CN117694916A - Heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence - Google Patents
Heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence Download PDFInfo
- Publication number
- CN117694916A CN117694916A CN202311759483.9A CN202311759483A CN117694916A CN 117694916 A CN117694916 A CN 117694916A CN 202311759483 A CN202311759483 A CN 202311759483A CN 117694916 A CN117694916 A CN 117694916A
- Authority
- CN
- China
- Prior art keywords
- heart sound
- verification
- waveforms
- waveform
- peak
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 208000003017 Aortic Valve Stenosis Diseases 0.000 title claims abstract description 16
- 206010002906 aortic stenosis Diseases 0.000 title claims abstract description 16
- 238000002555 auscultation Methods 0.000 title claims abstract description 16
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 12
- 238000012795 verification Methods 0.000 claims abstract description 105
- 238000003745 diagnosis Methods 0.000 claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims abstract description 13
- 238000010586 diagram Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 11
- 238000001228 spectrum Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000005236 sound signal Effects 0.000 claims description 6
- 238000004148 unit process Methods 0.000 claims description 3
- 206010044565 Tremor Diseases 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 210000003205 muscle Anatomy 0.000 abstract description 3
- 230000026676 system process Effects 0.000 abstract 1
- 208000035211 Heart Murmurs Diseases 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 208000019622 heart disease Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/02—Stethoscopes
- A61B7/04—Electric stethoscopes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/006—Detecting skeletal, cartilage or muscle noise
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Acoustics & Sound (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Biomedical Technology (AREA)
- Rheumatology (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence, which belongs to the technical field of intelligent medical treatment, wherein the heart sound auscultation system processes heart sound information between a first heart sound and a second heart sound in an obtained heart sound waveform chart, and obtains interference waveforms in the heart sound information through comparing continuous multiple groups of verification waveforms, so that abnormal verification waveform data are identified, influence of factors such as muscle trembling, friction between clothes and skin, environmental noise and the like on subsequent results is reduced, and accuracy of subsequent diagnosis is improved; the invention also distributes the heart sound images to proper doctors for further diagnosis according to the complexity degree of the corresponding heart sound images, thereby fully utilizing medical resources while ensuring the overall diagnosis accuracy and efficiency.
Description
Technical Field
The invention belongs to the technical field of intelligent medical treatment, and particularly relates to a heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence.
Background
The phonocardiogram is a graph recorded by converting vibrations of heart sounds into time-series vibration waves. The phonocardiogram instrument records heart sounds and heart murmurs for clinical analysis, and is helpful for diagnosis of etiology of heart diseases and understanding of generation mechanism of heart murmurs. Each cardiac cycle produces 4 heart sounds, but only the first heart sound and the second heart sound are typically heard using a stethoscope;
the invention provides a method for analyzing heart sound auscultation data of aortic valve stenosis, which can timely screen abnormal noise in heart sound auscultation data of the aortic valve stenosis to improve diagnosis efficiency and diagnosis accuracy.
Disclosure of Invention
The invention aims to provide a heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence, which solves the problem that the heart sound auscultation accuracy and efficiency of aortic valve stenosis in the prior art are limited.
