skip to main content
research-article

On-device Prior Knowledge Incorporated Learning for Personalized Atrial Fibrillation Detection

Published: 17 September 2021 Publication History

Abstract

Atrial Fibrillation (AF), one of the most prevalent arrhythmias, is an irregular heart-rate rhythm causing serious health problems such as stroke and heart failure. Deep learning based methods have been exploited to provide an end-to-end AF detection by automatically extracting features from Electrocardiogram (ECG) signal and achieve state-of-the-art results. However, the pre-trained models cannot adapt to each patient’s rhythm due to the high variability of rhythm characteristics among different patients. Furthermore, the deep models are prone to overfitting when fine-tuned on the limited ECG of the specific patient for personalization. In this work, we propose a prior knowledge incorporated learning method to effectively personalize the model for patient-specific AF detection and alleviate the overfitting problems. To be more specific, a prior-incorporated portion importance mechanism is proposed to enforce the network to learn to focus on the targeted portion of the ECG, following the cardiologists’ domain knowledge in recognizing AF. A prior-incorporated regularization mechanism is further devised to alleviate model overfitting during personalization by regularizing the fine-tuning process with feature priors on typical AF rhythms of the general population. The proposed personalization method embeds the well-defined prior knowledge in diagnosing AF rhythm into the personalization procedure, which improves the personalized deep model and eliminates the workload of manually adjusting parameters in conventional AF detection method. The prior knowledge incorporated personalization is feasibly and semi-automatically conducted on the edge, device of the cardiac monitoring system. We report an average AF detection accuracy of 95.3% of three deep models over patients, surpassing the pre-trained model by a large margin of 11.5% and the fine-tuning strategy by 8.6%.

