article

Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms

Authors:

M. -O. Cordier,

F. WangAuthors Info & Claims

Artificial Intelligence in Medicine, Volume 28, Issue 3

Pages 231 - 263

https://doi.org/10.1016/S0933-3657(03)00066-6

Published: 01 July 2003 Publication History

Abstract

This paper proposes a novel approach to cardiac arrhythmia recognition from electrocardiograms (ECGs). ECGs record the electrical activity of the heart and are used to diagnose many heart disorders. The numerical ECG is first temporally abstracted into series of time-stamped events. Temporal abstraction makes use of artificial neural networks to extract interesting waves and their features from the input signals. A temporal reasoner called a chronicle recogniser processes such series in order to discover temporal patterns called chronicles which can be related to cardiac arrhythmias. Generally, it is difficult to elicit an accurate set of chronicles from a doctor. Thus, we propose to learn automatically from symbolic ECG examples the chronicles discriminating the arrhythmias belonging to some specific subset. Since temporal relationships are of major importance, inductive logic programming (ILP) is the tool of choice as it enables first-order relational learning. The approach has been evaluated on real ECGs taken from the MIT-BIH database. The performance of the different modules as well as the efficiency of the whole system is presented. The results are rather good and demonstrate that integrating numerical techniques for low level perception and symbolic techniques for high level classification is very valuable.

References

[1]

ECG beat detection using filter banks. IEEE Trans. Biomed. Eng. v46. 192-202.

[2]

Al Nashash, H.A., Cardiac arrhythmia classification using neural networks. Technol. Health Care. v46. 1417-1425.

[3]

Bardou, A., Auger, P., Birkui, P. and Chasse, J.-L., Modeling of cardiac electrophysiological mechanisms: from action potential genesis to its propagation in myocardium. Crit. Rev. Biomed. Eng. v24. 141-221.

[4]

Behlouli H. Apprentissage auto-améliorant et modélisation de la dynamique temporelle de données évolutives par réseaux de neurones. Application au diagnostic et í la prédiction en électrocardiologie quantitative. Ph.D. thesis, INSA de Lyon, France; 1998.

[5]

Bourlas P, Giakoumakis E, Papakonstantinou G. A knowledge acquisition and management system for ECG diagnosis. In: Magoulas G, Prentza A, editors. Proceedings of the Workshop on Machine Learning in Medical Applications, Chania, Greece; 1999. p. 30-6.

[6]

Bratko I, Mozetič I, Lavrač N. Kardio: a study in deep and qualitative knowledge for expert systems. Cambridge, USA: MIT Press; 1989.

[7]

Carrault G, Cordier M-O, Quiniou R, Garreau M, Bellanger J-J, Bardou A. A model-based approach for learning to identify cardiac arrhythmias. In: Horn W, Shahar Y, Lindberg G, Andreassen S, Wyatt J, editors. Proceedings of AIMDM-99: Artificial Intelligence in Medicine and Medical Decision Making, vol. 1620 of LNAI. Aalborg, Denmark: Springer-Verlag; 1999. p. 165-74.

[8]

Clocksin WF, Mellish CS. Programming in prolog. Berlin: Springer-Verlag; 1981.

[9]

Coast, D.A., Stern, R.M., Cano, G.C. and Briller, S.A., An approach to cardiac arrhythmia analysis using Hidden Markov Models. IEEE Trans. Biomed. Eng. v27 i9. 826-836.

[10]

Coiera E. Designing for decision support in a clinical monitoring environment. In: Schizas CN, Chistodoulides G, editors. Proceedings of the International Conference on Medical Physics and Biomedical Engineering, Nicosia, Cyprus; 1994. p. 130-42.

[11]

Dechter, R., Meiri, I. and Pearl, J., Temporal constraint networks. Artif. Intell. v49 i1-3. 61-95.

[12]

Dousson, C., Alarm driven supervision for telecommunication networks. II. On-line chronicle recognition. Ann. Telecommun. v51 i9-10. 501-508.

