CN111820937A - Wireless stethoscope - Google Patents

Wireless stethoscope Download PDF

Info

Publication number
CN111820937A
CN111820937A CN202010626624.XA CN202010626624A CN111820937A CN 111820937 A CN111820937 A CN 111820937A CN 202010626624 A CN202010626624 A CN 202010626624A CN 111820937 A CN111820937 A CN 111820937A
Authority
CN
China
Prior art keywords
mobile terminal
diagnosis
signals
analysis
wireless
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.)
Pending
Application number
CN202010626624.XA
Other languages
Chinese (zh)
Inventor
郭连波
黄伟华
张登
寇卫萍
胡桢麟
汪威良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
Original Assignee
Huazhong University of Science and Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology filed Critical Huazhong University of Science and Technology
Priority to CN202010626624.XA priority Critical patent/CN111820937A/en
Publication of CN111820937A publication Critical patent/CN111820937A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B7/00Instruments for auscultation
    • A61B7/02Stethoscopes
    • A61B7/04Electric stethoscopes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/084Backpropagation, e.g. using gradient descent
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/27Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
    • G10L25/30Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/66Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04RLOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00Details of transducers, loudspeakers or microphones
    • H04R1/46Special adaptations for use as contact microphones, e.g. on musical instrument, on stethoscope

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Acoustics & Sound (AREA)
  • Data Mining & Analysis (AREA)
  • Epidemiology (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Primary Health Care (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Veterinary Medicine (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention provides a wireless stethoscope, which relates to the field of medical appliances and comprises: a chest piece and a mobile terminal; the chest piece is respectively placed at each part of the body of a user to collect the sound signals of each part and send the collected sound signals to the mobile terminal in a wireless transmission mode; the mobile terminal is used for diagnosing the sound signals by combining the trained analysis and diagnosis network so as to give auscultation results to the user; and the cloud system is used for carrying out structured and unstructured data analysis according to the sound signals, auscultation results, the past medical history, the genetic medical history, the genomics and related cases of the user, which are uploaded by the mobile terminal, excavating hidden information of the sound signals, and carrying out disease prediction so as to further diagnose the physical health condition of the user. The invention is suitable for multifunctional wireless auscultation and intelligent diagnosis and analysis in hospital medical systems, intelligent monitoring of family health, high infection risk and other occasions, and has wide application prospect.

