Probabilistic data fusion model for heart beat detection from multimodal physiological data

Automatic detection of heart beats constitutes the basis for electrocardiogram (ECG) analysis and mainly relies on detecting QRS complexes. Detection is typically performed by analyzing the ECG signal. However, when signal quality is low, it often leads to the triggering of false alarms. A contemporary approach to reduce false alarm rate is to use multimodal data such as arterial blood pressure (ABP) or photoplethysmogram (PPG) signals. To leverage the correlated temporal nature of these signals, a probabilistic data fusion model for heart beat detection is proposed. A hidden Markov model is used to decode waveforms into segments. A Bayesian network is employed for capturing intersegmental coupling between waveforms and detecting heart beats. The performance of the proposed system was evaluated on a dataset provided by PhysioNet Challenge 2014: Robust Detection of Heart Beats in Multimodal Data. The proposed method is comparatively analyzed with a baseline hidden Markov model method for ECG and an improvement of 9% in sensitivity and 26% in positive predictivity is observed. The efficiency of the proposed model is also compared with related data fusion methods and a comparable performance is found. The robustness of the method is analyzed by inducting Gaussian noise into the dataset. A performance gain of 31% both in sensitivity and positive predictivity is obtained in the worst case where both ECG and ABP are noisy with 6 dB signal-to-noise ratio.

PDF

___

[1] K¨ohler B , Hennig C, Orglmeister R. The principles of software QRS detection. IEEE Eng Med Biol Mag 2002; 21: 42-57.
[2] Costa D, Stern R, Cano G, Briller S. An approach to cardiac arrhythmia analysis using hidden Markov models. IEEE T Bio-Med Eng 1990; 37: 826-836.
[3] Andreao R, Dorizzi B, Boudy J. ECG signal analysis through hidden Markov models. IEEE T Bio-Med Eng 2006; 539: 1541-1549.
[4] Muller SMT, Andreao RV, Boudy J, Garcia-Salicetti, Filho TFB. Online HMM adaptation applied to ECG signal analysis. In: IEEE International Symposium on Industrial Electronics; 913 July 2006; Quebec, Canada. New York, NY, USA: IEEE. pp. 511-514.
[5] Hughes N, Tarassenko L, Roberts S. Markov models for automated ECG interval analysis. In: Advances in Neural Information Processing Systems; 2004; Vancouver, Canada. pp. 611-618.
[6] Thomas J, Rose C, Charpillet F. A support system for ECG segmentation based on hidden Markov models. In: Proceedings of IEEE Engineering Medicine Biology Society; 2326 August 2007; Lyon, France. New York, NY, USA: IEEE. pp. 3228-3231.
[7] Clifford G, McSharry P. A realistic coupled nonlinear artificial ECG, BP and respiratory signal generator for assessing noise performance of biomedical signal processing algorithms. In: Proceedings of SPIE; 2004. pp. 291-302.
[8] Li Q, Clifford G. Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a Kalman filter. Physiol Meas 2008; 29: 15-32.
[9] Pimentel M, Santos M, Springer D, Clifford G. Heart beat detection in multimodal physiological data using a hidden semi-Markov model and signal quality indices. Physiol Meas 2015; 36: 1717-1727.
[10] Macii D, Boni A, Cecco M, Petri D. Tutorial 14: multisensor data fusion. IEEE Instru Meas Mag 2008; 11: 24-33.
[11] Rabiner R, Juang B. An introduction to hidden Markov models. IEEE ASSP Mag 1989; 3: 4-16.
[12] Rabiner R. A tutorial on hidden Markov models and selected applications. P IEEE 1989; 77: 257-286.
[13] Aboy M, McNames J, Thong T, Tsunami D, Ellenby M, Goldstein B. An automatic beat detection algorithm for pressure signals. IEEE T Bio-Med Eng 2005; 52: 1662-1670.
[14] Koller D, Friedman N. Probabilistic Graphical Models: Principles and Techniques. 1st ed. Cambridge, MA, USA: MIT Press, 2009.
[15] Murphy K. Dynamic Bayesian networks: representation, inference and learning. PhD, University of California, Berkeley, CA, USA, 2002.
[16] Silva I, Moody B, Behar J, Johnson A, Oster J, Clifford GD, Moody GB. Robust detection of heart beats in multimodal data. Physiol Meas 2015; 36: 1629.
[17] Ganeshapillai G. Methods to improve the signal quality of corrupted multi-parameter physiological signals. PhD, Massachusetts Institute of Technology, Cambridge, MA, USA, 2011.
[18] Lam J. Preserving useful info while reducing noise of physiological signals by using wavelet analysis. MSc, University of North Florida, Jacksonville, FL, USA, 2011.