[13]

Dousson C, Gaborit P, Ghallab M. Situation recognition: representation and algorithms. In: Proceedings of IJCAI-93. Chambéry, France: Morgan Kaufman; 1993. p. 166-72.

[14]

Einthoven, W., Un nouveau galvanomètre. Arch. Néerland. Sci. Exact. Nat. v6. 625-633.

[15]

Fokapu O, Girard J-P. A new approach for P wave detection using analytic signal. In: Proceedings of the 15th IEEE/EMBS Conference. San Diego, USA: IEEE Computer Society Press; 1993. p. 400-1.

[16]

Freeman SP. P wave detection of ambulatory ECG. In: Proceedings of the 13th IEEE/EMBS Conference. Orlando, USA: IEEE Computer Society Press; 1991. p. 647-8.

[17]

Gritzali, F., Towards a generalized scheme for QRS detection in ECG waveforms. Signal Process. v15. 183-192.

[18]

Gritzali, F., Frangakis, G. and Papakonstantinou, G., Detection of the P and T waves in an ECG. Comput. Biomed. Res. v22. 83-91.

Digital Library

[19]

Guertin M. Abductive inference of events: diagnosing cardiac arrhythmias. In: Proceedings of the Florida Artificial Intelligence Research Symposium, Key West, USA; 1996.

[20]

Gustafson, D., Willsky, A., Wang, J., Lancaster, M. and Triebwasser, J., ECG/VCG rhythm diagnosis using statistical signal analysis, parts 1 and 2. IEEE Trans. Biomed. Eng. v25. 344-361.

[21]

Ham, F. and Han, S., Classification of cardiac arrhythmias using fuzzy ARTMAP. IEEE Trans. Biomed. Eng. v43 i4. 425-430.

[22]

Hernández, A., Carrault, G. and Mora, F., Improvement of a P wave detector by a bivariate classification stage. Trans. Inst. Meas. Contr. v22 i3. 231-242.

[23]

Hernández, A., Carrault, G., Mora, F. and Bardou, A., Overview of CARMEN: a new dynamic quantitative cardiac model for ECG monitoring and its adaptation to observed signals. Acta Biotheor. v48 i3-4. 303-322.

[24]

Hernández, A.I., Carrault, G., Mora, F., Passariello, G. and Schleich, J.M., Multisensor fusion for atrial and ventricular activity detection in coronary care monitoring. IEEE Trans. Biomed. Eng. v46. 1186-1190.

[25]

Hérault J, Jutten C. Réseaux neuronaux et traitement du signal. Paris, France: íditions Hermès, Traité des nouvelles technologies; 1994.

[26]

Jenkins, J. and Caswell, S., Detection algorithms in implantable cardioverter defibrillator. Proc. IEEE. v84 i3. 428-445.

[27]

Kókai G, Alexin Z, Gyimóthy T. Analysing and learning ECG waveforms. In: Muggleton S, editor. Proceedings of ILP'96, vol. 1314 of LNAI. Stockholm, Sweden: Springer-Verlag; 1996. p. 127-45.

[28]

A decentralised multichannel length transformation algorithm and its parallel implementation for real-time ECG monitoring. Comput. Biomed. Res. v33. 227-244.

Digital Library

[29]

Kristiansen DE, Husøy JH, Eftestøl T. Rhythm detection in ECG signals. In: Proceedings of the Norwegian Signal Processing Symposium, Norsig, Stavanger, Norway; 1995. p. 119-24.

[30]

Kundu, M., Nasipuri, M. and Basu, D., A knowledge-based approach to ECG interpretation using fuzzy logic. IEEE Trans. Syst. Man Cybernet. v28 i2. 237-243.

[31]

van Laer W, de Raedt L, Dzeroski S. On multi-class problems and discretization in inductive logic programming. In: Ras ZW, Skowron A, editors. Proceedings of ISMIS-97: 10th International Symposium on Methodologies for Intelligent Systems, vol. 1325 of LNAI. Charlotte, NC: Springer-Verlag; 1997. p. 277-86.