Description

Wireless stethoscope
Technical Field
The invention belongs to the technical field of medical instruments, and particularly relates to a wireless stethoscope.
Background
At present, medical care personnel usually need to adopt a wired stethoscope to listen to heart, lung, blood vessel and other parts of a patient, and then make a preliminary judgment on the state of an illness. However, the length of the air conduit of the wired stethoscope is limited, so that the doctor and the patient cannot ensure a sufficient safety distance, and a large infection risk exists. And the auscultation effect of the wired stethoscope can be accurately analyzed only by doctors with enough experience, so that the wired stethoscope is suitable for limited groups, is especially in shortage of medical resources, and cannot diagnose patients who cannot be hospitalized in time in household isolation. Therefore, there is a need for a multifunctional wireless intelligent stethoscope capable of intelligent diagnosis, home health monitoring, and data storage and analysis.
Currently, the stethoscope types mainly include two types: acoustic stethoscopes and electronic stethoscopes. The acoustic stethoscope is mainly a traditional air-conduction stethoscope and consists of a sound pickup part (chest piece), a conduction part (rubber tube) and an auditory part (ear piece). The auscultation distance is limited by the length of the catheter, the noise is large, and only one person can use the stethoscope at one time. Furthermore, the electronic stethoscope combines the signal processing technology and the wireless communication technology, and compared with an acoustic stethoscope, the electronic stethoscope has the advantages of stronger auscultation signal, low noise, wider frequency range, no distance limitation and better auscultation effect. Although the wireless stethoscope has a certain progress in the aspects of auscultation signal quality, preliminary diagnosis and the like, the wireless stethoscope still has the defects that multifunctional intelligent diagnosis, home health monitoring, complex operation, high cost and the like cannot be realized in actual auscultation. For example, Erturul et al uses an auscultation head in combination with a mobile phone and a wireless stethoscope for intelligent cloud analysis to measure the heart sounds of children, and obtains the detection result of the acute respiratory infection of children. However, the device needs to upload data to the intelligent cloud end for remote diagnosis by a doctor, and has the disadvantages of complex operation, single detection function, poor flexibility and high price.
Chinese patent document "an artificial intelligent stethoscope and a method for establishing a pathological sound library" (publication number CN110731791A, publication date 1/31/2020) discloses an artificial intelligent stethoscope and a method for establishing a pathological sound library, the main processes of the inventive method are as follows: the method comprises the steps of collecting heart sounds, breath sounds and the like of a patient who is registered for inquiry by using sound collection equipment, establishing a data set, extracting data frequency domain characteristics, and then carrying out classification and identification by using a convolutional neural network. The diagnosis result of the scheme can only judge the type of sound but cannot diagnose the specific symptom type, the requirement on the professional degree of a user is high, particularly, the monitoring on the patient in the scheme needs the patient to check and analyze the result by using a stethoscope when the patient perceives the abnormality, the actual monitoring effect is large due to human difference, and the crowd universality is not strong; in addition, the stethoscope structure in the scheme is not provided with a manual auscultation interface, can only be used for preliminary diagnosis of ordinary personnel, cannot be used in cooperation with professional auscultation skills and experience of doctors, and is poor in interactivity.
To sum up, the current multifunctional wireless intelligent stethoscope has the problems of single measurement and diagnosis function, poor actual monitoring effect, poor interactivity, complex operation, incomplete utilization of data and the like, so that the intelligent level of the stethoscope in actual use is not high, and the diagnosis effect is not ideal.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a wireless stethoscope and aims to solve the problems of single measurement and diagnosis function, poor actual monitoring effect, poor interactivity, complex operation, incomplete data utilization and the like of the conventional multifunctional wireless intelligent stethoscope, so that the intelligent level is not high in actual use and the diagnosis effect is not ideal.
To achieve the above object, the present invention provides a wireless stethoscope, comprising: a chest piece and a mobile terminal;
the chest piece is used for collecting sound signals of all parts by being respectively placed at all parts of the body of a user and sending the collected sound signals to the mobile terminal in a wireless transmission mode; the various parts of the body include: heart, lung, abdomen, and blood vessels;
the mobile terminal is used for diagnosing the sound signals by combining the trained diagnostic network so as to give auscultation results to the user.
Optionally, the wireless stethoscope further comprises: a cloud system;
the mobile terminal is also used for uploading the sound signal and auscultation result of the user to the cloud system;
the cloud system is used for carrying out structured and unstructured data analysis according to the sound signals, auscultation results, the user's past medical history, genetic medical history, genomics and related cases uploaded by the mobile terminal, excavating hidden information of the sound signals, and carrying out disease prediction so as to further diagnose the health condition of the user.
Specifically, the cloud system sends the further diagnosis result to the mobile terminal so as to be displayed through the mobile terminal.
Optionally, the mobile terminal is further configured to display the diagnosis result.
Optionally, the mobile terminal is further configured to display a waveform of the sound signal and play the sound signal.
Optionally, the chest piece collects sound signals of all parts through a piezoelectric film sensor;
the piezoelectric thin film sensor includes: the device comprises a piezoelectric film sensing diaphragm, a protective diaphragm and a sound insulation bin;
the piezoelectric film sensing diaphragm is embedded in the center of the bottom surface of the chest piece shell, the protection diaphragm is fixed on the outer side of the piezoelectric film sensing diaphragm and is hermetically connected with the chest piece shell, and the sound insulation bin is fixed on the inner side of the piezoelectric film sensing diaphragm and tightly wraps the piezoelectric film sensing diaphragm.
Optionally, the chest piece performs preliminary classification and filtering on the collected sound signals before sending the collected sound signals to the mobile terminal in a wireless transmission manner.
Optionally, the trained diagnostic network comprises: a feature extraction network and an analysis and diagnosis network;
the feature extraction network extracts MFCC features and spectral centroid features of the preliminary classification and filtering signals and inputs the features into an analysis and diagnosis network;
the analysis and diagnosis network adopts a well-trained three-hidden-layer BP neural network, ResNet and a corresponding parameter set to analyze and calculate the input characteristic signals, and obtains corresponding symptom characteristics, possible diseases and the probability of the diseases through diagnosis.
Optionally, after receiving the sound signal, the mobile terminal performs digital filtering on the signal segment, separates four types of signals with large differences, namely heart sound, lung sound, bowel sounds and large vessel noise, and outputs the four types of signals according to requirements for auscultation; meanwhile, the four types of signals are input into a trained analysis and diagnosis network for diagnosis, the diagnosis result is displayed according to the intensity difference of the four types of signals, and the signal with the maximum intensity occupies a dominant position.
Optionally, the cloud system integrates and calls data of the data layer for analysis, and hidden information in the data is obtained by a classification, regression analysis, clustering, association rule, feature, change and deviation analysis data mining method to realize disease prediction and clinical decision support.
Optionally, a remote connection between the chest piece and a mobile terminal;
the wireless stethoscope is suitable for remote wireless diagnosis of a user and is also suitable for home self-diagnosis of the user.
Generally, compared with the prior art, the above technical solution conceived by the present invention has the following beneficial effects:
the wireless stethoscope provided by the invention adopts an intelligent diagnosis network, adopts a multi-feature extraction technology and a deep learning network to carry out data intelligent analysis and diagnosis, diagnoses possible symptoms, diseases and probability, provides an intelligent diagnosis result for home health monitoring and a reference result for auscultation of doctors, realizes double verification, reduces misdiagnosis rate and improves auscultation efficiency.
The wireless stethoscope provided by the invention has multiple auscultation functions, can be used for auscultating signals including heart sounds, lung sounds, bowel sounds, large vessel noise and the like at different parts, and can provide a plurality of diseases such as heartbeat premature beats, atrial fibrillation, abnormal heart structure, obstructive pulmonary emphysema, pleural effusion, acute gastroenteritis, mechanical intestinal obstruction, large gastric hemorrhage, carotid artery or vertebral artery abnormality and the like for pre-diagnosis and medical advice and the like by combining an intelligent diagnosis network and an intelligent cloud end system.
The wireless stethoscope provided by the invention has the advantages that the wireless auscultation and the equipment operation are simple, the chest piece is subjected to wireless auscultation, so that a doctor can avoid close contact during auscultation, the infection risk is reduced, and the wireless stethoscope can be applied to places with high infection risk. The surface smoothness of the chest piece and the good tightness of the button are convenient for cleaning and disinfection after use. The intelligent analysis of the intelligent mobile terminal makes frequent switching and auscultation function setting unnecessary, and the auscultation process is simplified.
The wireless stethoscope provided by the invention adopts the intelligent cloud system, auscultation data, other medical knowledge and hospitalizing history data can be collected, a large database is formed, data mining is carried out on massive data, the results are applied to disease prediction, data awakening, clinical decision support and the like, the maximum utility of the data is exerted, and intelligent monitoring of family health and intellectualization of the hospitalizing process are realized.
The wireless stethoscope provided by the invention can replace the existing wireless stethoscope to perform auscultation of heart sounds, lung sounds, bowel sounds and large vessel noise and perform pre-diagnosis analysis of various diseases, and can realize disease prediction, data awakening, clinical decision support and the like by combining with a cloud. Can be applied to common hospital clinic auscultation, isolation hospitals, common family health monitoring, nursing home health monitoring, medical research institutions and other related application and research related fields.
Drawings
FIG. 1 is a schematic view of a chest piece structure of a wireless stethoscope according to the present invention; FIG. 1 (a) is a schematic view of the external structure of the chest piece; FIG. 1 (b) is a schematic cross-sectional view of the chestpiece;
fig. 2 is a schematic structural diagram of an intelligent mobile terminal of a wireless stethoscope according to the present invention; fig. 2 (a) is a front view of the smart mobile terminal; fig. 2 (b) is a right side view of the smart mobile terminal; fig. 2 (c) is a left side view of the smart mobile terminal; fig. 2 (d) is a top view of the smart mobile terminal;
fig. 3 is a schematic diagram of the structure and working relationship of the intelligent cloud system of the wireless stethoscope according to the present invention;
FIG. 4 is a schematic diagram of a data preprocessing and feature extraction process of the intelligent diagnosis network provided by the present invention;
FIG. 5 is a schematic diagram of a data intelligent diagnosis neural network structure of the intelligent diagnosis network provided by the present invention;
the same reference numbers will be used throughout the drawings to refer to the same or like elements or structures, wherein: 1 is the chest casing, 2 is chest work pilot lamp, 3 is chest control button, 4 is the chest mouth that charges, 5 is piezoelectric film sensing diaphragm, 6 is the protection diaphragm, 7 is the storehouse that gives sound insulation, 8 is chest circuit board, 9 is chest battery module, 10 is chest operation and interface circuit module, 11 is the intelligent Mobile terminal shell, 12 is the intelligent Mobile terminal hangers, 13 is the volume key of transferring upward, 14 is the volume key of transferring downward, 15 is display screen, 16 is the key of shutting down, 17 is the ear piece interface, 18 is the work pilot lamp, 19 is the interface that charges, 20 is the quantity of electricity pilot lamp.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a multifunctional wireless intelligent stethoscope based on measurement of heart sounds, lung sounds, bowel sounds and blood vessel murmurs, which combines intelligent cloud storage calculation and data analysis, is simple to operate, and can realize intelligent discrimination and multi-feature extraction analysis of signals such as the heart sounds, the lung sounds, the bowel sounds and the large blood vessel murs and diagnose possible various diseases and disease degrees. Meanwhile, historical auscultation data of the patient are stored in the intelligent cloud, structured and unstructured data analysis is carried out, and the intelligent analysis result of a large amount of data can be used for achieving functions of data awakening, clinical decision support, disease prediction and the like. Simple operation, intelligent and humanized diagnosis report greatly reduces the difficulty of medical care and use of family personnel. The intelligent diagnosis report of the stethoscope can assist medical staff in auscultation, reduce misdiagnosis rate, assist doctors in realizing double-verification diagnosis and improve auscultation efficiency. Big data based on intelligence high in the clouds not only can be used for each hospital information island interconnection, and the analysis result of data still can be used for realizing disease prediction and early warning of seeking medical advice in advance etc. especially when medical resources to the limit, provide long-range wireless diagnosis to the disease that the house kept apart, realize real family health monitoring, provide instruction and support for accurate medical resources allotment under the urgent epidemic situation.
The invention provides a multifunctional wireless intelligent stethoscope based on heart, lung, abdomen and blood vessels, which can be used for multifunctional wireless auscultation and intelligent diagnosis analysis in hospital medical systems, intelligent monitoring of family health, high infection risk and other occasions.
Aiming at the defects of the existing wireless stethoscope, the invention provides the following technical scheme: a multifunctional wireless intelligent stethoscope comprises a chest piece, an intelligent mobile terminal and an intelligent cloud system; the chest piece is a column piece which accords with the human engineering structure and is suitable for being grasped, and comprises a peripheral connecting control piece, a sensing module and a main control circuit module; the intelligent mobile terminal is a display control device capable of being wirelessly connected with a chest piece and an intelligent cloud, and comprises an external connection control piece, a main control circuit module, an intelligent analysis module and a wireless communication module; the intelligent cloud system comprises a system layer, a data layer and an interaction layer. The chest piece is used for collecting heart sound, lung sound, bowel sounds and large vessel noise signals at different parts for preprocessing and wirelessly transmitting the signals to the intelligent mobile terminal. After various characteristics of the signals are extracted by mobile diagnosis, the BP network and ResNet are used for identification and diagnosis, and intelligent diagnosis results including health states, disease types and degrees, medical advice and the like are given. The intelligent cloud collects data signals collected by the intelligent mobile terminal after the user agrees to form a big database, and effective information is mined from the data. The intelligent mobile terminal and the intelligent cloud data are analyzed and combined to achieve intelligent diagnosis, health monitoring, disease prediction and the like.
The chest piece is used for being equipped with a sensing module, a chest piece circuit module and an indicating device. The chest piece is a column piece which accords with the human engineering structure and is suitable for being grasped, comprises a main switch key, an indicator lamp and a charging interface, and is internally provided with a piezoelectric film sensor, a sound insulation bin, a protective layer and a chest piece circuit module; switch button inlays in casing top center, and the pilot lamp is fixed in the button both sides respectively with the interface that charges.
The chest piece piezoelectric film sensor is used for collecting signals of cardiopulmonary sounds, bowel sounds, large vessel noise and the like at different parts. The chest piece piezoelectric film sensor comprises a piezoelectric film sensing diaphragm, a protective diaphragm and a sound insulation bin; the piezoelectric sensing diaphragm is embedded in the center of the bottom surface of the chest piece shell, the protection diaphragm is fixed on the outer side of the piezoelectric film and is hermetically connected with the shell, and the sound insulation bin is fixed on the inner side of the piezoelectric film and tightly wraps the piezoelectric film.
The chest piece circuit module is used for processing, sending signals and controlling. The chest piece circuit module is arranged above the sensing module and comprises a filtering amplification module, a Bluetooth and WiFi sending module, a switch module, a power supply module and a control module; the filter amplification circuit module receives and processes the measurement signal of the piezoelectric film sensor and performs primary processing; the control module converts the signal into a digital signal and sends the digital signal to the intelligent mobile terminal according to a certain frame format and rate; the power supply module supplies power to all the power consumption modules.
The intelligent mobile terminal is used for processing data and intelligently diagnosing. The intelligent mobile terminal comprises a signal receiving module, a signal filtering/separating module, an intelligent diagnosis network module, a display screen, a storage module, an intelligent cloud connection module, a switch button, two volume adjusting buttons, an earphone interface and a charging interface; switch button inlays in casing right side top, and the volume control button inlays in casing left surface top, and earphone interface, work pilot lamp, electric quantity pilot lamp, the interface that charges are all fixed arrange respectively in the casing top surface.
The intelligent mobile terminal intelligent diagnosis network module is used for diagnosing and analyzing signals and generating a diagnosis report. The intelligent mobile terminal intelligent diagnosis network module comprises a feature extraction network and a disease analysis and diagnosis network. The feature extraction network extracts MFCC features and spectral centroid features of the signals subjected to the preliminary classification and filtering and inputs the features into the analysis and diagnosis network. The analysis and diagnosis network adopts the well-trained three-hidden-layer BP neural network, ResNet and a corresponding parameter set to analyze and calculate the characteristic signals, and obtains the corresponding symptom characteristics, possible diseases and the probability thereof through diagnosis.
The intelligent cloud system is used for collecting effective auscultation signals from the intelligent mobile terminal, performing data structured and unstructured analysis, mining data hidden information, performing disease prediction, data awakening, clinical decision support and the like. The intelligent cloud system comprises a system layer, a data layer and an interaction layer. The system layer comprises a medical database system and an expert/remote system, the medical database system is used for collecting, counting and analyzing related data and mining data hidden information, and the expert/remote system is used for realizing information isolated island communication and remote medical diagnosis. The data layer comprises the past medical history, the genetic medical history, the genomics, the case structure and unstructured analysis and arrangement data, mass data is the basis of data mining, and the data layer provides necessary data support for intellectualization. And the interaction layer applies the statistical analysis results of the system layer and the data layer to different specific scenes to realize the maximization of data utilization. The application scene realized by the interaction layer comprises medication auxiliary management, cloud intelligent diagnosis, medication plan/suggestion, a medical history report, a housekeeping system and the like. The system layer, the data layer and the interaction layer are interconnected and operate together.
As shown in fig. 1 (a), the present invention provides a multifunctional wireless intelligent stethoscope based on heart, lung, abdomen and blood vessels, wherein the chest piece shell structure comprises: the device comprises an annular shell 1, a work indicator lamp 2, a switch key 3 and a charging port 4; the shell 1 is used for being equipped with peripheral equipment and a circuit module, the work indicator light 2 is used for indicating the chest piece shutdown/dormancy/work/electric quantity state, and the switch key 3 is used for the chest piece startup/shutdown.
As shown in fig. 1 (b), the chest piece includes inside: the device comprises a piezoelectric film sensing diaphragm 5, a protective diaphragm 6, a sound insulation bin 7, a main circuit board 8, a power supply battery bin 9 and an auxiliary circuit board 10.
As shown in fig. 2 (a), 2 (b), 2 (c), and 2 (d), the smart mobile terminal includes a housing 11, a suspension loop 12, a volume up key 13, a volume down key 14, a display screen 15, an on/off key 16, an earphone interface 17, a work indicator 18, a charging interface 19, and an electric quantity indicator 20.
Fig. 3 is a schematic diagram showing the working principle of the multifunctional wireless intelligent stethoscope system. Wherein: the chest piece circuit part comprises a piezoelectric film sensing module, an amplifying and filtering circuit module, an MCU main control module, a communication module and a power supply module. The intelligent mobile terminal part comprises a communication module, a main control module, a filtering/signal separating module, an intelligent diagnosis network, a storage module and a power supply module. The intelligent cloud system comprises a system layer, a data layer and an interaction layer. The system layer comprises a medical database system and an expert/remote system, the data layer comprises the historical medical history, the hereditary medical history, the genomics, the case structured and unstructured data analysis results, and the interaction layer comprises a medication auxiliary management system, a cloud intelligent diagnosis system, a treatment plan/suggestion, a medical history report, a housekeeping system and the like. Chest piece sensing module laminating auscultation position detects the sound signal that human organ activity produced, and high sensitivity piezoelectric film is current signal and input amplification filter circuit module through piezoelectricity conversion, and amplification filter circuit module received signal input tentatively filters out the noise, inputs master control module AD after the amplification and converts into digital signal, sends the signal to intelligent mobile terminal according to predetermineeing communication parameter through communication module.
After the intelligent mobile terminal receives the signals, the signals are segmented and digitally filtered, four types of signals with large differences, namely heart sounds, lung sounds, bowel sounds and large vessel noise, are separated, and the four types of signals can be output and auscultated as required. Meanwhile, the four types of signals are input into an intelligent diagnosis network for diagnosis, the diagnosis result is displayed according to the intensity difference of the four types of signals, and the signal with the maximum intensity occupies a leading position. The intelligent cloud system collects auscultation data after obtaining the consent of the user, and combines the data of the medical knowledge base and the results of structured analysis and unstructured analysis of the data to form a database system, the medical database system of the system layer can integrate and call the data of the data layer for analysis, and hidden information in the data is obtained by adopting data mining methods such as classification, regression analysis, clustering, association rules, characteristics, variation, deviation analysis and the like to realize the functions of disease prediction, clinical decision support and the like, and the system can be particularly applied to the scenes such as medication auxiliary management, cloud intelligent diagnosis, medication plan/suggestion, disease history report, housekeeper system and the like.
Fig. 4 is a schematic diagram illustrating data preprocessing and feature extraction of the intelligent diagnosis network. The four types of signals after the preliminary classification are subjected to down sampling, filtering and normalization operation and then are divided into two paths of signals, the first path of N groups of signals are subjected to pre-emphasis, M frame division and windowing, and N M groups of MFCC characteristic parameters are obtained after Fast Fourier Transform (FFT) transformation, Mel filtering, logarithm taking and DCT transformation are carried out. And the second path is subjected to time-frequency analysis, energy spectrum calculation and frequency weighting according to energy to obtain N groups of sound spectrum centroid characteristic parameters. Two parameters of the N groups of signals are input into the intelligent analysis network.
Fig. 5 is a schematic diagram of a data intelligent diagnosis neural network of the intelligent diagnosis network. Inputting N groups of sound spectrum centroid characteristic parameters into a three-hidden-layer BP network for identification and analysis to obtain initial discrimination results of signals, namely environmental noise, normal signals and abnormal signals, inputting the identification results and N groups of MFCCs into a ResNet network together, and selecting a corresponding trained parameter set according to the initial classification results of the signals by the network parameters to participate in calculation. And the signal data is calculated by a network and then outputs corresponding symptoms and probability values thereof, and the corresponding diseases and the severity thereof are matched in the database in a matching mode according to the probability interval and the symptoms.
The intelligent mobile terminal signal amplification filter circuit adopts an FIR digital filter circuit, 4 band-pass filters are arranged, the passband of a heart sound filter is 30 Hz-500 Hz, the passband of a lung sound filter is 100 Hz-1000 Hz, the bowel sound is 4 times/minute-5 times/minute, the times and frequency can change along with symptoms when abnormal, an effective signal segment of the bowel sound can be searched through a continuous monitoring and heterodyne method, the distribution frequency of the large vessel noise is wide, and a measurement signal is regarded as the large vessel noise signal after other main signals and environmental noise signals are subtracted through a subtraction method.
In a specific embodiment, the flow of the multifunctional wireless intelligent stethoscope is described by taking the application to the auscultation examination of patients in a shelter hospital as an example, and the specific operation steps are as follows:
auscultation measurement: the doctor wears intelligent Mobile terminal and carries the chest piece to each patient bed to carry out the auscultation, hold the chest piece by the patient during the auscultation and place the chest piece in appointed position according to the doctor instruction and listen sound, the doctor can switch the auscultation through signals such as intelligent Mobile terminal heart sound, lung sound, and simultaneously, intelligent Mobile terminal's intelligent diagnosis network also can carry out diagnostic analysis to the effective signal of gathering, obtain diagnosis symptom and probability, with this diagnosis of supplementary doctor to the disease, reduce the misdiagnosis rate, improve auscultation efficiency.
Health monitoring: because medical personnel staff is nervous, the disease is more, and the disease can be when medical personnel do not have spare intelligent auscultation instrument of use by oneself. The patient can intelligently auscultate only by placing the chest piece at a proper position according to the instruction of the intelligent mobile terminal, and a preliminary diagnosis conclusion is obtained. The disease can select to upload auscultation data and auscultation result to cloud system in the middle of, the doctor can look over numerous disease health monitoring condition through high in the clouds system, and the system also can remind the doctor when discovering abnormal signal, is reexamined by the doctor, greatly reduced doctor's work load.
The intelligent cloud: after auscultation data are collected by the intelligent cloud, transverse comparison and longitudinal analysis are carried out on a large amount of data by combining data such as medical history analysis data and a medical resource library, and specific symptom development prediction, medication guidance and clinical decision support are given to each patient by adopting data mining methods such as classification, regression analysis, clustering, association rule, characteristic, change and deviation analysis. The development trend and prediction of the disease are given according to the development of the whole epidemic situation, and medical care personnel and the government are guided to take corresponding measures in advance. Aiming at the virus medication guidance, the system searches for rules from the examples of symptoms, corresponding medication and effects of a large number of patients and digs out efficient medicine and efficient treatment modes aiming at the virus.
Remote medical treatment: the cloud system stores the medical history data of each patient and the past medical history and other data in the database, and when the patient encounters symptoms difficult to diagnose, the hospital can invite experts of other hospitals to carry out remote online diagnosis, so that assistance is provided for resisting epidemic situations. The cloud can record the medication, diagnosis results, disease development process and other data of the patient in the community hospital and after transfer, and after receiving a new hospital, a doctor can quickly know the disease condition of the patient, give corresponding treatment measures and save medical resources.
The invention discloses a multifunctional wireless intelligent stethoscope based on heart, lung, abdomen and blood vessels, which comprises a chest piece, an intelligent mobile terminal and an intelligent cloud system, wherein the chest piece is connected with the intelligent mobile terminal through a wireless network; the chest piece is a column piece which accords with the human engineering structure and is suitable for grasping, and comprises a peripheral connecting control piece, a sensing module and a main control circuit module; the intelligent mobile terminal comprises a signal preprocessing module, an intelligent diagnosis network and a main control system; the intelligent cloud system comprises a system layer, a data layer and an interaction layer. The chest piece is used for measuring the activity signals of organs at different parts of the body, performing primary processing and transmitting the signals to the intelligent terminal. And the intelligent terminal performs noise reduction and separation on the signals, performs intelligent diagnosis on the signals by adopting an intelligent diagnosis network and returns a diagnosis result. The cloud system stores and analyzes a large amount of case data, and data awakening, clinical decision support and disease prediction can be achieved through the expert system and the medical database system. The multifunctional wireless auscultation and intelligent diagnosis system is particularly suitable for being used for multifunctional wireless auscultation and intelligent diagnosis analysis in hospital medical systems, household health intelligent monitoring, high infection risk and other occasions, has the characteristics of simplicity in operation, no contact, intelligent diagnosis, cloud storage, data analysis and prediction and the like, and has wide application prospects.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.

Claims (10)

1. A wireless stethoscope, comprising: a chest piece and a mobile terminal;
the chest piece is used for collecting sound signals of all parts by being respectively placed at all parts of the body of a user and sending the collected sound signals to the mobile terminal in a wireless transmission mode; the various parts of the body include: heart, lung, abdomen, and blood vessels;
the mobile terminal is used for diagnosing the sound signals by combining the trained diagnostic network so as to give auscultation results to the user.
2. The wireless stethoscope of claim 1, further comprising: a cloud system;
the mobile terminal is also used for uploading the sound signal and auscultation result of the user to the cloud system;
the cloud system is used for carrying out structured and unstructured data analysis according to the sound signals, auscultation results, the past medical history, the genetic medical history, genomics and related cases of the user, which are uploaded by the mobile terminal, excavating hidden information of the sound signals, and carrying out disease prediction so as to further diagnose the physical health condition of the user.
3. The wireless stethoscope of claim 1, wherein said mobile terminal is further configured to display said diagnostic result.
4. The wireless stethoscope according to claim 1, wherein said mobile terminal is further configured to display the waveform of said sound signal and play said sound signal.
5. The wireless stethoscope according to any one of claims 1 to 4, wherein said chestpiece collects sound signals from various locations via a piezoelectric film sensor;
the piezoelectric thin film sensor includes: the device comprises a piezoelectric film sensing diaphragm, a protective diaphragm and a sound insulation bin;
the piezoelectric film sensing diaphragm is embedded in the center of the bottom surface of the chest piece shell, the protection diaphragm is fixed on the outer side of the piezoelectric film sensing diaphragm and is hermetically connected with the chest piece shell, and the sound insulation bin is fixed on the inner side of the piezoelectric film sensing diaphragm and tightly wraps the piezoelectric film sensing diaphragm.
6. The wireless stethoscope according to any one of claims 1 to 4, wherein said chestpiece is configured to perform preliminary classification and filtering of the collected sound signals before transmitting the collected sound signals to said mobile terminal by wireless transmission.
7. The wireless stethoscope of claim 6, wherein said trained diagnostic network comprises: a feature extraction network and an analysis and diagnosis network;
the feature extraction network extracts MFCC features and sound spectrum centroid features of the preliminary classification and filtering signals and inputs the features into an analysis and diagnosis network;
the analysis and diagnosis network adopts a well-trained three-hidden-layer BP neural network, ResNet and a corresponding parameter set to analyze and calculate the input characteristic signals, and obtains corresponding symptom characteristics, possible diseases and probability thereof through diagnosis.
8. The wireless stethoscope according to any one of claims 1 to 4, wherein said mobile terminal receives sound signals, digitally filters the received sound signals, separates four types of signals with large differences, namely heart sounds, lung sounds, bowel sounds and large vessel noise, and outputs the four types of signals according to the requirements for auscultation; meanwhile, the four types of signals are input into a trained analysis and diagnosis network for diagnosis, the diagnosis result is displayed according to the intensity difference of the four types of signals, and the signal with the maximum intensity occupies a dominant position.
9. The wireless stethoscope according to any one of claims 1 to 4, wherein said cloud system integrates and calls data of said data layer for analysis, and uses classification, regression analysis, clustering, association rule, feature, variation and deviation analysis data mining methods to obtain hidden information in said data for implementing disease prediction and clinical decision support.
10. The wireless stethoscope according to any one of claims 1 to 4, wherein said chestpiece and mobile terminal are remotely connected;
the wireless stethoscope is suitable for remote wireless diagnosis of a user and is also suitable for home self-diagnosis of the user.
CN202010626624.XA 2020-07-02 2020-07-02 Wireless stethoscope Pending CN111820937A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010626624.XA CN111820937A (en) 2020-07-02 2020-07-02 Wireless stethoscope

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010626624.XA CN111820937A (en) 2020-07-02 2020-07-02 Wireless stethoscope

Publications (1)

Publication Number Publication Date
CN111820937A true CN111820937A (en) 2020-10-27

Family

ID=72900047

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010626624.XA Pending CN111820937A (en) 2020-07-02 2020-07-02 Wireless stethoscope

Country Status (1)

Country Link
CN (1) CN111820937A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112617886A (en) * 2020-12-14 2021-04-09 华中科技大学 Wearable wireless auscultation device
RU2749725C1 (en) * 2020-12-07 2021-06-16 Ооо «Медхард» Digital stethoscope
CN113017681A (en) * 2021-03-05 2021-06-25 北京奥图无线技术有限公司 Intelligent stethoscope system
CN113081025A (en) * 2021-03-10 2021-07-09 华中科技大学 New crown pneumonia intelligent diagnosis system and device based on lung sounds
CN113974679A (en) * 2020-11-13 2022-01-28 广东科学技术职业学院 Stethoscope, heart sound detection method, heart sound detector and auscultation system
WO2023070212A1 (en) * 2021-10-26 2023-05-04 Sparrow Acoustics Inc. Method and an electronic device for processing a waveform

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140128753A1 (en) * 2012-11-08 2014-05-08 Aliphcom Piezoelectric heart rate sensing for wearable devices or mobile devices
CN110731791A (en) * 2019-10-30 2020-01-31 郑州大学第一附属医院 artificial intelligent stethoscope and method for establishing pathological sound library
CN111035407A (en) * 2019-12-26 2020-04-21 航天中心医院 Wireless electronic stethoscope

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140128753A1 (en) * 2012-11-08 2014-05-08 Aliphcom Piezoelectric heart rate sensing for wearable devices or mobile devices
CN110731791A (en) * 2019-10-30 2020-01-31 郑州大学第一附属医院 artificial intelligent stethoscope and method for establishing pathological sound library
CN111035407A (en) * 2019-12-26 2020-04-21 航天中心医院 Wireless electronic stethoscope

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113974679A (en) * 2020-11-13 2022-01-28 广东科学技术职业学院 Stethoscope, heart sound detection method, heart sound detector and auscultation system
RU2749725C1 (en) * 2020-12-07 2021-06-16 Ооо «Медхард» Digital stethoscope
WO2022124940A1 (en) * 2020-12-07 2022-06-16 Максим Григорьевич ГУМЕНЮК Digital stethoscope
CN112617886A (en) * 2020-12-14 2021-04-09 华中科技大学 Wearable wireless auscultation device
CN113017681A (en) * 2021-03-05 2021-06-25 北京奥图无线技术有限公司 Intelligent stethoscope system
CN113081025A (en) * 2021-03-10 2021-07-09 华中科技大学 New crown pneumonia intelligent diagnosis system and device based on lung sounds
WO2023070212A1 (en) * 2021-10-26 2023-05-04 Sparrow Acoustics Inc. Method and an electronic device for processing a waveform

Similar Documents

Publication Publication Date Title
CN111820937A (en) Wireless stethoscope
Jin et al. Predicting cardiovascular disease from real-time electrocardiographic monitoring: An adaptive machine learning approach on a cell phone
CN102973263B (en) Intelligent ambulatory electrocardiogram comprehensive treatment device
CN108577830B (en) User-oriented physical sign information dynamic monitoring method and system
KR101178867B1 (en) Telemedical stethoscope
TWI650737B (en) Wearable device and method for evaluating possible occurrence of cardiac arrest
CN104305961A (en) Bowel sounds monitoring and recognizing system
CN104873186A (en) Wearable artery detection device and data processing method thereof
CN208582430U (en) Multifunctional medical care stethoscope
CN103479385A (en) Wearable heart, lung and intestine comprehensive detection equipment and method
CN109276272A (en) A kind of multifunctional intellectual stethoscope
CN106510751A (en) Multifunctional electronic stethoscope and auscultation system
CN204909917U (en) Intelligent sheet of sleep guardianship and medical diagnosis based on cloth sensor
CN111407306A (en) Multi-channel differential respiration sound intelligent wearable monitoring system based on mobile terminal
CN113633277A (en) Intelligent mattress with health monitoring function
CN103169459A (en) Medical device and implementation method
EP4205661B1 (en) Wearable heart sound detection system and method thereof
CN110638482A (en) Real-time monitoring system and method for bowel sound and abdominal pressure
KR20180065039A (en) Smart phone ubiquitous healthcare diagnosis system using vital integrated communication module
CN206499478U (en) Multi-purpose electronic stethoscope
CN215272721U (en) Community outpatient service hypertension diagnosis and treatment information management system
CN115844346A (en) Wireless physical sign parameter monitoring device applied to disease examination, observation and treatment
CN206239404U (en) A kind of dynamic electrocardiogram and blood pressure wireless monitoring system
Sergi et al. An IoT-based Platform for Remote Monitoring of Patients with Heart Failure: an Overview of Integrable Devices
CN113197597A (en) Portable handheld cardiopulmonary data synchronous acquisition equipment

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20201027

RJ01 Rejection of invention patent application after publication