Abstract
Atrial fibrillation is the most common arrhythmia, which substantially increases the risk of stroke and other heart-related complications. Hence, forecasting the onset of paroxysmal atrial fibrillation (PAF) has become increasingly paramount and influential in AF managements and preventive treatments. Previous studies mainly focused on utilizing the morphological-temporal or time-frequency features from the surface electrocardiogram (ECG) to heighten the accuracy of PAF classification but not truely yielded onset predictions. To address this issue, this paper proposes a model that deploys the adaptive neuro-fuzzy inference system (ANFIS) and Unscented Kalman Filter to approximate the nonlinear-system state distribution for PAF onset prediction. The model is based on a combination of Kalman filter algorithm and a neural fuzzy network to predict PAF onset in 70 patients. Initially, we extracted the feature AWSUM to quantify the accumulation of extrasystolic beats within 30-min ECG recordings prior to the PAF onset of 24 patients. The extracted features then were utilized to reconstruct the dynamic-system state space, on which neural fuzzy based UKF algorithm were performed. The forecasting results highlighted low-level prediction errors averaged over 24 patients, by which RMSE = 0.42 ± 0.24 for the training data and RMSE = 0.34 ± 0.46 for the testing data; the testing-error had large variance due to the interpatient variabilities and abrupt changes in the system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Feinberg, W.M., et al.: Prevalence, age distribution, and gender. Arch. Intern. Med. 155, 469–473 (1995)
Levy, S.: Atrial fibrillation: old and new classifications, p. 107–113, Futura Publishing, Armonk, NY (1998)
Takahashi, N., et al.: Clinical features of paroxysmal atrial fibrillation. Jpn. Heart J. 22(2), 143–149 (1981)
Das, S.: Time series analysis. Princeton University Press, Princeton, NJ (1994)
Thong, T., et al.: Prediction of paroxysmal atrial fibrillation by analysis of atrial premature complexes. IEEE Trans. Biomed. Eng. 51(4), 561–569 (2004)
Lynn, K., Chiang, H.: A two-stage solution algorithm for paroxysmal atrial fibrillation prediction. In: Computers in Cardiology 2001, IEEE (2001)
Mohebbi, M., Ghassemian, H.: Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal. Comput. Methods Programs Biomed. 105(1), 40–49 (2012)
Shumway, R.H., Stoffer, D.S.: State-Space models. In: Time Series Analysis and its Applications, p. 319–404. Springer (2011)
Zong, W., Mukkamala, R., Mark, R.: A methodology for predicting paroxysmal atrial fibrillation based on ECG arrhythmia feature analysis. In: Computers in Cardiology 2001, IEEE (2001)
Bui, C., et al.: Time series forecasting for healthcare diagnosis and prognostics with the focus on cardiovascular diseases. In: The 6th International Conference on the Development of Biomedical Engineering in Vietnam, IFMBE Proceedings, vol. 63, pp. 809–818. Springer (2017)
Cheng, C., et al.: Time series forecasting for nonlinear and nonstationary processes: a review and comparative study. IIE Trans. 47(10):1053–1071 (2015)
Zarchan, P.: Progress in astronautics and aeronautics: fundamentals of Kalman filtering: a practical approach. In: Aiaa, vol. 208 (2005)
Julier, S.J., Uhlmann, J.K.: New extension of the Kalman filter to nonlinear systems. In Signal processing, sensor fusion, and target recognition VI, International Society for Optics and Photonics (1997)
Julier, S.J., Uhlmann, J.K.: Unscented filtering and nonlinear estimation. Proc.IEEE 92(3), 401–422 (2004)
Grinstead, C.M., Snell J.L.: Introduction to Probability, American Mathematical Soc (2012)
Jang, J.-S.: ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans. Syst. Man Cybern. 23(3), 665–685 (1993)
Jang, J.-S.R. Fuzzy modeling using generalized neural networks and Kalman filter algorithm. In AAAI. (1991)
Moody, G., et al.: Predicting the onset of paroxysmal atrial fibrillation: The Computers in Cardiology Challenge 2001. In: Computers in Cardiology 2001. IEEE (2001)
Casdagli, M., et al.: State space reconstruction in the presence of noise. Physica D: Nonlinear Phenomena 51(1–3), 52–98 (1991)
Le, T.Q., et al.: Topology and random-walk network representation of cardiac dynamics for localization of myocardial infarction. IEEE Trans. Biomed. Eng. 2325–2331 (2013)
Conflict of Interest
The authors declare that they have no conflict of interest.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bui, C.T., Huynh, P.K., Phan, H.T., Le, T.Q., Van Toi, V. (2020). Developing Neural-fuzzy-based Unscented Kalman Filter Algorithm for Atrial Fibrillation Onset Prediction. In: Van Toi , V., Le, T., Ngo, H., Nguyen, TH. (eds) 7th International Conference on the Development of Biomedical Engineering in Vietnam (BME7). BME 2018. IFMBE Proceedings, vol 69. Springer, Singapore. https://doi.org/10.1007/978-981-13-5859-3_20
Download citation
DOI: https://doi.org/10.1007/978-981-13-5859-3_20
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-5858-6
Online ISBN: 978-981-13-5859-3
eBook Packages: EngineeringEngineering (R0)