[32]

Lavrač N. Machine learning for data mining in medicine. In: Horn W, Shahar Y, Lindberg G, Andreassen S, Wyatt J, editors. Proceedings of AIMDM'99, vol. 1620 of LNAI. Aalborg, Denmark: Springer-Verlag; 1999. p. 47-62.

[33]

Lavrač N, Dzeroski S, Grobelnik M. Learning non-recursive definitions of relations with LINUS. In: Kodratoff Y, editor. Proceedings of EWSL, Porto, Portugal; 1991. p. 265-81.

[34]

Lavrač N, Dzeroski S, Pirnat V, Krizman V. Learning rules for early diagnosis of rheumatic diseases. In: Mayoh B, editor. Proceedings of the third Scandinavian Conference on AI, vol. 12 of Frontiers in Artificial Intelligence and Applications. Roskilde, Denmark: IOS Press; 1991. p. 138-49.

[35]

Le Blanc, R., Quantitative analysis of cardiac arrhythmias. Crit. Rev. Biomed. Eng. v14 i1. 1-43.

[36]

Long, W.J., Temporal reasoning for diagnosis in a causal probabilistic knowledge base. Artif. Intell. Med. v8. 193-215.

[37]

Lucas, P., Tholen, A. and van Oort, G., A model-based system for pacemaker reprogramming. Artif. Intell. Med. v17. 249-269.

[38]

Moody GB, Mark RG. The MIT-BIH arrhythmia database on CD-ROM and software for use with it. In: Proceedings of Computers in Cardiology Conference, vol. 17. San Diego, USA: IEEE Computer Society Press; 1990. p. 185-8.

[39]

Muggleton, S., Inductive logic programming: issues, results and the challenge of learning language in logic. Artif. Intell. v114 i1-2. 283-296.

[40]

An intelligent framework for the classification of the 12-lead ECG. Artif. Intell. Med. v8. 363-372.

[41]

Pan, J. and Tompkins, W.J., A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. v32. 230-236.

[42]

Passariello, G., Mora, F., Carrault, G. and Le Pichon, J.-P., Intelligent patient monitoring and management systems: a review. IEEE Eng. Med. Biol. v12 i4. 23-33.

[43]

Quiniou R, Cordier M-O, Carrault G, Wang F. Application of ILP to cardiac arrhythmia characterisation for chronicle recognition. In: Rouveirol C, Sebag M, editors. Proceedings of ILP-2001, vol. 2157 of LNAI. Strasbourg, France: Springer-Verlag; 2001. p. 193-215.

[44]

Quinlan J. Machine learning and ID3. Los Altos: Morgan Kauffman; 1992.

[45]

de Raedt L, van Laer W. Inductive constraint logic. In: Jantke KP, Shinohara T, Zeugmann T, editors. Proceedings of ALT-95: 6th Workshop on Algorithmic Learning Theory, vol. 997 of LNAI. Fukuoka, Japan: Springer-Verlag; 1995. p. 80-94.

[46]

Reddy S, Elko P, Chistenson D, Rowlandson G. Detection of P waves in resting ECG : a preliminary study. In: Proceedings of Computers in Cardiology Conference. San Diego, USA: IEEE Computer Society Press; 1992. p. 87-90.

[47]

Ryan, T.J., Antman, E.M. and Brooks, N.H., 1999 update: ACC/AHA guidelines for the management of patients with acute myocardial infarction. J. Am. College Cardiol. v34. 890-911.

[48]

Senhadji, L., Carrault, G. and Bellanger, J.-J., Comparing wavelet transforms for recognizing cardiac patterns. IEEE Eng. Med. Biol. Mag. v14 i2. 167-173.

[49]

Senhadji L, Wang F, Hernández AI, Carrault G. Wavelets extrema representation for QRS-T cancellation and P wave detection. In: Proceedings of Computers in Cardiology Conference. Memphis, USA: IEEE Computer Society Press; 2002.

