WO2016206704A1 - The smart stethoscope - Google Patents
The smart stethoscope Download PDFInfo
- Publication number
- WO2016206704A1 WO2016206704A1 PCT/EG2016/000018 EG2016000018W WO2016206704A1 WO 2016206704 A1 WO2016206704 A1 WO 2016206704A1 EG 2016000018 W EG2016000018 W EG 2016000018W WO 2016206704 A1 WO2016206704 A1 WO 2016206704A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- sounds
- stethoscope
- smart
- sound
- smart stethoscope
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
Definitions
- the stethoscope is a medical instrument used by physicians to hear sounds produced by the body. It enables auscultation of heart, lung, intestinal sounds and blood pressure detection in association with sphygmomanometer. It is used in any clinical examination, and all physicians and students are trained to use it. It was invented in 1816 by the French Doctor Rene Theophile Hyacinthe Laennec (1781-1826] at the Necker-Enfants Malades Hospital in Paris. [1]
- stethoscopes There are a variety of stethoscopes in shape and function that are freely available. Some stethoscopes can intensify the sounds.
- Electronic stethoscopes require conversion of acoustic sound waves to electrical signals, which can then be amplified and processed for optimal listening. Unlike acoustic stethoscopes, which are all based on the same physics. Transducers in electronic stethoscopes vary widely. [2,3]
- Electronic stethoscopes are not limited to placing a microphone in the chest- piece, Welch-Allyn's Meditron stethoscope, places a piezoelectric crystal at the head of a metal shaft that makes contact with a diaphragm, 3M also places a piezo-electric crystal within foam behind a diaphragm that responds to sound waves, with changes in an electric field.
- Enabled wireless transmission of heart sounds to a smart phone or tablet is a possibility, with blue tooth features and other features available as on-line applications.
- Electronic stethoscopes are also used with Computer Aided Auscultation (CAA) programs to analyze the recorded heart sounds pathological or innocent heart murmurs.
- the CCA can show recorded heart sounds and ECG signals as plotted phonocardiogram (PCG) on screens of monitors or mobile phone using downloaded applications, or tablets or laptops, etc.
- CCA allows also storing of recorded sounds for research purposes.
- the stethoscope suspected heart, chest or other system abnormality is then confirmed by further diagnostic modalities that include chest X-ray, computed tomography (CT), echocardiography, electrocardiogram, chest sonography and magnetic resonance imaging (MRI), etc.
- CT computed tomography
- MRI magnetic resonance imaging
- Heart murmur recognition systems include: Artificial Neural Network (ANN) [5] Back Propagation Neural Network (BPNN) using Hidden Markov Model (HMM), and Mel Frequency Cepestral coefficient (MFCC), [6] HMM and MFCC combined with statistical moment Empirical Mode Decomposition (EMD)[7], ANN, BPNN, SVM, ANN with RBF ANFIS [8], Where: SVM: Support Vector Machine, RBF: Radial Basis Function, ANFIS: Adaptive Neuro-Fuzzy Inference System. These systems accuracy compromised the recognition except for the EMD based system.
- ANN Artificial Neural Network
- BPNN Back Propagation Neural Network
- HMM Hidden Markov Model
- MFCC Mel Frequency Cepestral coefficient
- EMD Empirical Mode Decomposition
- SVM Support Vector Machine
- RBF Radial Basis Function
- ANFIS Adaptive Neuro-Fuzzy Inference System.
- the smart stethoscope is a stethoscope for auscultation, recognition of heart murmurs, heart sounds, breath sounds and all other sounds produced by the body and displays the final diagnosis as interpreted from recognized defect or norm that help in diagnosis of heart, chest and other defects.
- the smart stethoscope identifies normal and abnormal heart, chest sounds and other sounds produced body.
- the smart stethoscope comprises at least one diaphragm with at least one microphone that also serves as a sensor, attached to a recording sound system that allows sound analysis, and recognition and classification of sounds and a displaying system that allows observer to read name of defect. Contrary to all electronic stethoscopes that allow observer to read a phonogram/phonocardiogram the smart stethoscope allows recognition and diagnosis of normal and abnormal sounds and displays the frequency and final diagnosis.
- the smart stethoscope comprises a diaphragm with optional earpieces, that is connected to a microphone, and a heart recognition system.
- the heart recognition system could be any known heart recognition system or preferably our novel developed machine-learning model. Where we collected sounds to build a machine-learning model. We allowed feature extraction and sound separation depending upon specific amplitude threshold. We used MFCC computation display, Baum-Welch in HMM to produce new parameter estimates that have equal or greater likelihood of having generated the training data, Viterbi algorithm to determine the best state sequence to maximize the probability of generation of the observation sequence (each feature matrix represent one observation), and forward-backward algorithm to calculate the probability.
- HMM model for each auscultation area related sounds and according iu known auscultation areas that comprised a minimum of 4 areas to increase HMM model accuracy to sense frequencies and designate origin of structural abnormality to overcome limitations of frequencies overlap. Then HMM model showed test result according to classified frequencies as low (lHz-139Hz) and high (156Hz-556Hz). Structurally normal hearts frequencies were encountered in the low range but never in high range, yet the opposite was not correct, as we encountered low and high frequencies were encountered from mild cases of valvular defects. Thus any low frequency was subjected to amplification one fold before designation.
- the smart stethoscope comprises a stethoscope with a diaphragm, bell, tubing, binaural mechanism, ear tubes and ear-pieces, small sized microphone, an electronic board and a digital screen.
- Figure 1 demonstrates the smart stethoscope. It has to be noted that the ear tubes and ear-pieces are optional.
- Examples of the displaying screens include digital screens of laptops, computers, smart phones and any other digital screen.
- the smart stethoscope affords the first Auscultation Diagnoses Coupling not dependent on operator and dependent on machine learning model.
- the microphone (1) is attached to diaphragm of stethoscope (4), which has an optional earpiece (5), the detected sounds are recognized by the electronic board (2), and then displayed on the digital screen (3).
- the smart stethoscope comprises:
- the microphone (1) used is any suitable microphone that is preferably small and allows sound sensing and amplification.
- the smart stethoscope comprises any suitable stethoscope(4) with a diaphragm that can accommodate at least one microphone.
- the diaphragm can be small or big to spread on more than an auscultation area.
- the tubing, binaural, uniaural mechanisms and ear piece of the smart stethoscope are optional parts to be removed or placed according to user needs.
- the electronic board (2) comprises a reception system for incoming sensed validated machine-learning model that recognizes sounds by their specific frequencies and classifies the sounds.
- the electronic board (2) has a storage and sound banking features, and can be trained to recognize novel real or simulated sounds, and validate the recognition of the novel sounds.
- the digital screen (3) displays the recognized sounds by displaying diagnoses of detected and recognized sounds for example "normal chest sounds” or ''Aortic stenosis" or "normal intestinal sounds”.
- the softwear on the electronic board is upgradeable through on line applications.
- the electronic board (2) communicates with digital screen (3) through a wired or wireless communication, where any wireless solution can be applied.
- the electronic board recognizing system of the sounds is preferably our machine-learning model dependent on HMM and MFCC, but any recognition system can be used.
- the smart stethoscope displays frequency and other features as rate or velocity etc is an optional feature according to user requirements.
Abstract
The contemporary stethoscopes are either auscultation or electronic. The stethoscope allows the person using it to hear sounds or see the phonocardiogram of the stethoscope-detected sound. The stethoscope suspected heart and chest abnormality is then confirmed by further diagnostic modalities that include chest X-ray, computed tomography (CT), echocardiography, electrocardiogram, chest sonography and magnetic resonance imaging (MRI). The smart stethoscope is a stethoscope for auscultation, recognition of heart murmurs, heart sounds, breath sounds and displays the interpreted recognized defect and any other sounds produced by the body that help in diagnosis of heart, chest and other system defects or assure well being. The smart stethoscope identifies normal and abnormal heart, chest and other system sounds. Where the purpuse of the smart stethoscope is auscultation and displaying of defect, the smart stethoscope comprises at least one diaphragm with at least one microphone, attached to a recording sound system that allows sound analysis, and recognition and classification of sounds and a displaying system that allows observer to read the diagnosis of defect or norm. Contrary to all electronic stethoscopes that allow observer to read a phonogram/phonocardiogram the smart stethoscope allows recognition and diagnosis of normal and abnormal sounds by displaying the final diagnosis. Smart stethoscope displays frequency and other features as rate or velocity etc is an optional feature according to user requirements. The smart stethoscope validation has a very high correct classification rate (CCR) and almost 98% sensitivity in recognizing sounds, classifying sounds, interpreting and displaying the diagnoses of the sensed sound as normal/abnormal and defining the type of abnormality.
Description
The Smart Stethoscope
1- Technical Field
Medical diagnosis equipment.
Medical diagnostic device for auscultation.
2- Background art
Currently the stethoscope is a medical instrument used by physicians to hear sounds produced by the body. It enables auscultation of heart, lung, intestinal sounds and blood pressure detection in association with sphygmomanometer. It is used in any clinical examination, and all physicians and students are trained to use it. It was invented in 1816 by the French Doctor Rene Theophile Hyacinthe Laennec (1781-1826] at the Necker-Enfants Malades Hospital in Paris. [1]
There are a variety of stethoscopes in shape and function that are freely available. Some stethoscopes can intensify the sounds.
Available electronic stethoscopes amplify sounds electronically. Amplification of stethoscope contact artifacts, and component cutoffs (frequency response thresholds of electronic stethoscope microphones, pre-amps, amps, and speakers) limit electronically amplified stethoscopes' overall utility. Thus ambient noise reduction and amplification is a feature in some electronic stethoscopes.
Electronic stethoscopes require conversion of acoustic sound waves to electrical signals, which can then be amplified and processed for optimal listening. Unlike acoustic stethoscopes, which are all based on the same physics. Transducers in electronic stethoscopes vary widely. [2,3]
Electronic stethoscopes are not limited to placing a microphone in the chest- piece, Welch-Allyn's Meditron stethoscope, places a piezoelectric crystal at the head of a metal shaft that makes contact with a diaphragm, 3M also places a piezo-electric crystal within foam behind a diaphragm that responds to sound waves, with changes in an electric field. Enabled wireless transmission of heart sounds to a smart phone or tablet is a possibility, with blue tooth features and other features available as on-line applications.
Most of these features are helpful for telemedicine and teaching purposes. Electronic stethoscopes are also used with Computer Aided Auscultation (CAA) programs to analyze the recorded heart sounds pathological or innocent heart murmurs. The CCA can show recorded heart sounds and ECG signals as plotted phonocardiogram (PCG) on screens of monitors or mobile phone using downloaded applications, or tablets or laptops, etc. CCA allows also storing of recorded sounds for research purposes.
These electronic applications are not yet established for training purposes albeit might be more popular among trainees aiming at improving personal
professionalism.
Washington Post announced the first smartphone application for stethoscope in 2015 as a "reinvention of healthcare." [4]
The stethoscope suspected heart, chest or other system abnormality is then confirmed by further diagnostic modalities that include chest X-ray, computed tomography (CT), echocardiography, electrocardiogram, chest sonography and magnetic resonance imaging (MRI), etc.
Heart murmur recognition systems include: Artificial Neural Network (ANN) [5] Back Propagation Neural Network (BPNN) using Hidden Markov Model (HMM), and Mel Frequency Cepestral coefficient (MFCC), [6] HMM and MFCC combined with statistical moment Empirical Mode Decomposition (EMD)[7], ANN, BPNN, SVM, ANN with RBF ANFIS [8], Where: SVM: Support Vector Machine, RBF: Radial Basis Function, ANFIS: Adaptive Neuro-Fuzzy Inference System. These systems accuracy compromised the recognition except for the EMD based system.
The review by Leng and co-workers (December 2015) describes the state of art of stethoscopes available technology and all marketed stethoscopes. [9].
3- Detailed Description of Invention:
The smart stethoscope is a stethoscope for auscultation, recognition of heart murmurs, heart sounds, breath sounds and all other sounds produced by the body and displays the final diagnosis as interpreted from recognized defect or norm that help in diagnosis of heart, chest and other defects. The smart stethoscope identifies normal and abnormal heart, chest sounds and other sounds produced body.
Where the purpose of the smart stethoscope is auscultation and displaying of diagnosis of defect, the smart stethoscope comprises at least one diaphragm with at least one microphone that also serves as a sensor, attached to a recording sound system that allows sound analysis, and recognition and classification of sounds and a displaying system that allows observer to read name of defect. Contrary to all electronic stethoscopes that allow observer to read a phonogram/phonocardiogram the smart stethoscope allows recognition and diagnosis of normal and abnormal sounds and displays the frequency and final diagnosis.
The smart stethoscope comprises a diaphragm with optional earpieces, that is connected to a microphone, and a heart recognition system. The heart recognition system could be any known heart recognition system or preferably our novel developed machine-learning model. Where we collected sounds to build a machine-learning model. We allowed feature extraction and sound separation depending upon specific amplitude threshold. We used MFCC computation display, Baum-Welch in HMM to produce new parameter estimates that have equal or greater likelihood of having generated the training data, Viterbi algorithm to determine the best state sequence to maximize the probability of generation of the observation sequence (each feature matrix
represent one observation), and forward-backward algorithm to calculate the probability.
We isolated HMM model for each auscultation area related sounds and according iu known auscultation areas that comprised a minimum of 4 areas to increase HMM model accuracy to sense frequencies and designate origin of structural abnormality to overcome limitations of frequencies overlap. Then HMM model showed test result according to classified frequencies as low (lHz-139Hz) and high (156Hz-556Hz). Structurally normal hearts frequencies were encountered in the low range but never in high range, yet the opposite was not correct, as we encountered low and high frequencies were encountered from mild cases of valvular defects. Thus any low frequency was subjected to amplification one fold before designation.
Our validated Machine learning Model Based on HMM and MFCC displayed a 96% correct classification rate (CCR) and 98% sensitivity.
Accordingly the smart stethoscope comprises a stethoscope with a diaphragm, bell, tubing, binaural mechanism, ear tubes and ear-pieces, small sized microphone, an electronic board and a digital screen. Figure 1 demonstrates the smart stethoscope. It has to be noted that the ear tubes and ear-pieces are optional.
Examples of the displaying screens include digital screens of laptops, computers, smart phones and any other digital screen.
4- What is Novel in Invention
The smart stethoscope affords the first Auscultation Diagnoses Coupling not dependent on operator and dependent on machine learning model.
5- Brief Description of Drawing:
The microphone (1) is attached to diaphragm of stethoscope (4), which has an optional earpiece (5), the detected sounds are recognized by the electronic board (2), and then displayed on the digital screen (3).
Where according to drawing the smart stethoscope comprises:
The microphone (1) used is any suitable microphone that is preferably small and allows sound sensing and amplification.
The smart stethoscope comprises any suitable stethoscope(4) with a diaphragm that can accommodate at least one microphone. The diaphragm can be small or big to spread on more than an auscultation area. The tubing, binaural, uniaural mechanisms and ear piece of the smart stethoscope are optional parts to be removed or placed according to user needs.
The electronic board (2) comprises a reception system for incoming sensed validated machine-learning model that recognizes sounds by their specific frequencies and classifies the sounds. The electronic board (2) has a storage and sound banking features, and can be trained to recognize novel real or simulated sounds, and validate the recognition of the novel sounds.
The digital screen (3) displays the recognized sounds by displaying diagnoses of detected and recognized sounds for example "normal chest sounds" or ''Aortic stenosis" or "normal intestinal sounds". The softwear on the electronic board is upgradeable through on line applications. The electronic board (2) communicates with digital screen (3) through a wired or wireless communication, where any wireless solution can be applied. The electronic board recognizing system of the sounds is preferably our machine-learning model dependent on HMM and MFCC, but any recognition system can be used. The smart stethoscope displays frequency and other features as rate or velocity etc is an optional feature according to user requirements.
Examples are not exclusive.
References:
1- Laennec, Rene (1819). De l'auscultation mediate ou traite du diagnostic des maladies des poumon et du coeur. Paris: Brosson & Chaude.
2- Website selling stethoscopes: http://www.made-in-china.com/products- search/hot-china-products/Stethoscope.html. Accessed on June, 3rd, 2016.
3- Google search for electronic stethoscpes:
https: //www.google.com.eg/search?client=safari&rls=en&q=electronic+s tehthoscopes&ie=UTF-8&oe=UTF-
8&gfe rd=cr&ei=bDdRV6qtEMqA80fA35m4D0#q=electronic+stethoscop es.. Accessed on Accessed on June, 3rd, 2016.
4- Matt McFarland, "Eko's stethoscope shows the potential of digital
technology to reinvent health care", Washington Post.
https://www.washingtonpost.com/news/innovations/wp/2015/09/02/ ekos-stethoscope-shows-the-potential-of-digital-technology-to-reinvent- health-care/ Accessed on Accessed on June, 3rd, 2016.
5- Strunic SL, Rios-Gutierrez F, Flores RA, Nordehn G, Burns S. Detection and Classification of Cardiac Murmurs Using Segmentation Techniques and Artificial Neural Networks. The Proceedings of Computational Intelligence and Data Mining IEEE Symposium on Conference, DOI: 10.1 109/CIDM.2007.368902, pp:397-404, Honolulu, USA, 1 March-5 April 2007.
6- Zhong L, Wan J, Huang Z, Cao G, Xiao B. Heart Murmur Recognition Based on Hidden Markov Model. Journal of Signal and Information Processing,. DOI: 10.4236/jisp.2013.42020, 4:140-144, 2013.
7- Jimenez JA, Becerra MA, Delgado-Trejos E. Heart Murmur Detection Using Ensemble Empirical Mode Decomposition and Derivations of The Mel- Frequency Cepstral Coefficients on 4-Area Phonocardiographic Signals. The Proceedings of The Computing Cardiology Conference, pp:493-496. Cambridge, USA, 7-10 September 2014.
- Devi A, Misal A. A Survey on Classifiers Used in Heart Valve Disease Detection. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 2: 609-614, 2013. - Leng S, Tan RS, Chai KT, Wang C, Ghista D, Zhong L. The electronic stethoscope. Biomed Eng Online. 2015 Jul 10; 14:66. doi: 10. 186/sl2938-015- 0056-y. Review.
Claims
1. A smart stethoscope comprising: a sensor microphone that is attached to diaphragm of stethoscope, which has an optional earpiece, where the detected sounds are recognized at the electronic board, and then the diagnoses is displayed on the digital screen.
2. Wherein according to claim 1 the smart stethoscope comprises any suitable stethoscope with a diaphragm, and the diaphragm can host one or more microphones, according to the spreading size of the diaphragm upon known auscultation areas of human or animal body.
3. Wherein according to claim 1 the smart stethoscope comprises any suitable stethoscope with a diaphragm, that might be connected by tube to binaural spreading mechanism or uniaural and connected to ear piece(s), or that might not be connected by tube to binaural spreading mechanism or uniaural to ear piece(s), where the tube can be removed or placed according to preference of user.
4. Wherein according to claim 1 the smart stethoscope comprises an electronic board that can separate sounds and recognize sounds.
5. Wherein accordmg to claims 1 and 4 the smart stethoscope comprises an electronic board that has storage and sound banking features.
6. Wherein according to claims 1, 4 and 5 the smart stethoscope comprises an electronic board that can be trained to recognize novel real or simulated sounds, and validate the recognition of the novel real or simulated sounds.
7. Wherein according to claims 1 ,4,5 and 6 the smart stethoscope comprises a electronic board that has storage and sound banking features, and optional training features to recognize novel real sounds, and validate the recognition of the novel sounds.
8. Wherein according to claims 1,4,5,6 and 7 the smart stethoscope comprises an electronic board that recognizes the sounds through any recognizing system but preferably the machine-learning model dependent on HMM and MFCC.
9. Where in according to claims 1,4,5,6,7 and 8 the smart stethoscope comprises an electronic board that is upgradeable through on line applications.
10. Where in according to claim 1 the smart stethoscope displays the recognized sounds by displaying diagnoses of detected and recognized sounds on a digital screen for example "normal chest sounds" or "Aortic stenosis" or "normal intestinal sounds".
11. Where in according to claims 1 ,2,3,4,5,6,7,8,9 andl O the smart stethoscope displays the recognized sounds by displaying detected and recognized sounds on a digital screen through communication with electronic board through any suitable wired or wireless communication.
12. Where in according to claims 1 ,2,3,4,5,6,7,8,9 andl O the smart stethoscope displays frequency and other features as rate or velocity etc is an optional feature according to user requirements.
13. Where according to claims from 1 -12 the smart stethoscope is capable of sound separation, sound classification sound banking, sound recognition and display diagnosis for purposes of clinical education and training.
14. Where according to claims from 1 -13 the smart stethoscope is capable of sound separation, sound banking, sound recognition and display diagnosis for purposes of clinical examination, diagnosis, and provides a sensitive screening device that allows prompt referral, confirmation and management of subjects.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EG2015061052 | 2015-06-25 | ||
EG2015061052 | 2015-06-25 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2016206704A1 true WO2016206704A1 (en) | 2016-12-29 |
Family
ID=56194197
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EG2016/000018 WO2016206704A1 (en) | 2015-06-25 | 2016-06-05 | The smart stethoscope |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2016206704A1 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108969005A (en) * | 2018-06-27 | 2018-12-11 | 王尔笑 | A kind of inside of human body audio frequency extraction element |
WO2019202385A1 (en) * | 2018-04-20 | 2019-10-24 | RADHAKRISHNA, Suresh, Jamadagni | Electronic stethoscope |
CN111166371A (en) * | 2018-11-09 | 2020-05-19 | 宏碁股份有限公司 | Diagnostic support method |
US10665223B2 (en) | 2017-09-29 | 2020-05-26 | Udifi, Inc. | Acoustic and other waveform event detection and correction systems and methods |
US10667783B1 (en) | 2019-02-19 | 2020-06-02 | Samson Arigbamu | Stethoscope with sound recognition capacity |
CN111904459A (en) * | 2020-08-27 | 2020-11-10 | 广东汉泓医疗科技有限公司 | Cardiopulmonary sound auscultation detector for guiding rapid auscultation, auscultation system and auscultation method |
US20210378624A1 (en) * | 2020-06-04 | 2021-12-09 | Entac Medical, Inc. | Apparatus and methods for predicting in vivo functional impairments and events |
CN113974680A (en) * | 2021-09-28 | 2022-01-28 | 浙江大学 | Stethoscope with AI recognition function and capable of being placed outside |
CN114863951A (en) * | 2022-07-11 | 2022-08-05 | 中国科学院合肥物质科学研究院 | Rapid dysarthria detection method based on modal decomposition |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5218969A (en) * | 1988-02-04 | 1993-06-15 | Blood Line Technology, Inc. | Intelligent stethoscope |
US20020058889A1 (en) * | 2000-11-16 | 2002-05-16 | Byung Hoon Lee | Automatic diagnostic apparatus with a stethoscope |
US20110087135A1 (en) * | 2009-10-09 | 2011-04-14 | Ferzli George S | Stethoscope, stethoscope attachment and collected data analysis method and system |
-
2016
- 2016-06-05 WO PCT/EG2016/000018 patent/WO2016206704A1/en active Application Filing
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5218969A (en) * | 1988-02-04 | 1993-06-15 | Blood Line Technology, Inc. | Intelligent stethoscope |
US20020058889A1 (en) * | 2000-11-16 | 2002-05-16 | Byung Hoon Lee | Automatic diagnostic apparatus with a stethoscope |
US20110087135A1 (en) * | 2009-10-09 | 2011-04-14 | Ferzli George S | Stethoscope, stethoscope attachment and collected data analysis method and system |
Non-Patent Citations (9)
Title |
---|
DEVI A; MISAL A.: "A Survey on Classifiers Used in Heart Valve Disease Detection. International Journal of Advanced Research in Electrical", ELECTRONICS AND INSTRUMENTATION ENGINEERING, vol. 2, 2013, pages 609 - 614 |
GRZEGORZ REDLARSKI ET AL: "A System for Heart Sounds Classification", PLOS ONE, vol. 9, no. 11, 13 November 2014 (2014-11-13), pages e112673, XP055303458, DOI: 10.1371/journal.pone.0112673 * |
JIMENEZ JA; BECERRA MA; DELGADO-TREJOS E: "Heart Murmur Detection Using Ensemble Empirical Mode Decomposition and Derivations of The Mel-Frequency , Cepstral Coefficients on 4-Area Phonocardiographic Signals", THE PROCEEDINGS OF THE COMPUTING CARDIOLOGY CONFERENCE, 7 September 2014 (2014-09-07), pages 493 - 496, XP032737402 |
LAENNEC, RENE: "De l'auscultation mediate ou traite du diagnostic des maladies des poumon et du coeur." |
LENG S; TAN RS; CHAI KT; WANG C; GHISTA D; ZHONG L: "The electronic stethoscope", BIOMED ENG ONLINE, vol. 14, 10 July 2015 (2015-07-10), pages 66, XP021226045, DOI: doi:10.1186/s12938-015-0056-y |
MATT MCFARLAND: "Eko's stethoscope shows the potential of digital technology to reinvent health care", WASHINGTON POST, Retrieved from the Internet <URL:https://www.washingtonpost.com/news/innovations/wp/2015/09/02/ ekos-stethoscope-shows-the-potential-of-digital-technology-to-reinvent- health-care> |
STRUNIC SL; RIOS-GUTIERREZ F; FLORES RA; NORDEHN G; BURNS S: "Detection and Classification of Cardiac Murmurs Using Segmentation Techniques and Artificial Neural Networks", THE PROCEEDINGS OF COMPUTATIONAL INTELLIGENCE AND DATA MINING IEEE SYMPOSIUM ON CONFERENCE, 1 March 2007 (2007-03-01), pages 397 - 404 |
WEBSITE SELLING STETHOSCOPES, Retrieved from the Internet <URL:http://www.made-in-china.com/products-search/hot-china-products/Stethoscope.html> |
ZHONG L; WAN J; HUANG Z; CAO G; XIAO B: "Heart Murmur Recognition Based on Hidden Markov Model", JOURNAL OF SIGNAL AND INFORMATION PROCESSING, vol. 4, 2013, pages 140 - 144 |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10665223B2 (en) | 2017-09-29 | 2020-05-26 | Udifi, Inc. | Acoustic and other waveform event detection and correction systems and methods |
WO2019202385A1 (en) * | 2018-04-20 | 2019-10-24 | RADHAKRISHNA, Suresh, Jamadagni | Electronic stethoscope |
CN108969005A (en) * | 2018-06-27 | 2018-12-11 | 王尔笑 | A kind of inside of human body audio frequency extraction element |
CN111166371A (en) * | 2018-11-09 | 2020-05-19 | 宏碁股份有限公司 | Diagnostic support method |
US10667783B1 (en) | 2019-02-19 | 2020-06-02 | Samson Arigbamu | Stethoscope with sound recognition capacity |
US20210378624A1 (en) * | 2020-06-04 | 2021-12-09 | Entac Medical, Inc. | Apparatus and methods for predicting in vivo functional impairments and events |
CN111904459A (en) * | 2020-08-27 | 2020-11-10 | 广东汉泓医疗科技有限公司 | Cardiopulmonary sound auscultation detector for guiding rapid auscultation, auscultation system and auscultation method |
CN113974680A (en) * | 2021-09-28 | 2022-01-28 | 浙江大学 | Stethoscope with AI recognition function and capable of being placed outside |
CN114863951A (en) * | 2022-07-11 | 2022-08-05 | 中国科学院合肥物质科学研究院 | Rapid dysarthria detection method based on modal decomposition |
CN114863951B (en) * | 2022-07-11 | 2022-09-23 | 中国科学院合肥物质科学研究院 | Rapid dysarthria detection method based on modal decomposition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2016206704A1 (en) | The smart stethoscope | |
Leng et al. | The electronic stethoscope | |
Swarup et al. | Digital stethoscope: technology update | |
Thiyagaraja et al. | A novel heart-mobile interface for detection and classification of heart sounds | |
US20210345890A1 (en) | An intelligent cardio pulmonary screening device for telemedicine applications | |
US10349893B2 (en) | Smartphone with telemedical device | |
US20210030390A1 (en) | Electronic stethoscope | |
KR101178867B1 (en) | Telemedical stethoscope | |
US9973847B2 (en) | Mobile device-based stethoscope system | |
US20160287207A1 (en) | Smart medical examination and communication apparatus | |
US20180177432A1 (en) | Apparatus and method for detection of breathing abnormalities | |
US11813109B2 (en) | Deriving insights into health through analysis of audio data generated by digital stethoscopes | |
Schmidt et al. | Noise and the detection of coronary artery disease with an electronic stethoscope | |
Malek et al. | Design and development of wireless stethoscope with data logging function | |
Suseno et al. | The signal processing of heart sound from digital stethoscope for identification of heart condition using wavelet transform and neural network | |
US11232866B1 (en) | Vein thromboembolism (VTE) risk assessment system | |
Anumukonda et al. | Heart sound sensing through MEMS microphone | |
CN109346193A (en) | One kind being based on stethoscopic speech recognition equipment and its method | |
WO2020105229A1 (en) | Diagnostic assistance system | |
Monika et al. | Embedded Stethoscope for Real Time Diagnosis of Cardiovascular Diseases | |
Perera | Advancements of Electronic Stethoscope: A Review | |
JP2021502194A (en) | Non-invasive heart valve screening device and method | |
US20220151582A1 (en) | System and method for assessing pulmonary health | |
US11083403B1 (en) | Pulmonary health assessment system | |
WO2019073281A1 (en) | System for recording chest signals and method using said system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 16731505 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16731505 Country of ref document: EP Kind code of ref document: A1 |