The aim of the invention can be achieved by the following technical scheme:
heart sound auscultation system based on artificial intelligence judges aortic valve stenosis includes:
the heart sound sensor is used for collecting heart sound information, converting the heart sound information into an electric signal and transmitting the electric signal to the data processing unit;
the data processing unit is used for analyzing and processing the heart sound information, judging whether the corresponding heart sound information needs further diagnosis or not, and transmitting the heart sound information needing further diagnosis to the corresponding doctor;
the method for judging whether the corresponding heart sound information needs further diagnosis by the data processing unit comprises the following steps:
firstly, acquiring a heart sound signal of a detection object through a heart sound sensor, converting the heart sound signal into an electric signal, and transmitting the electric signal to a data processing unit;
the data processing unit processes the electric signals transmitted by the heart sound sensor to obtain a heart sound chart;
taking absolute values of ordinate parameters of the heart sound waveform diagram to obtain the heart sound waveform diagram;
identifying a first heart sound S1 and a second heart sound S2 in the heart sound waveform diagram;
marking waveforms between adjacent first heart sound S1 and second heart sound S2 in the heart sound waveform diagram as verification waveforms; marking the interference waveform in the verification waveform;
the interference waveform is a verification waveform which is influenced by other factors to be more than a preset degree in the heart sound information acquisition process;
when the number of verification waveforms determined as the interference waveforms is larger than a preset value e, the corresponding phonocardiogram is considered to have large error and needs to be collected again, and meanwhile, a prompt message is sent out through an alarm unit to remind a worker and/or a detection object to collect the phonocardiogram again;
otherwise, when the number of verification waveforms determined as the interference waveforms is smaller than or equal to a preset value e, the corresponding phonocardiogram error range is considered to be reasonable, and after the corresponding interference waveforms are deleted, the next step is carried out;
third, for k verification waveforms remaining after the disturbance waveform is deleted;
calculating verification coefficients W of all verification waveforms according to W=λ1×b+λ2×hmax, and transmitting the verification coefficients W to corresponding doctors for further diagnosis when the duty ratio of the verification waveforms with the verification coefficients W being larger than or equal to a preset value W1 in k verification waveforms reaches more than mu;
otherwise, the corresponding heart sound waveform diagram is considered to be a normal heart sound waveform diagram; mu is a preset value;
λ1 and λ2 are preset values, b is the number of peaks in the corresponding verification waveform, h is the average peak height in the corresponding verification waveform, and hmax is the maximum peak height in the corresponding verification waveform;
where k=n-e 1, e1 is the number of corresponding interference waveforms.
As a further scheme of the invention, the duration of the coverage of the heart sound oscillogram is 8-12s.
As a further aspect of the invention, the method of marking the interference waveform in the verification waveform is as follows:
marking the peak with the peak value smaller than the preset value a1 in the verification waveform as a hidden peak;
after deleting the hidden peaks, obtaining the peak number and peak height data in each verification waveform;
acquiring the peak number bi in the peak interval Rj and the peak height average value hi of each corresponding peak in each verification waveform;
wherein the peak value interval is m number intervals which are equally divided within the range of 0-alpha, and alpha is a preset value; j is more than or equal to 1 and less than or equal to m, i is more than or equal to 1 and less than or equal to n;
according to the formulaCalculating to obtain a peak number discrete value F1j in a peak value interval Rj in n verification waveforms;
then according to the formulaCalculating to obtain peak height discrete values F2j in the peak value interval Rj in the n verification waveforms;
wherein bip is the average value of peak numbers bi corresponding to n verification waveforms in the corresponding peak interval Rj;
hip is the average value of peak height average values hi corresponding to n verification waveforms in the corresponding peak value interval Rj;
when F1j > F1 is established, sequentially deleting the corresponding bi values according to the sequence of |bi-bip| from large to small until F1j is less than or equal to F1, and marking the verification waveform corresponding to the deleted bi values as an abnormal waveform;
when F2j > F2 is established, deleting corresponding hi values in sequence from large to small according to the value of i hi-hip until F2j is less than or equal to F2, and marking the verification waveform corresponding to the deleted hi values as an abnormal waveform; wherein F1 and F2 are preset values.
And acquiring the number d of times that each verification waveform is marked as an abnormal waveform, and when d > d1 is satisfied, considering the corresponding verification waveform as an interference waveform, wherein d1 is a preset value.
As a further aspect of the invention, the μ takes a value of 60%.
