Auscultation method and system for digitally storing and analyzing heart and lung sounds

Abstract

The invention provides an auscultation method and an auscultation system for digitally storing and analyzing heart and lung sounds. The auscultation method comprises the following steps: acquiring heart and lung sound signals of a patient by using a sound pickup of a digital stethoscope; the heart and lung sound signals are converted into digital signals through an analog-to-digital conversion chip; carrying out adaptive filtering processing on the digital signal; band-pass filtering is carried out through a signal filtering loop at the rear end of the microphone; identifying and removing environmental noise; performing fast Fourier transform analysis on the preprocessed digital signal; the analysis result is stored in a local storage device; and the heart and lung sound digital signal is transmitted to a remote server through the Wi-Fi module. According to the portable auscultation method and system, through accurate signal collecting and processing, real-time feedback and interaction, powerful data analysis capacity, safe data storage and transmission, portability and usability, the efficiency and accuracy of heart and lung sound diagnosis are remarkably improved, and important technical support is provided for modern medical diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to an auscultation method and system for digital storage and analysis of heart and lung sounds. Background Art

[0002] Traditional stethoscopes are widely used in the medical field. Auscultation of respiratory and heart sounds is of great significance in disease diagnosis and treatment, and can be used to diagnose and judge the efficacy of cardiopulmonary diseases. However, traditional stethoscopes have significant limitations. First, because the sound of the stethoscope is obtained through an ear-hanging stethoscope, only the auscultating doctor himself can hear the relevant sound, and the same sound cannot be identified and analyzed between different doctors or during medical teaching. This leads to subjectivity and inconsistency in diagnosis, limiting multi-doctor collaboration and teaching effectiveness.

[0003] With the progress of society and the improvement of civilization, patients are very concerned about their health status and are eager to understand the abnormal sounds of their heart and lungs. However, traditional stethoscopes cannot meet this demand of patients. At present, traditional stethoscopes cannot store abnormal sounds, making it difficult to reproduce case data and doctors cannot fully understand and track the characteristics of the disease. This limitation makes the diagnosis process lack of data support and difficult to track and analyze the disease for a long time.

[0004] Doctors are unable to use traditional ear-hanging stethoscopes to diagnose and treat patients due to isolation and protection measures. This situation highlights the shortcomings of traditional stethoscopes in responding to public health crises. The physical distance between doctors and patients limits the use of traditional stethoscopes, affecting the efficiency and safety of diagnosis and treatment.

[0005] In addition, with the rapid development of big data and artificial intelligence, AI diagnostic systems require the collection, storage and analysis of a large amount of cardiopulmonary abnormality data to improve diagnostic efficiency and accuracy. However, traditional stethoscopes are unable to digitize cardiopulmonary sound data, which makes further follow-up work impossible. The lack of digitized data means that AI systems cannot be effectively trained, limiting the development and application of intelligent diagnostic technology.

[0006] Therefore, these problems in the existing technology, especially the inability to share and store auscultation data, the lack of digital processing capabilities, and the inability to provide effective data for AI systems, have seriously restricted the efficiency and accuracy of cardiopulmonary disease diagnosis. Solving these problems is the key to improving the level of modern medical diagnosis. Summary of the invention

[0007] In order to overcome the shortcomings of the prior art, the present invention proposes an auscultation method and system for digital storage and analysis of heart and lung sounds. Through a high-precision microphone and an analog-to-digital conversion chip, the heart and lung sound signals are accurately captured and converted to ensure the high fidelity of the signal. Adaptive filtering algorithms and deep learning algorithms are used for noise processing to effectively remove environmental noise, retain the key features of heart and lung sounds, and further improve the accuracy of diagnosis.

