Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction
Abstract
:1. Introduction
- (1)
- The novel machine learning framework can intelligently and systematically identify the heartbeats from a noisy and subtle mobile ECG, localize the ECG QRS complexes, purify the complexes, and transform the mobile ECG QRS durations to the standard chest ECG QRS durations.
- (2)
- The support vector machine classifier determines the raw heartbeats from the signal spikes, which include both real and false heartbeats that are due to the motion artifacts.
- (3)
- The ECG QRS localization step leverages the multiview dynamic time warping for sophisticated pattern matching, to compare a given raw heartbeat with the high-quality heartbeat template determined using the k-medoid clustering method.
- (4)
- The purification step further leverages the pattern matching scores to generate the signal quality indices and boost the performance.
- (5)
- The transformation of mobile ECG QRS durations to the commonly used standard chest ECG QRS durations facilitates the convenient usage of the extracted cardiac pattern.
2. Materials and Methods
2.1. System Overview
2.2. Stage I: ECG Heartbeat Identification
2.3. Stage II: QRS Localization and then Purification
2.3.1. Representative Heartbeat Template Learning by K-Medoid Clustering
2.3.2. QRS Localization by Multiview Dynamic Time Warping
2.3.3. Heartbeat Distortion Quantization
2.3.4. Distortion Threshold Learning by Histogram Triangle Search
2.3.5. QRS Purification
2.4. Stage III: QRS Duration Calibration
2.4.1. QRS Duration Estimation
2.4.2. Mobile QRS Duration to Chest QRS Duration Calibration
3. Results and Discussion
3.1. Experimental Setup
3.2. Heartbeat Identification
3.3. Representative Heartbeat Learned by Clustering
3.4. QRS Located by Multiview DTW
3.5. Distortion Quantization and Threshold Learning
3.6. Heartbeat Quality Labelling and Purification
3.7. Mobile QRS to Chest QRS Calibration
3.8. Performance Summary
3.9. Future Studies
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- WHO. The 10 Leading Causes of Death in the World. 2014. Available online: http://www.who.int/mediacentre/factsheets/fs310/en/ (accessed on 20 May 2023).
- Maron, B.J.; Friedman, R.A.; Kligfield, P.; Levine, B.D.; Viskin, S.; Chaitman, B.R.; Okin, P.M.; Saul, J.P.; Salberg, L.; Van Hare, G.F. Assessment of the 12-Lead ECG as a Screening Test for Detection of Cardiovascular Disease in Healthy General Populations of Young People (12–25 Years of Age). Circulation 2014, 130, 1303–1334. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Alhussein, M.; Muhammad, G.; Hossain, M.S. EEG pathology detection based on deep learning. IEEE Access 2019, 7, 27781–27788. [Google Scholar] [CrossRef]
- Amin, F.-E.; Hussain, M.; Ali, Z.; Busaleh, M.; Al Sultan, S.A. Development of a Secure Cloud-based Breast Cancer Diagnosis System. In Proceedings of the 2022 6th International Conference on Cloud and Big Data Computing, Birmingham, UK, 18–20 August 2022; pp. 42–48. [Google Scholar]
- Abdul, W.; Ali, Z.; Ghouzali, S.; Alfawaz, B.; Muhammad, G.; Hossain, M.S. Biometric security through visual encryption for fog edge computing. IEEE Access 2017, 5, 5531–5538. [Google Scholar] [CrossRef]
- Wang, R.; Lai, J.; Zhang, Z.; Li, X.; Vijayakumar, P.; Karuppiah, M. Privacy-preserving federated learning for internet of medical things under edge computing. IEEE J. Biomed. Health Inform. 2023, 27, 854–865. [Google Scholar] [CrossRef] [PubMed]
