Apnea bradycardia detection based on new coupled hidden semi Markov model

In this paper, a method for apnea bradycardia detection in preterm infants is presented based on coupled hidden semi Markov model (CHSMM). CHSMM is a generalization of hidden Markov models (HMM) used for modeling mutual interactions among different observations of a stochastic process through using finite number of hidden states with corresponding resting time. We introduce a new set of equations for CHSMM to be integrated in a detection algorithm. The detection algorithm was evaluated on a simulated data to detect a specific dynamic and on a clinical dataset of electrocardiogram signals collected from preterm infants for early detection of apnea bradycardia episodes. For simulated data, the proposed algorithm was able to detect the desired dynamic with sensitivity of 96.67% and specificity of 98.98%. Furthermore, the method detected the apnea bradycardia episodes with 94.87% sensitivity and 96.52% specificity with mean time delay of 0.73 s. The results show that the algorithm based on CHSMM is a robust tool for monitoring of preterm infants in detecting apnea bradycardia episodes. Graphical Abstract Apnea Bradycardia detection using Coupled hidden semi Markov Model from electrocardiography. In this model, a sequence of hidden states is assigned to each observation based on the effects of previous states of all observations.

[1]  E. Eichenwald.  Apnea of Prematurity , 2016, Pediatrics.

[2]  C. Poets,et al.  The Relationship between Bradycardia, Apnea, and Hypoxemia in Preterm Infants , 1993, Pediatric Research.

[3]  M Javorka,et al.  Apnea in preterm newborns: determinants, pathophysiology, effects on cardiovascular parameters and treatment , 2014 .

[4]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[5]  Shunzheng Yu,et al.  Practical implementation of an efficient forward-backward algorithm for an explicit-duration hidden Markov model , 2006, IEEE Transactions on Signal Processing.

[6]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

[7]  A NeathAndrew,et al.  The Bayesian information criterion , 2012 .

[8]  Mohammad B. Shamsollahi,et al.  Early detection of apnea-bradycardia episodes in preterm infants based on coupled hidden Markov model , 2013, IEEE International Symposium on Signal Processing and Information Technology.

[9]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10]  Julien Fleureau,et al.  Modelling temporal evolution of cardiac electrophysiological features using Hidden Semi-Markov Models , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[11]  J. Cavanaugh,et al.  The Bayesian information criterion: background, derivation, and applications , 2012 .

[12]  Alex Pentland,et al.  Coupled hidden Markov models for complex action recognition , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  K. Barrington,et al.  Apnea Is Associated with Neurodevelopmental Impairment in Very Low Birth Weight Infants , 2004, Journal of Perinatology.

[14]  Christian F Poets,et al.  Apnea of prematurity: What can observational studies tell us about pathophysiology? , 2010, Sleep medicine.

[15]  D. Mu,et al.  Apnea of prematurity: from cause to treatment , 2011, European Journal of Pediatrics.

[16]  F. Portet,et al.  Evaluation of On-Line Bradycardia Boundary Detectors from Neonatal Clinical Data , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[17]  Ramakant Nevatia,et al.  Coupled Hidden Semi Markov Models for Activity Recognition , 2007, 2007 IEEE Workshop on Motion and Video Computing (WMVC'07).

[18]  Miguel Altuve,et al.  Online apnea–bradycardia detection based on hidden semi-Markov models , 2014, Medical & Biological Engineering & Computing.

[19]  G. Carrault,et al.  Algorithm fusion for the early detection of apnea-bradycardia in preterm infants , 2006, 2006 Computers in Cardiology.

[20]  Joel Smoller,et al.  Qualitative theory of the FitzHugh-Nagumo equations , 1978 .

[21]  Nianjun Liu,et al.  Using Coupled Hidden Markov Models to Model Suspect Interactions in Digital Forensic Analysis , 2006, 2006 International Workshop on Integrating AI and Data Mining.

[22]  Miguel Altuve,et al.  Multivariate ECG analysis for apnoea–bradycardia detection and characterisation in preterm infants , 2011 .

[23]  Mohammad B. Shamsollahi,et al.  Coupled Hidden Markov Model-Based Method for Apnea Bradycardia Detection , 2016, IEEE Journal of Biomedical and Health Informatics.