[0008] To achieve the above object, the present invention provides an auscultation method for digital storage and analysis of heart and lung sounds, comprising:

[0009] Step 1: Use a microphone of a portable digital stethoscope to collect the patient's cardiopulmonary sound signals, wherein the microphone is used to amplify and transmit the patient's body sound waves;

[0010] Step 2: converting the heart and lung sound signal into a digital signal through an analog-to-digital conversion chip (ADC);

[0011] Step 3: Performing adaptive filtering on the digital signal, and dynamically adjusting the filtering parameters according to the noise environment using an adaptive filtering algorithm;

[0012] Step 4: Perform bandpass filtering through the signal filter circuit at the back end of the microphone to limit the frequency range of the audio signal to 20Hz to 20kHz, and increase the amplitude range of the audio signal to 0 to 4.5V through the op amp;

[0013] Step 5: Use deep learning algorithms to identify and remove environmental noise;

[0014] Step 6: The pre-processed digital signal is transmitted to a microcontroller unit (MCU) for fast Fourier transform (FFT) analysis;

[0015] Step 7: Storing the analysis results in a digital format in a local storage device;

[0016] Step 8: Transmit the cardiopulmonary sound digital signal to the remote server via the Wi-Fi module;

[0017] Step 9: During medical teaching or clinical diagnosis, the cardiopulmonary sound signals are played in real time using the built-in speaker.

[0018] Furthermore, the adaptive filtering process in step 3 includes the following steps:

[0019] Step 3.1: Initialize the adaptive filter parameters;

[0020] Step 3.2: Collect and analyze environmental noise data in real time;

[0021] Step 3.3: Dynamically adjust the filter parameters according to the environmental noise to optimize the filtering effect.

[0022] Furthermore, in step 5, the deep learning algorithm identifies and removes environmental noise including the following steps:

[0023] Step 5.1: Input the preprocessed digital signal into the pre-trained deep learning model;

[0024] Step 5.2: The model identifies and removes noise based on the learned noise features;

[0025] Step 5.3: Output the purified cardiopulmonary sound signal.

[0026] Further, the fast Fourier transform (FFT) analysis in step 6 includes the following steps:

[0027] Step 6.1: Windowing the digital signal;

[0028] Step 6.2: Apply FFT transform to the windowed signal;

[0029] Step 6.3: Extract spectrum features and store them in a local storage device.

[0030] Furthermore, an industrial-grade security encryption chip is used to perform data encryption processing during the data transmission process, and a multiple identity authentication mechanism is included to ensure the security of data access.

[0031] Furthermore, when abnormal cardiopulmonary sound signals are detected, an abnormality report is automatically generated and a reminder message is sent to the doctor via a mobile device. Based on the historical records and analysis results of the cardiopulmonary sound data, personalized health management suggestions and treatment plans are provided, and an AI-based predictive model is included to identify potential health problems in advance.

[0032] An auscultation system for digital storage and analysis of cardiopulmonary sounds, applicable to the auscultation method for digital storage and analysis of cardiopulmonary sounds, comprising: a sound pickup module, an analog-to-digital conversion module, a signal preprocessing module, a microcontroller unit, a storage module, a wireless transmission module, a playback module, a deep learning module, a data encryption module and a remote server;

[0033] The output end of the sound pickup module is connected to the input end signal of the analog-to-digital conversion module, the output end of the analog-to-digital conversion module is connected to the input end signal of the signal preprocessing module, the output end of the signal preprocessing module is connected to the input end signal of the microcontroller unit, the output end of the microcontroller unit is respectively connected to the input end signal of the storage module, the wireless transmission module and the playback module, and the output end of the wireless transmission module is connected to the input end signal of the remote server;

[0034] The signal preprocessing module includes a deep learning module, which is used for noise identification and removal. The wireless transmission module includes a data encryption module, which is used for encryption processing during data transmission.

[0035] Furthermore, the sound pickup module is used to collect the patient's cardiopulmonary sound signals and transmit them to the analog-to-digital conversion module;

[0036] The analog-to-digital conversion module is used to convert analog cardiopulmonary sound signals into digital signals;

[0037] The signal preprocessing module includes an adaptive filter for dynamically adjusting filter parameters according to environmental noise, and a bandpass filter for limiting the frequency range of the audio signal.

[0038] Furthermore, the deep learning module is used to identify and remove environmental noise;

[0039] The microcontroller unit includes a fast Fourier transform (FFT) analysis function for extracting the characteristic spectrum of the heart and lung sounds;

[0040] The storage module is used to store the analysis results in a local storage device in a digital format;

[0041] The wireless transmission module is used to transmit the digital signal of cardiopulmonary sound to a remote server via Wi-Fi, and includes a data encryption module to ensure the security during data transmission.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. The present invention provides an auscultation method and system for digital storage and analysis of cardiopulmonary sounds. Through high-precision microphones and analog-to-digital conversion chips, cardiopulmonary sound signals are accurately captured and converted to ensure high signal fidelity. Adaptive filtering algorithms and deep learning algorithms are used for noise processing to effectively remove environmental noise, retain key features of cardiopulmonary sounds, and further improve diagnostic accuracy.

[0044] 2. The present invention provides an auscultation method and system for digital storage and analysis of heart and lung sounds. The fast Fourier transform (FFT) algorithm extracts the spectral characteristics of heart and lung sounds and provides detailed signal analysis data. Big data analysis and artificial intelligence algorithm processing are performed through a remote server to further improve the accuracy and reliability of the diagnosis results. The built-in speaker plays the heart and lung sound signals in real time, which is convenient for doctors and patients to listen and analyze together, thereby improving the efficiency of doctor-patient communication and the effect of diagnosis and treatment. The real-time feedback mechanism enables doctors to obtain and process the patient's abnormal heart and lung sound signals in a timely manner, thereby improving the timeliness and effectiveness of medical services.

[0045] 3. The present invention provides an auscultation method and system for digital storage and analysis of cardiopulmonary sounds. The digital format is stored in an SD card or Flash memory to ensure high-capacity storage and long-term preservation of data. An industrial-grade security encryption chip and a multiple identity authentication mechanism are used to ensure the security and privacy protection of data during transmission, and prevent data leakage and illegal access.

[0046] 4. The present invention provides an auscultation method and system for digital storage and analysis of heart and lung sounds. The system is designed to be portable and suitable for various clinical and on-site medical environments, so that doctors can diagnose heart and lung sounds anytime and anywhere. By analyzing the patient's heart and lung sound data history records and current data, personalized health management suggestions and treatment plans are provided; AI-based predictive models are used to identify potential health problems in advance and provide early intervention and preventive measures; it is suitable for a variety of scenarios such as medical teaching, clinical diagnosis, and telemedicine, supports the classification and labeling of heart and lung sound data, and establishes a database of abnormal heart and lung sounds, providing rich data support for subsequent medical research and AI model training. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 It is a schematic diagram of the steps of the present invention DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be more clearly and completely explained below through description of preferred embodiments of the present invention in combination with the accompanying drawings.

[0050] like Figure 1 As shown, the present invention is specifically:

[0051] Step 1: Use the microphone of the digital stethoscope to collect the patient's cardiopulmonary sound signals, wherein the microphone is used to amplify and transmit the sound waves in the patient's body;

[0052] Step 2: Convert the heart and lung sound signals into digital signals through an analog-to-digital conversion chip;

[0053] Step 3: Perform adaptive filtering on the digital signal and use the adaptive filtering algorithm to dynamically adjust the filtering parameters according to the noise environment;

[0054] Step 4: Perform bandpass filtering through the signal filter circuit at the back end of the microphone to limit the frequency range of the audio signal to 20Hz to 20kHz, and increase the amplitude range of the audio signal to 0 to 4.5V through the op amp;

[0055] Step 5: Use deep learning algorithms to identify and remove environmental noise;

[0056] Step 6: The pre-processed digital signal is transmitted to the microcontroller unit for fast Fourier transform analysis;

[0057] Step 7: Storing the analysis results in a digital format in a local storage device;

[0058] Step 8: Transmit the cardiopulmonary sound digital signal to the remote server via the Wi-Fi module;

[0059] Step 9: During medical teaching or clinical diagnosis, the cardiopulmonary sound signals are played in real time using the built-in speaker.

[0060] The details are as follows:

[0061] Step 1: Use the microphone of a portable digital stethoscope to collect the patient's cardiopulmonary sound signals.

[0062] The microphone contacts the patient's body, amplifies and transmits the sound waves in the patient's body through the diaphragm, and captures the heart and lung sound signals.

[0063] The captured sound waves are converted into electrical signals and transmitted to the subsequent processing unit.

[0064] Step 2:

[0065] The cardiopulmonary sound signal is input into the analog-to-digital conversion chip (ADC).

[0066] The analog-to-digital conversion chip converts analog signals into digital signals, ensuring accurate signal conversion.

[0067] Adopting high-performance 32-bit processor, it can capture subtle sound details with high sampling rate and high resolution.