- Andreu-Perez, J.; Perez-Espinosa, H.; Timonet, E.; Kiani, M.; Girón-Pérez, M.I.; Benitez-Trinidad, A.B.; Jarchi, D.; Rosales-Pérez, A.; Gatzoulis, N.; Reyes-Galaviz, O.F. A generic deep learning based cough analysis system from clinically validated samples for point-of-need COVID-19 test and severity levels. IEEE Trans. Serv. Comput. 2021, 15, 1220–1232. [Google Scholar] [CrossRef] [PubMed]
- Ahmed, J.; Nguyen, T.N.; Ali, B.; Javed, M.A.; Mirza, J. On the physical layer security of federated learning based IoMT networks. IEEE J. Biomed. Health Inform. 2022, 27, 691–697. [Google Scholar] [CrossRef]
- Zhang, Q.; Frick, K. All-ECG: A Least-Number of Leads ECG Monitor for Standard 12-Lead ECG Tracking During Motion. In Proceedings of the 6th Annual IEEE EMB Strategic Conference on Healthcare Innovations and Point-Of-Care Technologies (IEEE HI-POCT 2019), Bethesda, MD, USA, 20–22 November 2019; pp. 103–106. [Google Scholar]
- Pantelopoulos, A.; Bourbakis, N.G. A survey on wearable sensor-based systems for health monitoring and prognosis. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 2010, 40, 1–12. [Google Scholar] [CrossRef] [Green Version]
- Zhang, Q.; Zhou, D.; Zeng, X. A Novel Framework for Motion-tolerant Instantaneous Heart Rate Estimation By Phase-domain Multi-view Dynamic Time Warping. IEEE Trans. Biomed. Eng. 2017, 64, 2562–2574. [Google Scholar]
- Zhang, Q.; Zhou, D.; Zeng, X. Hear the heart: Daily cardiac health monitoring using Ear-ECG and machine learning. In Proceedings of the 8th IEEE Ubiquitous Computing, Electronics and Mobile Communication Conference (IEEE UEMCON), New York, NY, USA, 19–21 October 2017; pp. 448–451. [Google Scholar]
- Zou, J.; Zhang, Q. eyeSay: Eye Electrooculography Decoding with Deep Learning. In Proceedings of the 2021 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 10–12 January 2021; pp. 1–3. [Google Scholar]
- Nanhore, S.D.; Bartere, M.M. Mobile phone sensing system for health monitoring. Int. J. Sci. Res. 2013, 2, 252–255. [Google Scholar]
- Hsieh, J.-H.; Hung, K.-C.; Lin, Y.-L.; Shih, M.-J. A speed-and power-efficient SPIHT design for wearable quality-on-demand ECG applications. IEEE J. Biomed. Health Inform. 2017, 22, 1456–1465. [Google Scholar] [CrossRef]
- Zhang, Q. Deep Learning of Electrocardiography Dynamics for Biometric Human Identification in era of IoT. In Proceedings of the 9th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (IEEE UEMCON), New York, NY, USA, 8–10 November 2018; pp. 885–888. [Google Scholar]
- Oliver, N.; Flores-Mangas, F.; De Oliveira, R. Towards wearable physiological monitoring on a mobile phone. In Mobile Health Solutions for Biomedical Applications; IGI Global: Hershey, PA, USA, 2009; pp. 208–243. [Google Scholar]
- Almotiri, S.H.; Khan, M.A.; Alghamdi, M.A. Mobile health (m-health) system in the context of IoT. In Proceedings of the 2016 IEEE 4th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW), Vienna, Austria, 22–24 August 2016; pp. 39–42. [Google Scholar]
- Zhang, Q.; Zhu, S. Real-time Activity and Fall Risk Detection for Aging Population Using Deep Learning. In Proceedings of the 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (IEEE UEMCON), New York, NY, USA, 8–10 November 2018; pp. 1055–1059. [Google Scholar]
- Zhang, Q. Deep Learning of Biomechanical Dynamics in Mobile Daily Activity and Fall Risk Monitoring. In Proceedings of the 6th Annual IEEE EMB Strategic Conference on Healthcare Innovations and Point-of-Care Technologies (IEEE HI-POCT 2019), Bethesda, MD, USA, 20–22 November 2019. [Google Scholar]
- Maji, S.; Burke, M.J. Establishing the Input Impedance Requirements of ECG Recording Amplifiers. IEEE Trans. Instrum. Meas. 2020, 69, 825–835. [Google Scholar] [CrossRef]
- Zhang, Q.; Zeng, X.; Hu, W.; Zhou, D. A Machine Learning-empowered System for Long-term Motion-tolerant Wearable Monitoring of Blood Pressure and Heart Rate with Ear-ECG/PPG. IEEE Access 2017, 5, 10547–10561. [Google Scholar] [CrossRef]
- Teodorescu, C.; Reinier, K.; Uy-Evanado, A.; Navarro, J.; Mariani, R.; Gunson, K.; Jui, J.; Chugh, S.S. Prolonged QRS duration on the resting ECG is associated with sudden death risk in coronary disease, independent of prolonged ventricular repolarization. Heart Rhythm 2011, 8, 1562–1567. [Google Scholar] [CrossRef] [Green Version]
- Van Huysduynen, B.H.; van Straten, A.; Swenne, C.A.; Maan, A.C.; van Eck, H.J.R.; Schalij, M.J.; van der Wall, E.E.; de Roos, A.; Hazekamp, M.G.; Vliegen, H.W. Reduction of QRS duration after pulmonary valve replacement in adult Fallot patients is related to reduction of right ventricular volume. Eur. Heart J. 2005, 26, 928–932. [Google Scholar] [CrossRef]
- Kurl, S.; Mäkikallio, T.; Rautaharju, P.; Kiviniemi, V.; Laukkanen, J.A. The duration of QRS complex in resting electrocardiogram is a predictor of sudden cardiac death in men. Circulation 2012, 125, 2588–2594. [Google Scholar] [CrossRef] [Green Version]
- Yokokawa, M.; Kim, H.M.; Good, E.; Crawford, T.; Chugh, A.; Pelosi, F.; Jongnarangsin, K.; Latchamsetty, R.; Armstrong, W.; Alguire, C. Impact of QRS duration of frequent premature ventricular complexes on the development of cardiomyopathy. Heart Rhythm 2012, 9, 1460–1464. [Google Scholar] [CrossRef] [PubMed]
- Gold, M.R.; Thébault, C.; Linde, C.; Abraham, W.T.; Gerritse, B.; Ghio, S.; Sutton, M.S.J.; Daubert, J.-C. The effect of QRS duration and morphology on cardiac resynchronization therapy outcomes in mild heart failure: Results from the REsynchronization reVErses Remodeling in Systolic left vEntricular dysfunction (REVERSE) study. Circulation 2012, 126, 822–829. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Holm, H.; Gudbjartsson, D.F.; Arnar, D.O.; Thorleifsson, G.; Thorgeirsson, G.; Stefansdottir, H.; Gudjonsson, S.A.; Jonasdottir, A.; Mathiesen, E.B.; Njølstad, I. Several common variants modulate heart rate, PR interval and QRS duration. Nat. Genet. 2010, 42, 117–122. [Google Scholar] [CrossRef]
- Iuliano, S.; Fisher, S.G.; Karasik, P.E.; Fletcher, R.D.; Singh, S.N.; Department of Veterans Affairs Survival Trial of Antiarrhythmic Therapy in Congestive Heart Failure. QRS duration and mortality in patients with congestive heart failure. Am. Heart J. 2002, 143, 1085–1091. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Q.; Zhou, D.; Zeng, X. A novel machine learning-enabled framework for instantaneous heart rate monitoring from motion-artifact-corrupted electrocardiogram signals. Physiol. Meas. 2016, 37, 1945. [Google Scholar] [CrossRef] [PubMed]
- Jain, A.K. Data clustering: 50 years beyond K-means. Pattern Recognit. Lett. 2010, 31, 651–666. [Google Scholar] [CrossRef]
- Zack, G.; Rogers, W.; Latt, S. Automatic measurement of sister chromatid exchange frequency. J. Histochem. Cytochem. 1977, 25, 741–753. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Q.; Zhou, D.; Zeng, X. Highly wearable cuff-less blood pressure and heart rate monitoring with single-arm electrocardiogram and photoplethysmogram signals. Biomed. Eng. Online 2017, 16, 23. [Google Scholar] [CrossRef] [Green Version]
