short-paper

Open access

Unsupervised non-parametric change point detection in electrocardiography

Authors:

Nikolay Shvetsov,

Dmitry V. DylovAuthors Info & Claims

SSDBM '20: Proceedings of the 32nd International Conference on Scientific and Statistical Database Management

Article No.: 19, Pages 1 - 4

https://doi.org/10.1145/3400903.3400917

Published: 30 July 2020 Publication History

All formats PDF

Abstract

We propose a new unsupervised and non-parametric method to detect change points in electrocardiography. The detection relies on optimal transport theory combined with topological analysis and the bootstrap procedure. The algorithm is designed to detect changes in virtually any harmonic or a partially harmonic signal and is verified on ECG data streams. We successfully find abnormal or irregular cardiac cycles in the waveforms for the six of the most frequent types of clinical arrhythmias using a single algorithm. Our unsupervised approach reaches the level of performance of the supervised state-of-the-art techniques. We provide conceptual justification for the efficiency of the method.

References

[1]

Ryan Prescott Adams and David J. C. MacKay. 2007. Bayesian Online Changepoint Detection. arXiv 0710.3742(2007).

[2]

Miquel Alfaras, Miguel C. Soriano, and Silvia Ortín. 2019. A Fast Machine Learning Model for ECG-Based Heartbeat Classification and Arrhythmia Detection. Frontiers in Physics 7(2019), 103. https://doi.org/10.3389/fphy.2019.00103

[3]

Nazar Buzun. 2019. Gaussian approximation for empirical barycenters. arXiv 1904.00891(2019).

[4]

Nazar Buzun and Valeriy Avanesov. 2017. Bootstrap for change point detection. arXiv 1710.07285(2017).

[5]

Victor Chernozhukov, Denis Chetverikov, and Kengo Kato. 2013. Comparison and anti-concentration bounds for maxima of Gaussian random vectors. arXiv 1301.4807(2013).

[6]

Victor Chernozhukov, Denis Chetverikov, and Kengo Kato. 2014. Anti-concentration and honest, adaptive confidence bands. The Annals of Statistics 42, 5 (Oct 2014), 1787–1818. https://doi.org/10.1214/14-aos1235

[7]

Victor Chernozhukov, Denis Chetverikov, and Kengo Kato. 2014. Gaussian approximation of suprema of empirical processes. The Annals of Statistics 42, 4 (Aug 2014), 1564–1597. https://doi.org/10.1214/14-aos1230

[8]

Aritra Chowdhury, Dmitry V Dylov, Qing Li, Michael MacDonald, Dan E Meyer, Michael Marino, and Alberto Santamaria-Pang. 2017. Blood vessel characterization using virtual 3D models and convolutional neural networks in fluorescence microscopy. In IEEE ISBI 2017. IEEE, 629–632.

[9]

Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. In Advances in neural information processing systems. 2292–2300.

[10]

J Faganeli and F Jager. 2010. Automatic classification of transient ischaemic and transient non-ischaemic heart-rate related ST segment deviation episodes in ambulatory ECG records. Physiological Measurement 31, 3 (feb 2010), 323–337. https://doi.org/10.1088/0967-3334/31/3/004

[11]

Giulia Guidi and Manas Karandikar. 2014. Classification of Arrhythmia using ECG data. https://doi.org/proj2014

[12]

Jing Hua, Hua Zhang, Jizhong Liu, Yilu Xu, and Fumin Guo. 2018. Direct arrhythmia classification from compressive ECG signals in wearable health monitoring system. Journal of Circuits, Systems and Computers 27, 06 (2018), 1850088.

[13]

Jane Huff. 2006. ECG workout: Exercises in arrhythmia interpretation. Lippincott Williams & Wilkins.

[14]

Tae Joon Jun, Hoang Minh Nguyen, Daeyoun Kang, Dohyeun Kim, Daeyoung Kim, and Young-Hak Kim. 2018. ECG arrhythmia classification using a 2-D convolutional neural network. arXiv 1804.06812(2018).

[15]

Hiroshi Kawazoe, Yukiko Nakano, Hidenori Ochi, Masahiko Takagi, Yusuke Hayashi, Yuko Uchimura, Takehito Tokuyama, Yoshikazu Watanabe, Hiroya Matsumura, Shunsuke Tomomori, Akinori Sairaku, Kazuyoshi Suenari, Akinori Awazu, Yosuke Miwa, Kyoko Soejima, Kazuaki Chayama, and Yasuki Kihara. 2016. Risk stratification of ventricular fibrillation in Brugada syndrome using noninvasive scoring methods. Heart Rhythm 13, 10 (2016), 1947 – 1954. https://doi.org/10.1016/j.hrthm.2016.07.009 Focus Issue: Sudden Death.

[16]

Rebecca Killick, Paul Fearnhead, and Idris A Eckley. 2012. Optimal detection of changepoints with a linear computational cost. J. Amer. Statist. Assoc. 107, 500 (2012), 1590–1598.

[17]

Dmitrii Krylov, Dmitry V. Dylov, and Michael Rosenblum. 2020. Reinforcement learning for suppression of collective activity in oscillatory ensembles. Chaos 30, 3 (2020). https://doi.org/10.1063/1.5128909 arxiv:1909.12154

[18]

Hans R Kunsch. 1989. The jackknife and the bootstrap for general stationary observations. The annals of Statistics(1989), 1217–1241.

[19]

Soumendra Nath Lahiri. 2013. Resampling methods for dependent data. Springer Science & Business Media.

[20]

Vadim Liventsev, Irina Fedulova, and Dmitry Dylov. 2019. Deep Text Prior: Weakly Supervised Learning for Assertion Classification. In International Conference on Artificial Neural Networks. Springer, 243–257.

[21]

Nicos Maglaveras, Telemachos Stamkopoulos, Konstantinos Diamantaras, Costas Pappas, and Michael Strintzis. 1998. ECG pattern recognition and classification using non-linear transformations and neural networks: A review. International Journal of Medical Informatics 52, 1(1998), 191 – 208. https://doi.org/10.1016/S1386-5056(98)00138-5

[22]

George B Moody and Roger G Mark. 2001. The impact of the MIT-BIH arrhythmia database. IEEE Engineering in Medicine and Biology Magazine 20, 3 (2001), 45–50.

[23]

Jose Perea and John Harer. 2013. Sliding Windows and Persistence: An Application of Topological Methods to Signal Analysis. arXiv 1307.6188(2013).

[24]

Philip de Chazal, M. O’Dwyer, and R. B. Reilly. 2004. Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Transactions on Biomedical Engineering 51, 7 (July 2004), 1196–1206. https://doi.org/10.1109/TBME.2004.827359

[25]

Ivan Rodin, Irina Fedulova, Artem Shelmanov, and Dmitry V Dylov. 2019. Multitask and Multimodal Neural Network Model for Interpretable Analysis of X-ray Images. In 2019 IEEE BIBM. IEEE, 1601–1604.

[26]

Artem Shelmanov, Vadim Liventsev, Danil Kireev, Nikita Khromov, Alexander Panchenko, Irina Fedulova, and Dmitry V Dylov. 2019. Active Learning with Deep Pre-trained Models for Sequence Tagging of Clinical and Biomedical Texts. In 2019 IEEE BIBM. IEEE, 482–489.

[27]

Nikolay Shvetsov, Nazar Buzun, and Dmitry V. Dylov. 2020. Unsupervised non-parametric change point detection in quasi-periodic signals. arxiv:2002.02717 [cs.LG]

[28]

Max Sommerfeld and Axel Munk. 2016. Inference for Empirical Wasserstein Distances on Finite Spaces. arXiv 1610.03287(2016).

[29]

Charles Truong, Laurent Oudre, and Nicolas Vayatis. 2018. Selective review of offline change point detection methods. Signal Processing 167(2018).

Cited By

Gedda RBeilina LTan R(2023)Change Point Detection for Process Data Analytics Applied to a Multiphase Flow FacilityComputer Modeling in Engineering & Sciences10.32604/cmes.2022.019764134:3(1737-1759)Online publication date: 2023
https://doi.org/10.32604/cmes.2022.019764
Buzun N(2023)Gaussian Approximation for Penalized Wasserstein BarycentersMathematical Methods of Statistics10.3103/S106653072301003932:1(1-26)Online publication date: 26-Apr-2023
https://doi.org/10.3103/S1066530723010039
Ragot J(2022)Detection of operating mode changes, without a priori model and in uncertain environmentsTransactions of the Institute of Measurement and Control10.1177/0142331222109252744:13(2653-2671)Online publication date: 27-Apr-2022
https://doi.org/10.1177/01423312221092527
Show More Cited By

Recommendations

A wearable smartphone-based platform for real-time cardiovascular disease detection via electrocardiogram processing
Special section on new and emerging technologies in bioinformatics and bioengineering

Cardiovascular disease (CVD) is the single leading cause of global mortality and is projected to remain so. Cardiac arrhythmia is a very common type of CVD and may indicate an increased risk of stroke or sudden cardiac death. The ECG is the most widely ...
Efficient Fine Arrhythmia Detection Based on DCG P-T Features

Due to the high mortality associated with heart disease, there is an urgent demand for advanced detection of abnormal heart beats. The use of dynamic electrocardiogram (DCG) provides a useful indicator of heart condition from long-term monitoring ...
Unsupervised anomaly detection in brain MRI: Learning abstract distribution from massive healthy brains
Abstract Purpose
To develop a general unsupervised anomaly detection method based only on MR images of normal brains to automatically detect various brain abnormalities.
Materials and methods
In this ...
Highlights
- An unsupervised learning framework to detect various brain abnormalities in MR images without lesion labeling.

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

SSDBM '20: Proceedings of the 32nd International Conference on Scientific and Statistical Database Management

July 2020

241 pages

ISBN:9781450388146

DOI:10.1145/3400903

Copyright © 2020 ACM.

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

Publication History

Published: 30 July 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper
Research
Refereed limited

Funding Sources

Russian Foundation for Basic Research

Conference

SSDBM 2020

SSDBM 2020: 32nd International Conference on Scientific and Statistical Database Management

July 7 - 9, 2020

Vienna, Austria

Acceptance Rates

Overall Acceptance Rate 56 of 146 submissions, 38%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
421
Total Downloads

Downloads (Last 12 months)190
Downloads (Last 6 weeks)92

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Gedda RBeilina LTan R(2023)Change Point Detection for Process Data Analytics Applied to a Multiphase Flow FacilityComputer Modeling in Engineering & Sciences10.32604/cmes.2022.019764134:3(1737-1759)Online publication date: 2023
https://doi.org/10.32604/cmes.2022.019764
Buzun N(2023)Gaussian Approximation for Penalized Wasserstein BarycentersMathematical Methods of Statistics10.3103/S106653072301003932:1(1-26)Online publication date: 26-Apr-2023
https://doi.org/10.3103/S1066530723010039
Ragot J(2022)Detection of operating mode changes, without a priori model and in uncertain environmentsTransactions of the Institute of Measurement and Control10.1177/0142331222109252744:13(2653-2671)Online publication date: 27-Apr-2022
https://doi.org/10.1177/01423312221092527
Bardhan SSwain SJenamani MRoutray A(2022)Novel CUSUM Methods for Repetitive Change Detection in Sensor Signals2022 IEEE 1st Industrial Electronics Society Annual On-Line Conference (ONCON)10.1109/ONCON56984.2022.10127062(1-7)Online publication date: 9-Dec-2022
https://doi.org/10.1109/ONCON56984.2022.10127062
Bespalov IBuzun NDylov D(2022)BRULÈPattern Recognition10.1016/j.patcog.2022.108816131:COnline publication date: 1-Nov-2022
https://dl.acm.org/doi/10.1016/j.patcog.2022.108816
Katser IKozitsin VLobachev VMaksimov I(2021)Unsupervised Offline Changepoint Detection EnsemblesApplied Sciences10.3390/app1109428011:9(4280)Online publication date: 9-May-2021
https://doi.org/10.3390/app11094280

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents