# US 2010/0249629 A1 · Segmenting a cardiac acoustic signal

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2010/0249629 A1
- Document ID: US20100249629A1
- Status: Published application
- Kind: A1
- Application number: 12/726,364
- Filed: 2010-03-18
- Published: 2010-09-30
- Earliest claimed: 2009-03-18
- Assignees: Coloplast A/S
- Inventors: Samuel Emil Schmidt; Johannes Jan Struijk
- Web page: https://patentgrep.com/patent/US20100249629A1

## CPC

- A61B 7/04: Electric stethoscopes
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

The invention relates to segmentation of cardiac acoustic signals, such as the heart sound signal, based on statistical algorithms. A duration-dependent Hidden Markov Model is disclosed which models the shifting states of the heart, based on the cardiac acoustic signal and the time spent in the given states relating to physiological events, e.g. the various states of the heart during the heart beat cycle.

## Claims

### Claim 1

A method of segmenting a cardiac acoustic signal, the method comprising:
obtaining a cardiac acoustic signal; and
segmenting the cardiac acoustic signal into time intervals related to physiological events;
wherein the segmenting of the cardiac acoustic signal is based on a duration-dependent Hidden Markov Model analysis of the cardiac acoustic signal.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the duration-dependent Hidden Markov Model models a state duration of the physiological event.

### Claim 3 (depends on 2)

The method according to claim 2, wherein the state duration is defined by a predefined probability distribution.

### Claim 4 (depends on 1)

The method according to claim 1, wherein the segmenting of the cardiac acoustic signal is a segmenting into segments related at least to the first (S1) and second (S2) heart sound.

### Claim 5 (depends on 1)

The method according to claim 1, wherein the duration-dependent Hidden Markov Model assumes a cyclic state sequence with the following transitions: S1→siSys→S2→siDia→S1.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the segmenting reflects the most probable timing of the sequence of segments related at least to the first (S1) and second (S2) heart sound given the cardiac acoustic signal.

### Claim 7 (depends on 1)

The method according to claim 1, wherein prior to segmenting the cardiac acoustic signal, the cardiac acoustic signal is pre-processed.

### Claim 8 (depends on 1)

The method according to claim 1, wherein prior to segmenting the cardiac acoustic signal, the cardiac acoustic signal is processed to an envelope signal.

### Claim 9 (depends on 1, 8)

The method according to claim 1 or 8, wherein the cardiac acoustic signal or the envelope signal is auto-correlated in order to extract the state durations.

### Claim 10 (depends on 8)

The method according to claim 8, wherein the cardiac acoustic signal or the envelope signal is auto-correlated in order to extract the state durations.

### Claim 11 (depends on 1)

The method according to claim 1, wherein the cardiac acoustic signal is obtained in real-time and the segmenting is performed in real-time.

### Claim 12 (depends on 1)

The method according to claim 1, wherein the segmentation is performed on a pre-recorded cardiac acoustic signal.

### Claim 13

An apparatus for segmenting a cardiac acoustic signal, the apparatus comprising:
an input unit for receiving a cardiac acoustic signal; and
a processing unit adapted to segmenting the cardiac acoustic signal;
wherein the processing unit is further adapted to segmenting of the cardiac acoustic signal into time intervals related to physiological events based on a duration-dependent Hidden Markov Model analysis of the cardiac acoustic signal.

### Claim 14 (depends on 1)

A computer-readable medium having stored therein instructions for causing a processing unit to execute the method according to claim 1.
