DE202022103576U1 - A heart sound analysis system to detect heart disease - Google Patents

Abstract

A cardiac analysis system for detecting cardiac disease (100), the system (100) comprising:
a heart murmur sensor (102) comprising at least one electrode capable of generating an electrical signal representative of at least one heart murmur of a user;
a pre-processing module (104) connected to the cardiac sound sensor (102) for enhancing the generated electrical signal;
a feature extraction module (106) coupled to the pre-processing module (104) for extracting a plurality of features from an enhanced signal, wherein signal processing circuitry is configured in the extraction module (106) for analyzing the extracted features to detect cardiac disease ; and
a classification module (108) connected to the feature extraction module (106) to classify the plurality of features into a plurality of classes, a first class detecting a heart disease state upon detection of an abnormal murmur along with a normal murmur, wherein a second class detects a normal condition upon detection of the normal sound, and a third condition detects failure of a ventricle.

Description

FIELD OF THE INVENTION

The present invention relates to the field of heart disease detection. More particularly, the present invention relates to the field of heart murmur analysis to detect heart disease.

BACKGROUND OF THE INVENTION

An estimated 32 percent of all deaths worldwide in 2019 were due to cardiovascular disease (CVD), which is one of the leading causes of death worldwide. About three quarters of these deaths occur in low- and middle-income countries. Cardiovascular disease needs to be caught early so that it can be treated with medication and lifestyle changes before it becomes a serious condition. Attempts have been made over the past decade to apply machine learning (ML) to healthcare to make healthcare more accessible by reducing costs, effort, and time. This will reduce the burden on the healthcare system and result in a healthier population.

Clinically, the use of new techniques such as ultrasound cardiogram, color ultrasound, CT, MRI makes the doctor can obtain the most direct and accurate diagnosis basis than cardiac auscultation. However, because these equipment manufacturing costlinesses, bulky and complicated operation are inconvenient for the Popularization in inferior degree hospital and community medicine.

On the other hand, auditory tones can respond effectively to the heart's valve activity and blood flow situation, e.g. B. on the closure of the atrioventricular (AV) valves, and they produce the main components and the occurrence of the second heart sound during the closure of the semilunar valves. In many cardiovascular diseases, especially in diseases of the heart valves, the auditory noises are important diagnostic clues, which is why very extensive clinical procedures are used. But cardiac auscultation is easy to be subjected to the influence of doctors experience, auscultation level.

Historically, some heart sound detection systems and methods have been used to diagnose diseases CN100418480C and US7922669B2 were disclosed.

However, the above prior art discloses an expensive, complex and inaccurate system for detecting heart disease.

Therefore, there is a need to develop an inexpensive, simple, accurate, and non-invasive system for heart disease detection.

The technical advance disclosed by the present invention overcomes the limitations and disadvantages of existing and conventional systems and methods.

SUMMARY OF THE INVENTION

• Ziel der vorliegenden Erfindung ist es, ein Herzschallanalysesystem zur Erkennung von Herzerkrankungen bereitzustellen,
• Ein weiteres Ziel der vorliegenden Erfindung ist es, ein nicht-invasives, einfaches System bereitzustellen, und
• Ein weiteres Ziel der vorliegenden Erfindung ist es, ein kostengünstiges und genaues System zur Erkennung von Herzerkrankungen bereitzustellen.

The present invention generally relates to a cardiac phonoanalysis system for detecting cardiac diseases.

• The aim of the present invention is to provide a heart sound analysis system for detecting heart diseases
• Another object of the present invention is to provide a non-invasive, simple system, and
• Another object of the present invention is to provide an inexpensive and accurate cardiac disease detection system.

In one embodiment, a heart sound analysis system for detecting heart disease, the system comprising: a heart murmur sensor comprising at least one electrode operable to generate an electrical signal representative of at least one heart murmur of a user; a pre-processing module connected to enhance the generated electrical signal; a feature extraction module connected to the pre-processing module to extract a plurality of features from the enhanced signal, signal processing circuitry included in the extraction module to analyze the extracted features to detect cardiac disease and a classification module connected to the feature extraction module to classify the plurality of features into a plurality of classes, a first class detecting a heart disease condition upon detection of an abnormal sound along with a normal sound, a second class detecting a normal condition upon detection of the normal sound and wherein a third condition detects a failure of a ventricle.

In one embodiment, the pre-processing module uses a filter to remove the Noise signal from the generated electrical signal and improves the signal quality.

In one embodiment, the heart disease is either an enlargement of the heart chambers, heart valve disease, or heart muscle problems such as dilated cardiomyopathy or restrictive cardiomyopathy.

In one embodiment, the phonocardial sensor measures either a lub (s1) or a sub (s2) representing normal heart valve closure.

In one embodiment, the murmur sensor measures the abnormal sound as either an S3 diastole signal or an S4 systole signal or a combination thereof to detect the abnormal condition.

In one embodiment, the S3 signal detects the presence of cardiac disease and the S4 signal detects left ventricular failure in the heart.

In one embodiment, a display is coupled to the classification module to display the classified signal based on the recognized plurality of classes.

In one embodiment, the classification module is equipped with a deep learning neural network to classify the plurality of extracted features.

In one embodiment, a phonocar chart is connected to the phonocardial sensor to record the phonocardial sensor.

In order to further clarify the advantages and features of the present invention, a more detailed description of the invention will be made by reference to specific embodiments thereof illustrated in the attached figure. It is understood that this figure represents only typical embodiments of the invention and therefore should not be considered as limiting its scope. The invention will be described and illustrated with additional specificity and detail with the accompanying figure.

character list

• 1 ein Blockdiagramm eines Herztonanalysesystems zur Erkennung von Herzerkrankungen zeigt.

These and other features, aspects and advantages of the present invention will be better understood when the following detailed description is read with reference to the accompanying figure, in which like characters represent like parts throughout the figure, wherein:

• 1 Figure 12 shows a block diagram of a heart sound analysis system for detecting heart disease.

Those skilled in the art will understand that the elements in the figure are shown for simplicity and are not necessarily drawn to scale. For example, the flow charts illustrate the method of key steps to enhance understanding of aspects of the present disclosure. Furthermore, one or more components of the device in the figure may be represented by conventional symbols, and the figure only shows the specific details relevant to understanding the embodiments of the present disclosure, not to encircle the figure with details to overload, which are easily recognizable to those skilled in the art familiar with the present description.

DETAILED DESCRIPTION

For the purposes of promoting an understanding of the invention, reference will now be made to the embodiment illustrated in the Figure and specific language will be used to describe the same. It should be understood, however, that no limitation on the scope of the invention is intended, and such alterations and further modifications to the illustrated system and such further applications of the principles of the invention set forth therein are contemplated as would occur to those skilled in the art invention would normally come to mind.

Those skilled in the art will understand that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not intended to be limiting.

When this specification refers to "an aspect," "another aspect," or the like, it means that a particular feature, structure, or characteristic described in connection with the embodiment is present in at least one embodiment of the present invention. Therefore, the phrases "in one embodiment," "in another embodiment," and similar phrases throughout this specification may or may not all refer to the same embodiment.

The terms "comprises,""including," or other variations thereof are intended to cover non-exclusive inclusion such that a method or method that includes a list of steps does not include only those steps, but may include other steps not expressly listed or pertaining to such a process or method. Likewise, any device or subsystem or element or structure or component preceded by "comprises...a" does not, without further limitation, exclude the existence of other devices or other subsystem or other element or other structure or other component or additional device or additional subsystems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one skilled in the art to which this invention pertains. The system, methods, and examples provided herein are for purposes of illustration only and are not intended to be limiting.

Embodiments of the present invention are described in detail below with reference to the attached figure.

1 shows a block diagram of a heart sound analysis system for the detection of heart diseases (100), the system (100) comprising: a heart sound sensor (102), a pre-processing module (104), a feature extraction module (106), a classification module (108), a display (110) and a phonocar diagram (112).

The heart murmur sensor (102) consists of at least one electrode capable of generating an electrical signal representing at least one heart murmur of a user. The heart disease is either an enlargement of the heart chambers, heart valve disease, or heart muscle problems such as dilated cardiomyopathy or restrictive cardiomyopathy. The heart sound sensor (102) measures either a lub (s1) or a sub (s2) which indicates the closing of the heart valve in the normal state. The cardiac sound sensor (102) measures the abnormal sound either an S3 diastole signal or an S4 systole signal or a combination thereof to detect the abnormal condition. The SI signal is generated when the atrioventricular (tricuspid and mitral) valves close at the beginning of systole, while the S2 signal detects the closing of the aortic and pulmonary (crescent-shaped) valves at the end of systole.