As a further aspect of the present invention, the method for transmitting heart sound information to be further diagnosed to a corresponding doctor includes:
acquiring spectrograms of heart sounds of k verification waveforms which remain after the interference waveforms are deleted and correspond to time periods;
randomly selecting k1 groups of verification waveforms, wherein each group of verification waveforms comprises two verification waveforms; and any two groups of verification waveforms are different or not identical;
obtaining the similarity x between the frequency spectrums corresponding to each group of verification waveforms;
obtaining and calculating an average value xp of k1 similarity x;
dividing a diagnostician into a plurality of diagnosis levels;
setting a minimum diagnosis similarity xz for each diagnosis level;
marking doctors with the corresponding lowest diagnosis similarity xz smaller than xp as to-be-selected doctors;
and transmitting the corresponding phonocardiogram to at least one of the doctors to be selected.
The invention has the beneficial effects that:
1. according to the invention, the heart sound information between the first heart sound S1 and the second heart sound S2 in the obtained heart sound waveform diagram is processed, and the continuous multiple groups of verification waveforms are compared to obtain the interference waveforms, so that the identification of abnormal verification waveform data is realized, the influence of factors such as muscle trembling, friction between clothes and skin, environmental noise and the like on the subsequent results is reduced, and the accuracy of the subsequent diagnosis is improved;
2. according to the invention, the frequency spectrum is introduced to analyze the noise between the adjacent first heart sound and second heart sound, the complexity degree of the corresponding heart sound image is analyzed according to the comparison between the frequency spectrums corresponding to a plurality of verification waveforms in the acquired sample, and the corresponding heart sound image is distributed to a proper doctor for further diagnosis according to the complexity degree of the corresponding heart sound image, so that the medical resource is fully utilized while the overall diagnosis accuracy and efficiency are ensured.
Detailed Description
The following description of the technical solutions in the embodiments of the present invention will be clear and complete, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Heart sound auscultation system based on artificial intelligence judges aortic valve stenosis includes:
the heart sound sensor is used for collecting heart sound information, converting the heart sound information into an electric signal and transmitting the electric signal to the data processing unit;
the data processing unit is used for analyzing and processing the heart sound information, judging whether the corresponding heart sound information needs further diagnosis or not, and transmitting the heart sound information needing further diagnosis to the corresponding doctor;
the method for judging whether the corresponding heart sound information needs further diagnosis by the data processing unit comprises the following steps:
firstly, acquiring a heart sound signal of a detection object through a heart sound sensor, converting the heart sound signal into an electric signal, and transmitting the electric signal to a data processing unit;
the data processing unit processes the electric signals transmitted by the heart sound sensor to obtain a heart sound chart;
taking absolute values of ordinate parameters of the heart sound waveform diagram to obtain the heart sound waveform diagram;
identifying a first heart sound S1 and a second heart sound S2 in the heart sound waveform diagram;
in one embodiment of the invention, the duration of the coverage of the heart sound waveform pattern is preferably 8-12s;
marking waveforms between adjacent first heart sound S1 and second heart sound S2 in the heart sound waveform diagram as verification waveforms;
marking the peak with the peak value smaller than the preset value a1 in the verification waveform as a hidden peak;
after deleting hidden peaks in the verification waveforms, obtaining the peak number and peak height data in each verification waveform;
acquiring the peak number bi in the peak interval Rj and the peak height average value hi of each corresponding peak in each verification waveform;
wherein the peak value interval is m number intervals which are equally divided within the range of 0-alpha, and alpha is a preset value; j is more than or equal to 1 and less than or equal to m, i is more than or equal to 1 and less than or equal to n;
according to the formulaCalculating to obtain a peak number discrete value F1j in a peak value interval Rj in n verification waveforms;
then according to the formulaCalculating to obtain peak height discrete values F2j in the peak value interval Rj in the n verification waveforms;
wherein bip is the average value of peak numbers bi corresponding to n verification waveforms in the corresponding peak interval Rj;
hip is the average value of peak height average values hi corresponding to n verification waveforms in the corresponding peak value interval Rj;
when F1j > F1 is established, sequentially deleting the corresponding bi values according to the sequence of |bi-bip| from large to small until F1j is less than or equal to F1, and marking the verification waveform corresponding to the deleted bi values as an abnormal waveform;
when F2j > F2 is established, deleting corresponding hi values in sequence from large to small according to the value of i hi-hip until F2j is less than or equal to F2, and marking the verification waveform corresponding to the deleted hi values as an abnormal waveform;
wherein F1 and F2 are preset values;
thirdly, acquiring the times d of marking each verification waveform as an abnormal waveform, and considering the corresponding verification waveform as an interference waveform when d > d1 is satisfied;
wherein d1 is a preset value;
the interference waveform is a verification waveform which is greatly influenced by other factors such as muscle tremors, friction between clothes and skin, environmental noise and the like in the heart sound information acquisition process, so that the waveform cannot effectively reflect the noise generated by aortic valve stenosis in the area between the first heart sound and the second heart sound, and the subsequent judgment can be greatly influenced;
when the number of verification waveforms determined as the interference waveforms is larger than a preset value e, the corresponding phonocardiogram errors are considered to be larger, the phonocardiogram errors need to be collected again, and meanwhile, prompt information is sent out through an alarm unit to remind workers and/or detection objects to collect the phonocardiogram information again;
otherwise, when the number of verification waveforms determined as the interference waveforms is smaller than or equal to a preset value e, the corresponding phonocardiogram error range is considered to be reasonable, and after the corresponding interference waveforms are deleted, the next step is carried out;
according to the invention, the heart sound information between the first heart sound S1 and the second heart sound S2 in the obtained heart sound waveform diagram is processed, and the continuous multiple groups of verification waveforms are compared to obtain the interference waveforms, so that the identification of abnormal verification waveform data is realized, the influence of factors such as muscle trembling, friction between clothes and skin, environmental noise and the like on the subsequent results is reduced, and the accuracy of the subsequent diagnosis is improved;
fourth, for k verification waveforms remaining after the disturbance waveform is deleted;
calculating verification coefficients W of all verification waveforms according to W=λ1×b+λ2×hmax, and entering the next step when the duty ratio of the verification waveform with the verification coefficient W being larger than or equal to a preset value W1 in k verification waveforms reaches more than mu;
otherwise, the corresponding heart sound waveform diagram is considered to be a normal heart sound waveform diagram;
wherein μ is a preset value, in one embodiment of the invention, the μ is 60%;
λ1 and λ2 are preset values, b is the number of peaks in the corresponding verification waveform, h is the average peak height in the corresponding verification waveform, and hmax is the maximum peak height in the corresponding verification waveform;
where k=n-e 1, e1 is the number of corresponding interference waveforms;
fifthly, acquiring spectrograms of heart sounds of k verification waveforms which remain after the interference waveforms are deleted and correspond to time periods;
randomly selecting k1 groups of verification waveforms, wherein each group of verification waveforms comprises two verification waveforms; and any two groups of verification waveforms are different or not identical;
obtaining the similarity x between the frequency spectrums corresponding to each group of verification waveforms;
obtaining and calculating an average value xp of k1 similarity x;
dividing a diagnostician into a plurality of diagnosis grades, wherein the diagnosis grades can be divided by considering factors such as the job title, the service life and the like of the diagnostician;
setting a minimum diagnosis similarity xz for each diagnosis level;
marking doctors with the corresponding lowest diagnosis similarity xz smaller than xp as to-be-selected doctors;
and transmitting the corresponding phonocardiogram to at least one of the doctors to be selected.
According to the invention, noise between adjacent first heart sounds and second heart sounds is analyzed by introducing frequency spectrums, the complexity degree of a corresponding heart sound image is analyzed according to comparison among frequency spectrums corresponding to a plurality of verification waveforms in an acquired sample, and the complexity degree of the corresponding heart sound image is distributed to a proper doctor for further diagnosis;
the invention can realize the analysis and screening of the heart sound data, ensure the accuracy of the obtained heart sound data, and carry out subsequent diagnosis and distribution according to the actual condition of the obtained heart sound data, thereby greatly improving the diagnosis efficiency.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely illustrative and explanatory of the invention, as various modifications and additions may be made to the particular embodiments described, or in a similar manner, by those skilled in the art, without departing from the scope of the invention or exceeding the scope of the invention as defined in the claims.
Claims (5)
1. Heart sound auscultation system based on artificial intelligence judges aortic valve stenosis, its characterized in that includes:
the heart sound sensor is used for collecting heart sound information, converting the heart sound information into an electric signal and transmitting the electric signal to the data processing unit;
the data processing unit is used for analyzing and processing the heart sound information, judging whether the corresponding heart sound information needs further diagnosis or not, and transmitting the heart sound information needing further diagnosis to the corresponding doctor;
the method for judging whether the corresponding heart sound information needs further diagnosis by the data processing unit comprises the following steps:
firstly, acquiring a heart sound signal of a detection object through a heart sound sensor, converting the heart sound signal into an electric signal, and transmitting the electric signal to a data processing unit;
the data processing unit processes the electric signals transmitted by the heart sound sensor to obtain a heart sound chart;
taking absolute values of ordinate parameters of the heart sound waveform diagram to obtain the heart sound waveform diagram;
identifying a first heart sound S1 and a second heart sound S2 in the heart sound waveform diagram;
marking waveforms between adjacent first heart sound S1 and second heart sound S2 in the heart sound waveform diagram as verification waveforms; marking the interference waveform in the verification waveform;
the interference waveform is a verification waveform which is influenced by other factors to be more than a preset degree in the heart sound information acquisition process;
when the number of verification waveforms determined as the interference waveforms is larger than a preset value e, the corresponding phonocardiogram is considered to have large error and needs to be collected again, and meanwhile, a prompt message is sent out through an alarm unit to remind a worker and/or a detection object to collect the phonocardiogram again;
otherwise, when the number of verification waveforms determined as the interference waveforms is smaller than or equal to a preset value e, the corresponding phonocardiogram error range is considered to be reasonable, and after the corresponding interference waveforms are deleted, the next step is carried out;
third, for k verification waveforms remaining after the disturbance waveform is deleted;
calculating verification coefficients W of all verification waveforms according to W=λ1×b+λ2×hmax, and transmitting the verification coefficients W to corresponding doctors for further diagnosis when the duty ratio of the verification waveforms with the verification coefficients W being larger than or equal to a preset value W1 in k verification waveforms reaches more than mu;
otherwise, the corresponding heart sound waveform diagram is considered to be a normal heart sound waveform diagram; mu is a preset value;
λ1 and λ2 are preset values, b is the number of peaks in the corresponding verification waveform, h is the average peak height in the corresponding verification waveform, and hmax is the maximum peak height in the corresponding verification waveform;
where k=n-e 1, e1 is the number of corresponding interference waveforms.
2. The heart sound auscultation system for aortic valve stenosis determination based on artificial intelligence of claim 1, wherein the heart sound waveform pattern covers a period of 8-12s.
3. The heart sound auscultation system for aortic valve stenosis determination based on artificial intelligence of claim 1, wherein the method of marking the interference waveform in the verification waveform is:
marking the peak with the peak value smaller than the preset value a1 in the verification waveform as a hidden peak;
after deleting the hidden peaks, obtaining the peak number and peak height data in each verification waveform;
acquiring the peak number bi in the peak interval Rj and the peak height average value hi of each corresponding peak in each verification waveform;
wherein the peak value interval is m number intervals which are equally divided within the range of 0-alpha, and alpha is a preset value; j is more than or equal to 1 and less than or equal to m, i is more than or equal to 1 and less than or equal to n;
according to the formulaCalculating to obtain a peak number discrete value F1j in a peak value interval Rj in n verification waveforms;
then according to the formulaCalculating to obtain peak height discrete values F2j in the peak value interval Rj in the n verification waveforms;
wherein bip is the average value of peak numbers bi corresponding to n verification waveforms in the corresponding peak interval Rj;
hip is the average value of peak height average values hi corresponding to n verification waveforms in the corresponding peak value interval Rj;
when F1j > F1 is established, sequentially deleting the corresponding bi values according to the sequence of |bi-bip| from large to small until F1j is less than or equal to F1, and marking the verification waveform corresponding to the deleted bi values as an abnormal waveform;
when F2j > F2 is established, deleting corresponding hi values in sequence from large to small according to the value of i hi-hip until F2j is less than or equal to F2, and marking the verification waveform corresponding to the deleted hi values as an abnormal waveform; wherein F1 and F2 are preset values.
And acquiring the number d of times that each verification waveform is marked as an abnormal waveform, and when d > d1 is satisfied, considering the corresponding verification waveform as an interference waveform, wherein d1 is a preset value.
4. The artificial intelligence based heart sound auscultation system for aortic valve stenosis determination as in claim 1, wherein μ is 60%.
5. The heart sound auscultation system for aortic valve stenosis determination based on artificial intelligence according to claim 1, wherein the method of transmitting heart sound information required for further diagnosis to the corresponding doctor is:
acquiring spectrograms of heart sounds of k verification waveforms which remain after the interference waveforms are deleted and correspond to time periods;
randomly selecting k1 groups of verification waveforms, wherein each group of verification waveforms comprises two verification waveforms; and any two groups of verification waveforms are different or not identical;
obtaining the similarity x between the frequency spectrums corresponding to each group of verification waveforms;
obtaining and calculating an average value xp of k1 similarity x;
dividing a diagnostician into a plurality of diagnosis levels;
setting a minimum diagnosis similarity xz for each diagnosis level;
marking doctors with the corresponding lowest diagnosis similarity xz smaller than xp as to-be-selected doctors;
and transmitting the corresponding phonocardiogram to at least one of the doctors to be selected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311759483.9A CN117694916B (en) | 2023-12-20 | 2023-12-20 | Heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311759483.9A CN117694916B (en) | 2023-12-20 | 2023-12-20 | Heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117694916A true CN117694916A (en) | 2024-03-15 |
CN117694916B CN117694916B (en) | 2024-06-25 |
Family
ID=90155018
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311759483.9A Active CN117694916B (en) | 2023-12-20 | 2023-12-20 | Heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117694916B (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080262368A1 (en) * | 2007-04-17 | 2008-10-23 | Cardiac Pacemakers, Inc. | Heart sound tracking system and method |
US20090192401A1 (en) * | 2008-01-25 | 2009-07-30 | Sourabh Ravindran | Method and system for heart sound identification |
JP2012239748A (en) * | 2011-05-23 | 2012-12-10 | Toyota Central R&D Labs Inc | Elastic wave detector, personal authentication device, voice output device, elastic wave detection program, and personal authentication program |
CN106037792A (en) * | 2016-07-20 | 2016-10-26 | 上海康情信息科技有限公司 | Method for cardiac sound waveform data processing and graph displaying and auscultation system |
US20180214038A1 (en) * | 2017-02-02 | 2018-08-02 | International Business Machines Corporation | Determining blood pulse characteristics based on stethoscope data |
CN110831494A (en) * | 2017-06-30 | 2020-02-21 | 考拉生命公司 | Analysis of phonocardiogram data and electrocardiogram data from a portable sensor device |
CN112472120A (en) * | 2020-12-18 | 2021-03-12 | 科大讯飞股份有限公司 | Heart rate statistical method and device, electronic equipment and storage medium |
WO2022191105A1 (en) * | 2021-03-12 | 2022-09-15 | 国立大学法人大阪大学 | Cardiac-valve abnormality detection device, detection method, and computer program |
CN116019480A (en) * | 2022-12-16 | 2023-04-28 | 赣南医学院第一附属医院 | Tricuspid valve stenosis identification method and device integrating heart sound electrocardiosignal time sequence characteristics |
-
2023
- 2023-12-20 CN CN202311759483.9A patent/CN117694916B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080262368A1 (en) * | 2007-04-17 | 2008-10-23 | Cardiac Pacemakers, Inc. | Heart sound tracking system and method |
US20090192401A1 (en) * | 2008-01-25 | 2009-07-30 | Sourabh Ravindran | Method and system for heart sound identification |
JP2012239748A (en) * | 2011-05-23 | 2012-12-10 | Toyota Central R&D Labs Inc | Elastic wave detector, personal authentication device, voice output device, elastic wave detection program, and personal authentication program |
CN106037792A (en) * | 2016-07-20 | 2016-10-26 | 上海康情信息科技有限公司 | Method for cardiac sound waveform data processing and graph displaying and auscultation system |
US20180214038A1 (en) * | 2017-02-02 | 2018-08-02 | International Business Machines Corporation | Determining blood pulse characteristics based on stethoscope data |
CN110831494A (en) * | 2017-06-30 | 2020-02-21 | 考拉生命公司 | Analysis of phonocardiogram data and electrocardiogram data from a portable sensor device |
CN112472120A (en) * | 2020-12-18 | 2021-03-12 | 科大讯飞股份有限公司 | Heart rate statistical method and device, electronic equipment and storage medium |
WO2022191105A1 (en) * | 2021-03-12 | 2022-09-15 | 国立大学法人大阪大学 | Cardiac-valve abnormality detection device, detection method, and computer program |
CN116019480A (en) * | 2022-12-16 | 2023-04-28 | 赣南医学院第一附属医院 | Tricuspid valve stenosis identification method and device integrating heart sound electrocardiosignal time sequence characteristics |
Non-Patent Citations (1)
Title |
---|
王海滨;胡玉良;江钟伟;: "基于智能听诊器的心音信号采集与处理", 西华大学学报(自然科学版), no. 02, 15 March 2009 (2009-03-15) * |
Also Published As
Publication number | Publication date |
---|---|
CN117694916B (en) | 2024-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Patro et al. | Effective feature extraction of ECG for biometric application | |
CN109117730B (en) | Real-time electrocardiogram atrial fibrillation judgment method, device and system and storage medium | |
CN1301080C (en) | Reduced lead set for detecting acute cardiac ischemic conditions | |
CN103110417B (en) | Automatic electrocardiogram recognition system | |
US6024705A (en) | Automated seismic detection of myocardial ischemia and related measurement of cardiac output parameters | |
CN109758145B (en) | Automatic sleep staging method based on electroencephalogram causal relationship | |
EP3672474A1 (en) | A method of detecting abnormalities in ecg signals | |
CN113397555A (en) | Arrhythmia classification algorithm of C-LSTM for physiological parameter monitoring | |
CN112971839B (en) | Heart sound classification method based on feedforward convolution neural network | |
Fang et al. | Dual-channel neural network for atrial fibrillation detection from a single lead ECG wave | |
CN108294745A (en) | P waves, T wave start-stop point detecting methods and system in multi-lead ECG signal | |
Portet et al. | Evaluation of real-time QRS detection algorithms in variable contexts | |
CN116602642B (en) | Heart rate monitoring method, device and equipment | |
Ranjan et al. | A unified approach of ECG signal analysis | |
CN111557659A (en) | Arrhythmia classification method based on multi-feature fusion and Stacking-DWKNN | |
CN111067513B (en) | Sleep quality detection key brain area judgment method based on characteristic weight self-learning | |
CN117349598A (en) | Electroencephalogram signal processing method and device, equipment and storage medium | |
CN111568410A (en) | Electrocardiogram data classification method based on 12-lead and convolutional neural network | |
CN117694916B (en) | Heart sound auscultation system for judging aortic valve stenosis based on artificial intelligence | |
CN107753012A (en) | A kind of mcg-signalses method for evaluating quality, system and server | |
CN117582235A (en) | Electrocardiosignal classification method based on CNN-LSTM model | |
Shi et al. | Automated heartbeat classification based on convolutional neural network with multiple kernel sizes | |
Safara | Cumulant-based trapezoidal basis selection for heart sound classification | |
Hori et al. | Arrhythmia detection based on patient-specific normal ECGs using deep learning | |
CN108836312B (en) | Clutter rejection method and system based on artificial intelligence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |