Method and device for the determination of murmur frequency band

• US 8,649,854 B2
• Filed: 02/06/2009
• Issued: 02/11/2014
• Est. Priority Date: 02/06/2008
• Status: Active Grant

• Current Assignee: Capis SPRL
• Original Assignee: Capis SPRL
• Inventors: Sepehri, Amir A., Gharehbaghi, Arash
• Primary Examiner(s): Koharski, Christopher D
• Assistant Examiner(s): KIMBALL, JEREMIAH T
• Application Number:
  US12/866,139
• Publication Number:
  US 20110021939A1
• Time in Patent Office: 1,831 Days
• Field of Search: 600/528
• US Class Current: 600/523
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 7/00 Instruments for auscultation
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R

Abstract

The present invention is related to a method for the determination of frequency band characteristics of a heart disease. A first set of phonocardiograms are recorded from a first set of reference healthy patients, and a second set of phonocardiograms from a second set of patients suffering of a heart disease. Spectral energies of all possible frequency bands are then calculated. These spectral energies are then compared in order to determine an optimized frequency band that gives rise to the maximal distinction between spectral energies of the phonocardiograms from first and second set of phonocardiograms.

Claims

1. A method for a determination of frequency band characteristic of a heart disease comprising the steps of:

using an electronic stethoscope, collecting and/or recording a first set of phonocardiograms from a first set of reference healthy patients, and a second set of phonocardiograms from a second set of patients suffering of said heart disease;

defining a frequency sampling rate and a maximum cutoff frequency, producing a finite set of sampled frequencies;

calculating spectral energies at all sampled frequencies, said spectral energies being calculated on the entire phonocardiogram;

calculating spectral energies of all possible frequency bands by summing spectral energies at sample frequencies belonging to said frequency bands;

comparing said spectral energies of all possible frequency bands; and

determining a frequency band giving rise to a maximal distinction between spectral energies of the said phonocardiograms from the first and the second set of phonocardiograms.

2. A method for a detection of heart diseases comprising the steps of:

determining frequency band giving rise to a maximal distinction between spectral energies of the said phonocardiograms from the first and the second set of phonocardiograms by using the method of claim 1; and

comparing said determined frequency band energy of phonocardiograms of a patient to corresponding frequency band energy of the first and the second set of phonocardiograms to define if said patient suffers of the heart disease.

3. The method according to claim 1 wherein the heart disease is selected from the group consisting of ventricular septal defect, patent ductus arteriosus, pulmonary valve stenosis, tetralogy of fallot, aortic stenosis, atrial septal defect, coarctation of aorta, transposition of great arteries, atrioventricular septal defect, truncus arteriosus, tricuspid atresia, anomalous pulmonary venous connection or a mixture thereof.

4. The method according to claim 1 wherein the maximum cutoff frequency is about 500 Hz.

5. The method according to claim 2 wherein the determined frequency band is comprised of between 88 Hz and 96 Hz and the heart disease is ventricular septal defect.

6. The method according to claim 2 wherein the determined frequency band is comprised of between 50 Hz and 60 Hz and the heart disease is tetralogy of fallot.

7. The method according to claim 2 wherein the determined frequency band is comprised of between 15 Hz and 121 Hz and the heart disease is ventricular patent ductus arteriosus.

8. The method according to claim 2 wherein the determined frequency band is comprised of between 17 Hz and 129 Hz and the heart disease is aortic stenosis.

9. The method according to claim 2 wherein the determined frequency band is comprised of between 16 Hz and 32 Hz and the heart disease is pulmonary valve stenosis.

10. The method according to claim 1 wherein the spectral energies are calculated only in the systolic segment of the phonocardiogram.

11. The method according to claim 1 wherein the comparison between phonocardiograms is performed by a neural network.

12. The method according to claim 11 wherein the neural network is of multilayer perceptron type.

13. A device comprising non-transitory phonocardiogram(s) recording media, non-transitory phonocardiogram(s) storage media, non-transitory output media, a processor and a set of instructions for performing the method according claim 1.

14. A set of instructions, on a non-transitory computer readable medium, executable on a programmable device, which when executed on said programmable device, performs the method according to claim 1.