The pre-processing module (104) is connected to the heart sound sensor (102) in order to enhance the generated electrical signal. The pre-processing module (104) uses a filter to remove interference signals from the generated electrical signal and improves the signal quality.

The feature extraction module (106) is coupled to the pre-processing module (104) to extract a plurality of features from an enhanced signal, wherein signal processing circuitry is included in the extraction module (106) to analyze the extracted features to detect cardiac disease .

The classification module (108) is connected to the feature extraction module (106) to classify the plurality of features into a plurality of classes, a first class detecting a heart disease state upon detection of an abnormal murmur along with a normal murmur, a second class detects a normal condition upon detection of the normal murmur, and a third condition detects ventricular failure. The first class corresponds to the S3 signal for the presence of heart disease, and S4 detects left ventricular failure in the heart.

The display (110) is coupled to the classification module (108) to display the classified signal based on the recognized plurality of classes.

The deep learning neural network is included in the classification module (108) to classify the plurality of extracted features.

The phonocar chart (112) is connected to the heart murmur sensor (102) to record the heart murmur produced. Phonocardiography enables the detection of inaudible murmurs and heart murmurs and permanently records these events. The phonocardiogram (or PCG) is a recording of the sounds and murmurs produced by the heart using a device called a phonocardiograph, so phonocardiography is the recording of all the sounds produced by the heart during a cardiac cycle.

The figure and the preceding description give examples of embodiments. Those skilled in the art will understand that one or more of the elements described may well be combined into a single functional element. Alternatively, certain elements can be broken down into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, the order of the processes described herein may be changed and is not limited to the manner described herein. Furthermore the actions of a flowchart need not be performed in the order shown; Also, not all actions have to be carried out. Also, those actions that are not dependent on other actions can be performed in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples. Numerous variations are possible, regardless of whether they are explicitly mentioned in the description or not, e.g. B. Differences in structure, dimensions and use of materials. The scope of the embodiments is at least as broad as indicated in the following claims.

Advantages, other benefits, and solutions to problems have been described above with respect to particular embodiments. However, the benefits, advantages, problem solutions, and components that can cause an advantage, benefit, or solution to occur or become more pronounced are not to be construed as a critical, required, or essential feature or component of any or all claims.

reference list

100

A heart sound analysis system to detect heart disease.

102

Heart Sound Sensor.

104

preprocessing module

106

Feature extraction module

108

classification module

110

advertisement

112

phonocardiogram

QUOTES INCLUDED IN DESCRIPTION

This list of documents cited by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Patent Literature Cited

• CN100418480C [0005]
• US 7922669 B2 [0005]

Claims (9)

A cardiac analysis system for detecting cardiac disease (100), the system (100) comprising: a heart murmur sensor (102) comprising at least one electrode capable of generating an electrical signal representative of at least one heart murmur of a user; a pre-processing module (104) connected to the cardiac sound sensor (102) for enhancing the generated electrical signal; a feature extraction module (106) coupled to the pre-processing module (104) to extract a plurality of features from an enhanced signal, wherein signal processing circuitry is configured in the extraction module (106) to analyze the extracted features to detect cardiac disease ; and a classification module (108) connected to the feature extraction module (106) to classify the plurality of features into a plurality of classes, a first class detecting a heart disease state upon detection of an abnormal murmur along with a normal murmur, wherein a second class detects a normal condition upon detection of the normal murmur, and a third condition detects failure of a ventricle. system after claim 1 , wherein the pre-processing module (104) removes the noise signal from the generated electrical signal using a filter and improves the quality of the signal. system after claim 1 , where the heart condition is either enlarged heart chambers, heart valve disease, or heart muscle problems such as dilated cardiomyopathy or restrictive cardiomyopathy. system after claim 1 , wherein the heart murmur sensor (102) measures either a lub (s1) or a sub (s2) representing the closure of the heart valve in the normal state. system after claim 1 wherein the murmur sensor (102) measures the abnormal murmur as either an S3 diastole signal or an S4 systole signal or a combination thereof to detect the abnormal condition. system after claim 5 , wherein the S3 signal detects the presence of cardiac disease and S4 detects left ventricular failure. system after claim 1 , wherein a display (110) is connected to the classification module (108) to display the classified signal based on the recognized plurality of classes. system after claim 1 , wherein the classification module (108) includes a deep learning neural network for classifying the plurality of extracted features. system after claim 1 wherein a phonocar chart (112) is connected to the cardiac sound sensor (102) to record the cardiac sound produced.

Images