63 Ikaro Silva, "An Open-source Toolbox for Analysing and Processing PhysioNet Databases in MATLAB and Octave" Ubiquity Press, Ltd. 2 : 2014

64 American National Standard, "ANSI/AAMI EC57:1998, Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algorithms"

65 American National Standard, "ANSI/AAMI EC38:1998, Ambulatory Electrocardiographs"

66 L.R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition" Institute of Electrical and Electronics Engineers (IEEE) 77 (77): 257-286, 1989

67 Omkar Singh, "A new approach for identification of heartbeats in multimodal physiological signals" Informa UK Limited 42 (42): 182-186, 2018

68 Jiapu Pan, "A Real-Time QRS Detection Algorithm" Institute of Electrical and Electronics Engineers (IEEE) 3 : 230-236, 1985