- Arthur, D.; Vassilvitskii, S. K-means++: The advantages of careful seeding. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, New Orleans, LA, USA, 7–9 January 2007; pp. 1027–1035. [Google Scholar]
- Kaufman, L.; Rousseeuw, P.J. Partitioning around Medoids (Program Pam); John Wiley & Sons, Inc.: Hoboken, NJ, USA, 1990; pp. 68–125. [Google Scholar]
- Tsouri, G.R.; Ostertag, M.H. Patient-specific 12-lead ECG reconstruction from sparse electrodes using independent component analysis. IEEE J. Biomed. Health Inform. 2014, 18, 476–482. [Google Scholar] [CrossRef]
- Wong, J.; Piuri, V.; Scotti, F.; Zhang, Q. Efficient IoT Big Data Streaming with Deep-Learning-Enabled Dynamics. IEEE Internet Things J. 2023, 10, 4770–4782. [Google Scholar] [CrossRef]
- Gangadharan, K.; Zhang, Q. Deep Transferable Intelligence for Spatial Variability Characterization and Data-efficient Learning in Biomechanical Measurement. IEEE Trans. Instrum. Meas. 2023, 72, 2509812. [Google Scholar] [CrossRef]
- Stauffer, J.; Zhang, Q. SpikeBASE: Spiking Neural Learning Algorithm with Backward Adaptation of Synaptic Efflux. IEEE Trans. Comput. 2022, 71, 2707–2716. [Google Scholar] [CrossRef]
- Zou, J.; Zhang, Q. eyeSay: Brain Visual Dynamics Decoding with Deep Learning & Edge Computing. IEEE Trans. Neural Syst. Rehabil. Eng. 2022, 30, 2217–2224. [Google Scholar] [PubMed]
- Manogaran, G.; Shakeel, P.M.; Fouad, H.; Nam, Y.; Baskar, S.; Chilamkurti, N.; Sundarasekar, R. Wearable IoT smart-log patch: An edge computing-based Bayesian deep learning network system for multi access physical monitoring system. Sensors 2019, 19, 3030. [Google Scholar] [CrossRef] [Green Version]
- Azimi, M.; Eslamlou, A.D.; Pekcan, G. Data-driven structural health monitoring and damage detection through deep learning: State-of-the-art review. Sensors 2020, 20, 2778. [Google Scholar] [CrossRef]
- Singh, S.P.; Wang, L.; Gupta, S.; Goli, H.; Padmanabhan, P.; Gulyás, B. 3D deep learning on medical images: A review. Sensors 2020, 20, 5097. [Google Scholar] [CrossRef] [PubMed]
- Bhattacharya, D.; Sharma, D.; Kim, W.; Ijaz, M.F.; Singh, P.K. Ensem-HAR: An ensemble deep learning model for smartphone sensor-based human activity recognition for measurement of elderly health monitoring. Biosensors 2022, 12, 393. [Google Scholar] [CrossRef] [PubMed]
APPROACHES | CR | ME | STD | MAE | RMSE |
---|---|---|---|---|---|
DTW | −2.1% | 10.9 | 23.8 | 15.3 | 26.1 |
DTW + SQI | −4.9% | 8.0 | 24.8 | 16.4 | 26.0 |
DTW + Cal. | 48.5% | 2.2 | 8.2 | 5.8 | 8.4 |
DTW + SQI + Cal. | 54.1% | 2.7 | 7.8 | 5.1 | 8.2 |
MV-DTW | 28.3% | −3.6 | 6.2 | 5.4 | 7.1 |
MV-DTW + SQI | 46.6% | −5.8 | 5.1 | 6.2 | 7.7 |
MV-DTW + Cal. | 84.1% | −0.3 | 3.4 | 2.3 | 3.4 |
MV-DTW + SQI + Cal. (Proposed) | 91.2% | 0.4 | 2.6 | 1.7 | 2.6 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, Q.; Zhou, D. Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction. Sensors 2023, 23, 5723. https://doi.org/10.3390/s23125723
Zhang Q, Zhou D. Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction. Sensors. 2023; 23(12):5723. https://doi.org/10.3390/s23125723
Chicago/Turabian StyleZhang, Qingxue, and Dian Zhou. 2023. "Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction" Sensors 23, no. 12: 5723. https://doi.org/10.3390/s23125723
APA StyleZhang, Q., & Zhou, D. (2023). Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction. Sensors, 23(12), 5723. https://doi.org/10.3390/s23125723