[50]

Shapiro EY. Algorithmic program debugging, ACM distinguished dissertation. Cambridge, MA: MIT Press; 1982.

[51]

Shibahara T. On using causal knowledge to recognise vital signals: knowledge-based interpretation of arrhythmia. In: Joshi AK, editor. Proceedings of IJCAI-85. Los Angeles, CA: Morgan Kaufmann; 1985. p. 307-14.

[52]

Silipo R. Investigating electrocardiographic features in fuzzy models for cardiac arrhythmia classification. In: Proceedings of IDAMAP-99, Washington, DC; 1999. p. 123-34.

[53]

Silipo, R. and Marchesi, C., Artificial neural networks for automatic ECG analysis. IEEE Trans. Signal Process. v46 i5. 1417-1425.

[54]

Siregar, P., Chahine, M., Lemoulec, F. and LeBeux, P., An interactive qualitative model in cardiology. Comput. Biomed. Res. v28 i6. 443-478.

[55]

Theories for mutagenicity: a study of first-order and feature-based induction. Artif. Intell. J. v85 i1-2. 277-299.

[56]

Thakor, N. and Zhu, Y., Applications of adaptive filtering to ECG analysis: noise cancellation and arrhythmia detection. IEEE Trans. Biomed. Eng. v38. 785-794.

[57]

Tong, D.A. and Widman, L.E., Model-based interpretation of the ECG: a methodology for temporal and spatial reasoning. Comput. Biomed. Res. v26 i3. 206-219.

[58]

Tsien CL, Fackler JC. An annotated data collection system to support intelligent analysis of intensive care unit data. In: Liu X, Cohen P, Berthold M, editors. Advances in intelligent data analysis. London: Springer-Verlag; 1997. p. 111-21.

[59]

Uckun, S., Intelligent systems in patient monitoring and therapy management. A survey of research projects. Int. J. Clin. Monit. Comput. v11. 241-253.

[60]

Wang F, Quiniou R, Carrault G, Cordier M-O. Learning structural knowledge from the ECG. In: Crespo J, Maojo V, Martin F, editors. Proceedings of ISMDA-2001, vol. 1933 of LNCS. Madrid, Spain: Springer-Verlag; 2001. p. 288-94.

[61]

Watrous RL, Towell G. A patient-adaptive neural network ECG patient monitoring algorithm. In: Proceedings of Computers in Cardiology Conference. Wien, Austria: IEEE Computer Society Press; 1995. p. 229-32.

[62]

Wieben, O., Afonso, V.X. and Tompkins, W.J., Classification of premature ventricular complexes using filter bank features, induction of decision trees and a fuzzy rule-based system. Med. Biol. Eng. Comput. v37. 560-565.

[63]

World Health Organization. The world health report 1999: making a difference. Geneva, Switzerland: World Health Organization; 1999.

[64]

Zong W, Jiang D. Automated ECG rhythm analysis using fuzzy reasoning. In: Proceedings of Computers in Cardiology Conference. Cleveland, USA: IEEE Computer Society Press; 1998. p. 69-72.

Cited By

Gu MZhang YWen YAi GZhang HWang PWang G(2023)A lightweight convolutional neural network hardware implementation for wearable heart rate anomaly detectionComputers in Biology and Medicine10.1016/j.compbiomed.2023.106623155:COnline publication date: 1-Mar-2023
https://dl.acm.org/doi/10.1016/j.compbiomed.2023.106623
Margara ACugola GTamburrelli GBellur UKothari R(2014)Learning from the pastProceedings of the 8th ACM International Conference on Distributed Event-Based Systems10.1145/2611286.2611289(47-58)Online publication date: 26-May-2014
https://dl.acm.org/doi/10.1145/2611286.2611289
Bellazzi RFerrazzi FSacchi L(2011)Predictive data mining in clinical medicineWiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery10.1002/widm.231:5(416-430)Online publication date: 1-Sep-2011
https://dl.acm.org/doi/10.1002/widm.23
Show More Cited By

Temporal abstraction and inductive logic programming for arrhythmia recognition from electrocardiograms
1. Computing methodologies

Recommendations

Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals

Arrhythmia is a cardiac condition caused by abnormal electrical activity of the heart, and an electrocardiogram (ECG) is the non-invasive method used to detect arrhythmias or heart abnormalities. Due to the presence of noise, the non-stationary nature ...
Extracting Rules for Successful Conditions for Artificial Insemination in Dairy Cattle Using Inductive Logic Programming
ICMLC '17: Proceedings of the 9th International Conference on Machine Learning and Computing

This paper describes a method of pattern extraction to identify successful conditions for artificial insemination in dairy cattle using inductive logic programming. The fertility of lactating dairy cows is economically important but the mean ...
Automated detection of shockable and non-shockable arrhythmia using novel wavelet-based ECG features
Abstract
Malignant arrhythmia can lead to sudden cardiac death (SCD). Shockable arrhythmia can be terminated with device electrical shock therapies. Ventricular-tachycardia (VT) and ventricular fibrillation (VF) are responsive to electrical ...
Highlights
- A new optimal three-band wavelet-based system for identification of shockable and non-shockable arrhythmia.

Comments

Information & Contributors

Information

Published In

cover image Artificial Intelligence in Medicine

Artificial Intelligence in Medicine Volume 28, Issue 3

July, 2003

112 pages

ISSN:0933-3657

Issue’s Table of Contents

Copyright © Elsevier B.V. © 2003.

Publisher

Elsevier Science Publishers Ltd.

United Kingdom

Publication History

Published: 01 July 2003

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 24 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Gu MZhang YWen YAi GZhang HWang PWang G(2023)A lightweight convolutional neural network hardware implementation for wearable heart rate anomaly detectionComputers in Biology and Medicine10.1016/j.compbiomed.2023.106623155:COnline publication date: 1-Mar-2023
https://dl.acm.org/doi/10.1016/j.compbiomed.2023.106623
Margara ACugola GTamburrelli GBellur UKothari R(2014)Learning from the pastProceedings of the 8th ACM International Conference on Distributed Event-Based Systems10.1145/2611286.2611289(47-58)Online publication date: 26-May-2014
https://dl.acm.org/doi/10.1145/2611286.2611289
Bellazzi RFerrazzi FSacchi L(2011)Predictive data mining in clinical medicineWiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery10.1002/widm.231:5(416-430)Online publication date: 1-Sep-2011
https://dl.acm.org/doi/10.1002/widm.23
Artikis APaliouras GPortet FSkarlatidis APietzuch PBacon JSventek JCetintemel U(2010)Logic-based representation, reasoning and machine learning for event recognitionProceedings of the Fourth ACM International Conference on Distributed Event-Based Systems10.1145/1827418.1827471(282-293)Online publication date: 12-Jul-2010
https://dl.acm.org/doi/10.1145/1827418.1827471
Rigatos G(2009)Fault detection and isolation based on fuzzy automataInformation Sciences: an International Journal10.1016/j.ins.2009.01.015179:12(1893-1902)Online publication date: 1-May-2009
https://dl.acm.org/doi/10.1016/j.ins.2009.01.015
Callens LCarrault GCordier MFromont EPortet FQuiniou R(2008)Intelligent adaptive monitoring for cardiac surveillanceProceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence10.5555/1567281.1567423(653-657)Online publication date: 27-Jun-2008
https://dl.acm.org/doi/10.5555/1567281.1567423
Fromont ÉQuiniou RCordier M(2005)Learning rules from multisource data for cardiac monitoringProceedings of the 10th conference on Artificial Intelligence in Medicine10.1007/11527770_65(484-493)Online publication date: 23-Jul-2005
https://dl.acm.org/doi/10.1007/11527770_65

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents