A Model for Atrial Fibrillation Detection Based on Differentiation and Compression of Interbeat Interval Sequences
https://doi.org/10.15514/ISPRAS-2025-37(2)-21
Abstract
Atrial fibrillation is the most common arrhythmia with a major impact on public health. This paper presents a model for automatic detection of atrial fibrillation episodes in ECG, using information compression and numerical differentiation for classification of beat-to-beat interval sequences. The core of the model is normalized compression distance based on the theory of universal similarity metrics. To enable class discrimination by compression we consider finite-difference representation of interval sequences with subsequent quantization procedure. In particular, we introduce a simple Δ5RR-interval representation which improves the sensitivity of the model to heart rhythm fluctuations. Our model achieves 96.37% sensitivity, 97.74% specificity and 0.935 MCC in 8x5-fold cross-validation on the MIT-BIH AFDB dataset using a segment window of 128 R-peaks. The particular advantage of the model is the classification quality in a few-shot learning setting, i.e., a training set with a small number of sequence observations can be used for classification of sufficiently large test sets.
Keywords
normalized compression distance,
few-shot learning,
atrial fibrillation detection,
heart rate,
RR-interval sequences.
Supporting agencies: The author would like to thank Olga Eduardovna Solovyova for scientific supervision. The work was supported by the state task to IIP UrB RAS № 122022200089-4.
About the Author
Nikita Sergeevich MARKOV
Institute of Immunology and Physiology of the Ural Branch of the Russian Academy of Sciences, Ural Federal University
Russian Federation
Russian Federation
Junior researcher at the Laboratory of Translational Medicine and Bioinformatics of the Institute of Immunology and Physiology UrB RAS, assistant at the Department of Computational Mathematics and Computer Science of the Ural Federal University. Research interests: machine learning in physiology and medicine, few-shot learning, biomedical signal processing, high-performance computations, mathematical modeling in biophysics.
References
1. Staerk L., Sherer J. A., Ko D., Benjamin E. J., Helm R. H. Atrial fibrillation: epidemiology, pathophysiology, and clinical outcomes. Circulation research, vol. 120, issue 9, 2017, pp. 1501-1517. DOI:10.1161/CIRCRESAHA.117.309732.
2. Faust O., Ciaccio E. J., Acharya U. R. A review of atrial fibrillation detection methods as a service. International journal of environmental research and public health, vol. 17, issue 9, 2020, p. 3093. DOI:10.3390/ijerph17093093.
3. Moody G. B., Mark R. G. The impact of the MIT-BIH arrhythmia database. IEEE engineering in medicine and biology magazine, vol. 20, issue 3, 2001, pp. 45-50. DOI:10.1109/51.932724.
4. D’Aloia M., Longo A., Rizzi M. Noisy ECG signal analysis for automatic peak detection. Information, vol. 10, issue 2, 2019, p. 35.
5. Georgiou K., Larentzakis A. V., Khamis N. N., Alsuhaibani G. I., Alaska Y. A., Giallafos E. J. Can wearable devices accurately measure heart rate variability? A systematic review. Folia medica, vol. 60, issue 1, 2018, pp. 7-20. DOI:10.2478/folmed-2018-0012.
6. Zhou K., Liu Z., Qiao Y., Xiang T., Loy C. C. Domain generalization: A survey. IEEE transactions on Pattern Analysis and Machine Intelligence, vol. 45, issue 4, 2004, pp. 4396-4415. DOI:10.1109/TPAMI.2022.3195549.
7. Li M., Chen X., Li X., Ma B., Vitányi P. M. B. The similarity metric. IEEE transactions on Information Theory, vol. 50, issue 12, 2004, pp. 3250-3264. DOI:10.1109/TIT.2004.838101.
8. Tateno K., Glass L. Automatic detection of atrial fibrillation using the coefficient of variation and density histograms of RR and ΔRR intervals. Medical and Biological Engineering and Computing, vol. 39, 2001, pp. 664-671. DOI:10.1007/BF02345439.
9. Fornberg B. Generation of finite difference formulas on arbitrarily spaced grids. Mathematics of computation, vol. 51, issue 184, 2017, pp. 699-706. DOI:10.1090/S0025-5718-1988-0935077-0.
10. David A., Sergei V. k-means++: The Advantages of Careful Seeding. In Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms, 2007, pp. 1027-1035. Available at the URL: http://ilpubs.stanford.edu:8090/778/.
11. Gailly J.L., Adler M. GNU gzip. GNU Operating System, 1992. Available at the URL: https://www.gnu.org/software/gzip/manual/gzip.pdf.
12. Cilibrasi R., Vitányi P. M. B. Clustering by compression. IEEE Transactions on Information theory, vol. 51, issue 4, 2005, pp. 1523-1545. DOI:10.1109/TIT.2005.844059.
13. Bennett C. H., Gács P., Li M., Vitányi P. M. B., Zurek W. H. Information distance. IEEE Transactions on information theory, vol. 44, issue 4, 1998, pp. 1407-1423. DOI:10.1109/18.681318.
14. Goldberger A. L., Amaral L. A. N., Glass L., Hausdorff J. M., Ivanov P. C., Mark R. G., Mietus J. E., Moody G. B., Peng C. K., Stanley H. E. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, vol. 101, issue 23, 2000, pp. e215-e220. DOI: 10.1161/01.CIR.101.23.e21.
15. Moody G. A new method for detecting atrial fibrillation using RR intervals. Proc. Comput. Cardiol., vol. 10, 1983, pp. 227-230.
16. Chicco D., Jurman G. The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification. BioData Mining, vol. 16, issue 1, 2023, p. 1. DOI:10.1186/s13040-023-00322-4.
17. Efron B. Bootstrap methods: another look at the jackknife. Breakthroughs in statistics: Methodology and distribution. In Breakthroughs in Statistics. Springer Series in Statistics. New York, Springer, 1992, pp. 569-593. DOI:10.1007/978-1-4612-4380-9_41.
18. Benjamini Y., Hochberg Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal statistical society: series B (Methodological), vol. 57, issue 1, 1995, pp. 289-300. DOI: 10.1111/j.2517-6161.1995.tb02031.x.
19. Andersen R. S., Poulsen E. S., Puthusserypady S. A novel approach for automatic detection of Atrial Fibrillation based on Inter Beat Intervals and Support Vector Machine. In 2017 39th annual international conference of the IEEE engineering in medicine and biology society (EMBC). New York, IEEE, 2017. pp. 2039-2042. DOI:10.1109/EMBC.2017.8037253.
20. Xia Y., Wulan N., Wang K., Zhang H. Detecting atrial fibrillation by deep convolutional neural networks. Computers in biology and medicine, vol. 93, 2018, pp. 84-92. DOI: 10.1016/j.compbiomed.2017.12.007.
21. Wang Y., Yao Q., Kwok J. T., Ni L. M. Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys, vol. 53, issue 3, 2020, pp. 1-34. DOI:10.1145/3386252.
22. Ng Y., Liao M. T., Chen T. L., Lee C. K., Chou C. Y., Wang W. Few-shot transfer learning for personalized atrial fibrillation detection using patient-based siamese network with single-lead ECG records. Artificial Intelligence in Medicine, vol. 144, 2023, p. 102644. DOI: 10.1016/j.artmed.2023.102644.
23. Abdelfattah M. S., Hagiescu A., Singh D. Gzip on a chip: High performance lossless data compression on fpgas using opencl. In Proceedings of the international workshop on openCL 2013 & 2014. New York, ACM, 2014. pp. 1-9. DOI: 10.1145/2664666.2664670.
24. Lee K.-S., Park H.-J., Kim J.E., Kim H.J., Chon S., Kim S., Jang J., Kim J.-K., Jang S., Gil Y., Ho S.S. Compressed deep learning to classify arrhythmia in an embedded wearable device. Sensors. vol. 22, issue 5, 2022, p. 1776. DOI: 10.3390/s22051776.
25. Yang Z., Yu Y., You C., Steinhardt J., Ma Y. Rethinking bias-variance trade-off for generalization of neural networks. In Proceedings of the 37th International Conference on Machine Learning. Brookline, JMLR, 2020. pp. 10767-10777. URL:https://proceedings.mlr.press/v119/yang20j.html.
26. Abrosimova M., Rebak A., Novikov R., Markov N. Classification with PPMd Compression in Few-Shot Learning: The Case of Eye-Tracking Dyslexia Detection. In 2024 IEEE Ural-Siberian Conference on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT). New York, IEEE, 2024. pp. 204-207. DOI:10.1109/USBEREIT61901.2024.10583975.
Review
For citations:
MARKOV N.S. A Model for Atrial Fibrillation Detection Based on Differentiation and Compression of Interbeat Interval Sequences. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(2):281-300. https://doi.org/10.15514/ISPRAS-2025-37(2)-21
Email this article 