Why should you model time when you use Markov models for heart sound analysis

Auscultation is a widely used technique in clinical activity to diagnose heart diseases. However, heart sounds are difficult to interpret because a) of events with very short temporal onset between them (tens of milliseconds) and b) dominant frequencies that are out of the human audible spectrum. In this paper, we propose a model to segment heart sounds using a semi-hidden Markov model instead of a hidden Markov model. Our model in difference from the state-of-the-art hidden Markov models takes in account the temporal constraints that exist in heart cycles. We experimentally confirm that semi-hidden Markov models are able to recreate the “true” continuous state sequence more accurately than hidden Markov models. We achieved a mean error rate per sample of 0.23.

[1]  A. Guyton,et al.  Textbook of Medical Physiology , 1961 .

[2]  Søren Højsgaard,et al.  Hidden Semi Markov Models for Multiple Observation Sequences: The mhsmm Package for R , 2011 .

[3]  Rui Pedro Paiva,et al.  Noise detection during heart sound recording using periodicity signatures , 2011, Physiological measurement.

[4]  E. Toft,et al.  Segmentation of heart sound recordings from an electronic stethoscope by a duration dependent Hidden-Markov Model , 2008, 2008 Computers in Cardiology.

[5]  W. Marsden.  I and J , 2012 .

[6]  Kevin Barraclough,et al.  I and i , 2001, BMJ : British Medical Journal.

[7]  I. Hartimo,et al.  Heart sound segmentation algorithm based on heart sound envelogram , 1997, Computers in Cardiology 1997.

[8]  Miguel Tavares Coimbra,et al.  Exploring embedding matrices and the entropy gradient for the segmentation of heart sounds in real noisy environments , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  Yong-Joo Chung.  Classification of Continuous Heart Sound Signals Using the Ergodic Hidden Markov Model , 2007, IbPRIA.

[10]  Miguel Tavares Coimbra,et al.  A multi-spot exploration of the topological structures of the reconstructed phase-space for the detection of cardiac murmurs , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[11]  M. Inés Torres,et al.  Pattern Recognition and Image Analysis , 2017, Lecture Notes in Computer Science.

[12]  Miguel Tavares Coimbra,et al.  DigiScope — Unobtrusive collection and annotating of auscultations in real hospital environments , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Shankar M. Krishnan,et al.  Neural network classification of homomorphic segmented heart sounds , 2007, Appl. Soft Comput..

[14]  N. Intrator,et al.  Detection and identification of heart sounds using homomorphic envelogram and self-organizing probabilistic model , 2005, Computers in Cardiology, 2005.

[15]  Jithendra Vepa,et al.  Classification of heart murmurs using cepstral features and support vector machines , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.