Heart diseases diagnosis using HMM

The bare ear and the stethoscope were until recently of great help in classifying most heart diseases especially those related to valve problems. The newly developed electronic stethoscope and phonocardiography represent useful tools for recording heart sound signals. In this paper a diagnostic technique for heart diseases using heart sounds is suggested. Wavelet decomposition and mel cepstrum are used for feature extraction. Classification of the different heart diseases is then done using hidden Markov models (HMM). Three different techniques have been used and compared. The obtained recognition rates (RR) were 97.3%, 98.2%, and 99.1%.

[1]  L. Sakari,et al.  A heart sound segmentation algorithm using wavelet decomposition and reconstruction , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[2]  N. Hamdy,et al.  Heart diseases diagnosis using heart sounds , 2002, Proceedings of the Nineteenth National Radio Science Conference.

[3]  Raimo Sepponen,et al.  Multimedia personal computer based phonocardiography , 1996, Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

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

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

[6]  Joseph Picone,et al.  Signal modeling techniques in speech recognition , 1993, Proc. IEEE.