INFERENCE OF IRREGULAR CARDIAC ACTIVITY USING NEURAL TEMPORAL PERTURBATION FIELDS
DOI:
https://doi.org/10.53808/KUS.2022.ICSTEM4IR.0153-seKeywords:
Cardiac irregularity, Neural Perturbation Fields, Bayesian NetworksAbstract
Early diagnosis of irregular cardiac activity through existing tools such as Electrocardiogram and greater understanding of the underlying processes is critical for saving lives. Cardiac activity originates from a deterministic dynamical system of heart with trajectories following a linear map. Irregular cardiac activity observed in arrhythmia patients adds nonlinearities to the evolution function of the dynamical system underneath. Therefore, it is of great importance to quantitatively measure this non-linearity as a biomarker for impending cardiac diseases in patients. In this work, we formulated a novel mechanism named Neural Temporal Perturbation Field where perceived nonlinearities are modeled through deep neural network with perturbated inputs. Here, we examined the nonlinear state space by modeling the volatility of outputs for slightly adjusted inputs. We discovered that volatility characteristics clearly define a decision threshold that may be employed as a biomarker in clinical practice by applying our technique to data on normal and abnormal heart activity. Our approach resulted in the greater understanding of nonlinearity and volatility of irregular cardiac activity and as a biomarker achieved comparatively better accuracy than the state-of-the-art models.
Downloads
References
Chugh, S. S., Reinier, K., Teodorescu, C., Evanado, A., Kehr, E., Al Samara, M., Mariani, R., Gunson, K., & Jui, J. (2008). Epidemiology of Sudden Cardiac Death: Clinical and Research Implications. Progress in Cardiovascular Diseases, 51(3), 213–228. https://doi.org/10.1016/j.pcad.2008.06.003
Noponen, K., Kortelainen, J., & Seppänen, T. (2009). Invariant trajectory classification of dynamical systems with a case study on ECG. In Pattern Recognition, 42(9), 1832–1844. https://doi.org/10.1016/ j.patcog.2008.12.008
Shiogai, Y., Stefanovska, A., & McClintock, P. V. E. (2010). Nonlinear dynamics of cardiovascular ageing. In Physics Reports, 488(2–3), 51–110. https://doi.org/10.1016/j.physrep.2009.12.003
Oliveira, D. L. S. C., Andreao, R. V., & Sarcinelli-Filho, M. (2011). Premature Ventricular beat classification using a dynamic Bayesian Network. In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2011 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE. https://doi.org/10.1109/iembs.2011.6091235
Akhbari, M., Shamsollahi, M. B., & Jutten, C. (2017). Comparison of ECG fiducial point extraction methods based on dynamic Bayesian network. In 2017 Iranian Conference on Electrical Engineering (ICEE). 2017 Iranian Conference on Electrical Engineering (ICEE). https://doi.org/10.1109/iraniancee.2017. 7985197
Bousseljot R., Kreiseler D., Schnabel, A., Nutzung, D. E. K. G. Signaldatenbank, Cardiodat, D. P. T. B., Das, ü. (1995). Internet. Biomedizinische Technik, Band 40, Ergänzungsband 1, S 317.
Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101(23), e215–e220.
Xie, Y., Takikawa, T., Saito, S., Litany, O., Yan, S., Khan, N., Tombari, F., Tompkin, J., Sitzmann, V., & Sridhar, S. (2021). Neural Fields in Visual Computing and Beyond (Version 4). arXiv. https://doi.org/10. 48550/ARXIV.2111.11426
Balda, E. R., Behboodi, A., & Mathar, R. (2018). Perturbation Analysis of Learning Algorithms: A Unifying Perspective on Generation of Adversarial Examples (Version 1). arXiv. https://doi.org/10.48550/ ARXIV.1812.07385
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Khulna University Studies
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.