References

[1]
Erick A. Perez Alday, Annie Gu, Amit J. Shah, Chad Robichaux, An-Kwok Ian Wong, Chengyu Liu, Feifei Liu, Ali Bahrami Rad, Andoni Elola, Salman Seyedi, et al. 2020. Classification of 12-lead ecgs: The physionet/computing in cardiology challenge 2020. Physiological measurement (2020).
[2]
American Heart Association. 2016. What is Atrial Fibrillation (AFib or AF)?https://www.heart.org/en/health-topics/atrial-fibrillation/what-is-atrial -fibrillation-afib-or-af.
[3]
Paddy M. Barrett, Ravi Komatireddy, Sharon Haaser, Sarah Topol, Judith Sheard, Jackie Encinas, Angela J. Fought, and Eric J. Topol. 2014. Comparison of 24-hour Holter monitoring with 14-day novel adhesive patch electrocardiographic monitoring. The American journal of medicine 127, 1 (2014), 95–e11.
[4]
Boston Scientific, Inc. 2017. LUX-Dx™ Insertable Cardiac Monitor (ICM) System. https://www.bostonscientific.com/ content/dam/bostonscientific/Rhythm20Management/portfolio-group/lux-dx-icm/pdf/LUX-Dx-Clinic-Resource-Gui- de.pdf.
[5]
Carmen Camara, Pedro Peris-Lopez, and Juan E. Tapiador. 2015. Security and privacy issues in implantable medical devices: A comprehensive survey. Journal of Biomedical Informatics 55 (2015), 272–289.
[6]
D. Dorr. 2009. Determining voltage levels of concern for human and animal response to AC current. In 2009 IEEE Power & Energy Society General Meeting. IEEE, 1–6.
[7]
U.S. Food and Drug Administration. 2019. Cybersecurity Vulnerabilities - Medtronic Implantable Cardia Devices. https://www.fda.gov/medical-devices/safety-communications/cybersecurity-v ulnerabilities-affecting-medtronic-implantable-cardiac-devices-programmers-and-home.
[8]
Raspberry Pi Foundation. 2019. RASPBERRY PI 4 MODEL B. https://www.raspberrypi.org/products/raspberry-pi-4-model-b.
[9]
Tomer Golany and Kira Radinsky. 2019. PGANs: Personalized generative adversarial networks for ECG synthesis to improve patient-specific deep ECG classification. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 557–564.
[10]
Ary L. Goldberger, Luis A. N. Amaral, Leon Glass, Jeffrey M. Hausdorff, Plamen Ch. Ivanov, Roger G. Mark, Joseph E. Mietus, George B. Moody, Chung-Kang Peng, and H. Eugene Stanley. 2000. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. circulation 101, 23 (2000), e215–e220.
[11]
Awni Y. Hannun, Pranav Rajpurkar, Masoumeh Haghpanahi, Geoffrey H. Tison, Codie Bourn, Mintu P. Turakhia, and Andrew Y. Ng. 2019. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine 25, 1 (2019), 65.
[12]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
[13]
Gerhard Hindricks, Evgueny Pokushalov, Lubos Urban, Milos Taborsky, Karl-Heinz Kuck, Dmitry Lebedev, Guido Rieger, and Helmut Purerfellner. 2010. Performance of a new leadless implantable cardiac monitor in detecting and quantifying atrial fibrillation results of the XPECT trial. Circulation: Arrhythmia and Electrophysiology 3, 2 (2010), 141–147.
[14]
iRhythm Technologies, Inc. 2021. iRhythm Zio Patch. https://www.irhythmtech.com.
[15]
Zhenge Jia, Zhepeng Wang, Feng Hong, Lichuan Ping, Yiyu Shi, and Jingtong Hu. 2020. Personalized deep learning for ventricular arrhythmias detection on medical IoT systems. In Proceedings of the 39th International Conference on Computer-Aided Design (Virtual) (ICCAD’20). Article 38, 9 pages.
[16]
Serkan Kiranyaz, Turker Ince, and Moncef Gabbouj. 2015. Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Transactions on Biomedical Engineering 63, 3 (2015), 664–675.
[17]
Richard E. Klabunde. 2017. Cardiac electrophysiology: Normal and ischemic ionic currents and the ECG. Advances in physiology education 41, 1 (2017), 29–37.
[18]
Jie Lian, Lian Wang, and Dirk Muessig. 2011. A simple method to detect atrial fibrillation using RR intervals. The American journal of cardiology 107, 10 (2011), 1494–1497.
[19]
Dominique Makowski. 2016. Neurokit: A python toolbox for statistics and neurophysiological signal processing. Memory and Cognition Lab’Day 1 (2016).
[20]
Mark R. G. Moody G. R. 1983. A new method for detecting atrial fibrillation using R-R intervals. Computers in Cardiology 10 (1983), 227–230.
[21]
Sajad Mousavi, Fatemeh Afghah, and U. Rajendra Acharya. 2020. HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks. Computers in Biology and Medicine 127 (2020), 104057.
[22]
Nvidia. 2020. NVIDIA Jetson Nano. https://www.realtimes.cn/Uploads/download/JetsonNano_DataSheet.pdf.
[23]
Jiapu Pan and Willis J. Tompkins. 1985. A real-time QRS detection algorithm. IEEE transactions on biomedical engineering3 (1985), 230–236.
[24]
Simona Petrutiu, Alan V. Sahakian, and Steven Swiryn. 2007. Abrupt changes in fibrillatory wave characteristics at the termination of paroxysmal atrial fibrillation in humans. Europace 9, 7 (2007), 466–470.
[25]
Helmut Pürerfellner, Evgeny Pokushalov, Shantanu Sarkar, Jodi Koehler, Ren Zhou, Lubos Urban, and Gerhard Hindricks. 2014. P-wave evidence as a method for improving algorithm to detect atrial fibrillation in insertable cardiac monitors. Heart Rhythm 11, 9 (2014), 1575–1583.
[26]
Shantanu Sarkar, David Ritscher, and Rahul Mehra. 2008. A detector for a chronic implantable atrial tachyarrhythmia monitor. IEEE Transactions on Biomedical Engineering 55, 3 (2008), 1219–1224.
[27]
British Standards Institute Staff. 2006. Effects of Current on Human Beings and Livestock. General Aspects. B S I Standards. https://books.google.com/books?id=lBXqngEACAAJ.
[28]
STMicroelectronics. 2020. Discovery kit with STM32F469NI MCU. https://www.st.com/resource/en/user_manual/dm00218846-discovery-kit-with -stm32f469ni-mcu-stmicroelectronics.pdf.
[29]
STMicroelectronics. 2020. STM32 solutions for Artificial Neural Networks. https://www.st.com/content/st_com/en/ecosystems/stm32-ann.html.
[30]
Christos Strydis, Robert M. Seepers, Pedro Peris-Lopez, Dimitrios Siskos, and Ioannis Sourdis. 2013. A system architecture, processor, and communication protocol for secure implants. TACO 10, 4 (2013), 1–23.
[31]
Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic attribution for deep networks. In International Conference on Machine Learning. PMLR, 3319–3328.
[32]
Yong Xia, Naren Wulan, Kuanquan Wang, and Henggui Zhang. 2018. Detecting atrial fibrillation by deep convolutional neural networks. Computers in biology and medicine 93 (2018), 84–92.
[33]
Zhaohan Xiong, Martin K. Stiles, and Jichao Zhao. 2017. Robust ECG signal classification for detection of atrial fibrillation using a novel neural network. In 2017 Computing in Cardiology (CinC). IEEE, 1–4.
[34]
Jianwei Zheng, Jianming Zhang, Sidy Danioko, Hai Yao, Hangyuan Guo, and Cyril Rakovski. 2020. A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients. Scientific Data 7, 1 (2020), 1–8.
[35]
Peter Zimetbaum and Alena Goldman. 2010. Ambulatory arrhythmia monitoring: Choosing the right device. Circulation 122, 16 (2010), 1629–1636.

Cited By

View all
  • (2024)Sparse learned kernels for interpretable and efficient medical time series processingNature Machine Intelligence10.1038/s42256-024-00898-46:10(1132-1144)Online publication date: 18-Sep-2024
  • (2024)Medical informed machine learningArtificial Intelligence in Medicine10.1016/j.artmed.2023.102676145:COnline publication date: 1-Feb-2024
  • (2023)TinyML Design Contest for Life-Threatening Ventricular Arrhythmia DetectionIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2023.330974443:1(127-140)Online publication date: 29-Aug-2023
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Transactions on Embedded Computing Systems
ACM Transactions on Embedded Computing Systems  Volume 20, Issue 5s
Special Issue ESWEEK 2021, CASES 2021, CODES+ISSS 2021 and EMSOFT 2021
October 2021
1367 pages
ISSN:1539-9087
EISSN:1558-3465
DOI:10.1145/3481713
  • Editor:
  • Tulika Mitra
Issue’s Table of Contents
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Journal Family

Publication History

Published: 17 September 2021
Accepted: 01 July 2021
Revised: 01 June 2021
Received: 01 April 2021
Published in TECS Volume 20, Issue 5s

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Arrhythmia detection
  2. atrial fibrillation
  3. prior knowledge
  4. personalization
  5. neural networks

Qualifiers

  • Research-article
  • Refereed

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)64
  • Downloads (Last 6 weeks)2
Reflects downloads up to 22 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Sparse learned kernels for interpretable and efficient medical time series processingNature Machine Intelligence10.1038/s42256-024-00898-46:10(1132-1144)Online publication date: 18-Sep-2024
  • (2024)Medical informed machine learningArtificial Intelligence in Medicine10.1016/j.artmed.2023.102676145:COnline publication date: 1-Feb-2024
  • (2023)TinyML Design Contest for Life-Threatening Ventricular Arrhythmia DetectionIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems10.1109/TCAD.2023.330974443:1(127-140)Online publication date: 29-Aug-2023
  • (2023)Few-shot transfer learning for personalized atrial fibrillation detection using patient-based siamese network with single-lead ECG recordsArtificial Intelligence in Medicine10.1016/j.artmed.2023.102644144:COnline publication date: 1-Oct-2023

View Options

Login options

Full Access

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media