[0068] Step 3:

[0069] Perform adaptive filtering on digital signals.

[0070] Using the adaptive filtering algorithm, the filtering parameters are dynamically adjusted according to the environmental noise data collected in real time.

[0071] Initialize the adaptive filter parameters and make real-time adjustments according to the noise environment to optimize the filtering effect, remove background noise, and retain the key features of heart and lung sounds.

[0072] Step 4:

[0073] Bandpass filtering is performed through the signal filtering circuit at the back end of the microphone.

[0074] Limit the frequency range of the audio signal to 20Hz to 20kHz to filter out high- and low-frequency noise.

[0075] The audio signal amplitude range is increased to 0 to 4.5V by the op amp to match the input range of the analog-to-digital conversion chip.

[0076] Ensure signal clarity and amplitude consistency, and improve signal-to-noise ratio.

[0077] Step 5:

[0078] Use deep learning algorithms to identify and remove environmental noise.

[0079] The preprocessed digital signal is input into the pre-trained deep learning model.

[0080] The model identifies and removes noise based on the learned noise features.

[0081] Output the purified cardiopulmonary sound signal, retain the key features of the original signal, and improve the clarity and accuracy of the signal.

[0082] As a specific implementation method and implementation case

[0083] The collected original cardiopulmonary sound signals are segmented and processed, with audio segments of fixed length as input.

[0084] Normalize the audio clips to ensure that the input signal is within a uniform amplitude range and improve the stability of model processing.

[0085] Choose a deep learning model suitable for audio signal processing, such as a convolutional neural network (CNN) or a long short-term memory network (LSTM).

[0086] The CNN model is used to extract the spatial features of the audio signal, and the LSTM model is used to capture the temporal features of the audio signal.

[0087] The model is trained using a labeled heart and lung sound dataset, which includes heart and lung sound signals containing environmental noise and purified.

[0088] Data augmentation techniques are used during training, such as adding different types of noise, to improve the generalization ability of the model.

[0089] The preprocessed digital signal is input into the pre-trained deep learning model.

[0090] The model extracts features through convolutional layers and pooling layers to identify the noise part of the signal.

[0091] The purified signal output by the model is used to replace the noise part in the original signal, and the purified cardiopulmonary sound signal is output.

[0092] As a specific implementation case:

[0093] The environment in a certain hospital is noisy. When doctors use portable digital stethoscopes to diagnose heart and lung sounds, the collected signals contain a lot of environmental noise, which affects the diagnostic effect.

[0094] The steps to implement this method are as follows:

[0095] The doctor places the microphone of the portable digital stethoscope on the patient's chest to collect heart and lung sound signals.

[0096] The acquired signals are mixed with environmental noise, such as conversation and machine operation.

[0097] The collected heart and lung sound signals are processed in segments, with each segment being 2 seconds long.

[0098] Each signal is normalized so that its amplitude ranges from -1 to 1.

[0099] The preprocessed signal is input into the pre-trained CNN model.

[0100] The CNN model identifies the noise part of the signal and extracts signal features through convolution and pooling operations.

[0101] The model outputs the purified heart and lung sound signal, replacing it with the noise part of the original signal.

[0102] Results: The noise in the output heart and lung sound signals was significantly reduced, and the signal clarity was improved. Doctors were able to auscultate the patient's heart and lung sounds more accurately, thus improving the diagnostic effect.

[0103] Step 6: The pre-processed digital signal is transmitted to the microcontroller unit (MCU) for fast Fourier transform (FFT) analysis, which includes:

[0104] The pre-processed digital signal is transmitted to the microcontroller unit (MCU).

[0105] Perform window processing on digital signals and process the signals in segments.

[0106] The fast Fourier transform (FFT) algorithm is applied to the windowed signal to extract the spectral features of the heart and lung sounds.

[0107] Analyze spectral features and identify characteristic components in cardiopulmonary sound signals to provide a data basis for subsequent diagnosis and analysis.

[0108] As a specific implementation:

[0109] The preprocessed digital signal is segmented into fixed lengths, and each segment is called a window.

[0110] Usually a window function with good spectral characteristics (such as Hanning window) is selected to perform windowing processing on each signal segment.

[0111] Perform a Fast Fourier Transform (FFT) on each windowed signal segment.

[0112] FFT converts the time domain signal into the frequency domain signal and extracts the spectral characteristics of the heart and lung sounds.

[0113] Extract the main frequency components and amplitude information in the spectrum to form a feature vector.

[0114] Analyze the spectrum characteristics and identify abnormal components in the cardiopulmonary sound signals.

[0115] The extracted spectral features are stored in a local storage device for subsequent analysis.

[0116] Diagnosis and classification are performed based on spectral characteristics to assist doctors in making decisions.

[0117] As a specific implementation case:

[0118] Doctors analyze the patient's cardiopulmonary audio spectrum to identify potential cardiopulmonary diseases. The specific implementation steps are as follows:

[0119] The patient's heart and lung sound signals were collected using a portable digital stethoscope and normalized.

[0120] The signal is segmented, each segment is 1 second long, and the Hanning window is used for windowing.

[0121] The windowed signal segments are input to a microcontroller unit (MCU).

[0122] The MCU performs a Fast Fourier Transform (FFT) to convert the time domain signal into a frequency domain signal.

[0123] Extract the main frequency components and amplitude information in the frequency domain signal to form a feature vector.

[0124] Analyze spectral features and identify abnormal components in cardiopulmonary sound signals, such as noise and messy spectral structures.

[0125] The extracted spectrum features are stored in the SD card for subsequent analysis and diagnosis.

[0126] Based on the spectral characteristics, doctors can identify abnormalities in the patient's heart and lung sounds and make more accurate diagnostic decisions.

[0127] Feedback and Diagnosis:

[0128] Display spectrum characteristics in real time to provide reference for doctors.

[0129] Based on the analysis results, doctors can intervene and treat in a timely manner to improve the patient's diagnosis and treatment outcomes.

[0130] Step 7:

[0131] Store the analysis results in digital format in a local storage device such as an SD card or Flash memory.

[0132] Ensure the stability and high capacity of the storage device to save a large amount of cardiopulmonary sound data.

[0133] Reasonable data format and structure facilitate subsequent data retrieval and analysis.

[0134] Step 8:

[0135] The cardiopulmonary sound digital signal is transmitted to the remote server via the Wi-Fi module.

[0136] Industrial-grade security encryption chips are used for data encryption processing to ensure security and privacy protection during data transmission.

[0137] Leverage multi-factor authentication to ensure only authorized personnel can access and process data.

[0138] Step 9:

[0139] During medical teaching or clinical diagnosis, the built-in speaker can be used to play the heart and lung sound signals in real time.

[0140] The analog signal is output from the MCU to the speaker, and the cardiopulmonary sound signal is played through the speaker.

[0141] Doctors and patients listen to and analyze cardiopulmonary sound signals together to improve the efficiency of doctor-patient communication and the effectiveness of diagnosis and treatment.

[0142] As a specific implementation case, doctors in a hospital need to collect, process and analyze the patient's heart and lung sound signals in real time, store and transmit the data to a remote server for further analysis, and communicate effectively with the patient during the diagnosis process. The specific steps for implementing this method and system are as follows:

[0143] Implementing system architecture

[0144] Hardware Configuration

[0145] Pickup module: high-precision digital pickup

[0146] Analog-to-digital conversion module: ADC chip with high-performance 32-bit processor

[0147] Signal preprocessing module: adaptive filter and bandpass filter

[0148] Microcontroller unit (MCU): STM32H750 chip

[0149] Storage module: SD card

[0150] Wireless transmission module: Wi-Fi module with data encryption function

[0151] Playback module: built-in speaker

[0152] Deep learning module: for noise identification and removal

[0153] Data encryption module: SY1161Y encryption chip

[0154] Specific implementation steps

[0155] Step 1: Cardiopulmonary sound signal collection

[0156] The doctor places the microphone of the portable digital stethoscope on the patient's chest, and the microphone starts to collect the patient's cardiopulmonary sound signals.

[0157] The microphone converts the captured cardiopulmonary sound signals into electrical signals and transmits them to the analog-to-digital conversion module.

[0158] Step 2: Analog to Digital Conversion

[0159] The electrical signal is converted into a digital signal through an analog-to-digital conversion chip (ADC) to ensure the accuracy and precision of the signal conversion.

[0160] Step 3: Adaptive filtering

[0161] The digital signal enters the signal preprocessing module.

[0162] The adaptive filter dynamically adjusts the filtering parameters according to the real-time collected environmental noise data to optimize the filtering effect and remove background noise.

[0163] Step 4: Bandpass filtering

[0164] The signal filter circuit at the back end of the microphone performs bandpass filtering, limiting the frequency range of the audio signal to 20Hz to 20kHz, filtering out high-frequency and low-frequency noise.

[0165] The op amp boosts the audio signal's amplitude range to 0 to 4.5V to match the input range of the analog-to-digital conversion chip.

[0166] Step 5: Denoising with Deep Learning Algorithm

[0167] The preprocessed digital signal is input into the pre-trained deep learning model.

[0168] The deep learning model identifies and removes noise based on the learned noise features and outputs purified cardiopulmonary sound signals.

[0169] Step 6: Fast Fourier Transform (FFT) Analysis

[0170] The pre-processed digital signal is transmitted to the microcontroller unit (MCU).

[0171] Perform window processing on digital signals and process the signals in segments.

[0172] The fast Fourier transform (FFT) algorithm is used to extract the spectral characteristics of heart and lung sounds.

[0173] Step 7: Digital Signal Storage

[0174] The analysis results are stored in a digital format on an SD card, ensuring high-capacity storage and stability of data.

[0175] Step 8: Data Transfer

[0176] The cardiopulmonary sound digital signal is transmitted to the remote server via the Wi-Fi module.

[0177] The data is encrypted by the SY1161Y encryption chip during transmission to ensure data security and privacy protection.

[0178] After receiving the data, the remote server conducts further big data analysis and artificial intelligence algorithm processing to provide more accurate diagnostic results.

[0179] Step 9: Real-time broadcast and patient interaction

[0180] During medical teaching or clinical diagnosis, doctors use the built-in speakers to play heart and lung sound signals in real time.

[0181] Doctors and patients listen to and analyze cardiopulmonary sound signals together to improve the efficiency of doctor-patient communication and the effectiveness of diagnosis and treatment.

[0182] Implementation Effect

[0183] By using the portable digital stethoscope system, doctors can accurately and in real time collect and analyze the patient's cardiopulmonary sound signals, and can communicate effectively with the patient during the diagnosis process. The system not only improves the accuracy and efficiency of diagnosis, but also enhances the security of data and the stability of transmission. Through the big data analysis and artificial intelligence algorithm processing of the remote server, the accuracy and reliability of the diagnosis results are further improved. This portable digital stethoscope system provides an innovative, efficient and safe solution for medical diagnosis.

[0184] The above specific implementations are only descriptions of the preferred implementations of the present invention, and do not limit the protection scope of the present invention. Without departing from the design concept and spirit of the present invention, various modifications, substitutions and improvements made by ordinary technicians in this field to the technical solution of the present invention based on the text description and drawings provided by the present invention should all fall within the protection scope of the present invention. The protection scope of the present invention is determined by the claims.

Claims

1. An auscultation method for digital storage and analysis of heart and lung sounds, characterized in that: include: Step 1: Use the microphone of the digital stethoscope to collect the patient's cardiopulmonary sound signals, wherein the microphone is used to amplify and transmit the sound waves in the patient's body; Step 2: Convert the heart and lung sound signals into digital signals through an analog-to-digital conversion chip; Step 3: Perform adaptive filtering on the digital signal and use the adaptive filtering algorithm to dynamically adjust the filtering parameters according to the noise environment; Step 4: Perform bandpass filtering through the signal filter circuit at the back end of the microphone to limit the frequency range of the audio signal to 20Hz to 20kHz, and increase the amplitude range of the audio signal to 0 to 4.5V through the op amp; Step 5: Use deep learning algorithms to identify and remove environmental noise; Step 6: The pre-processed digital signal is transmitted to the microcontroller unit for fast Fourier transform analysis; Step 7: Storing the analysis results in a digital format in a local storage device; Step 8: Transmit the cardiopulmonary sound digital signal to the remote server via the Wi-Fi module; Step 9: During medical teaching or clinical diagnosis, the cardiopulmonary sound signals are played in real time using the built-in speaker.

2. The auscultation method for digital storage and analysis of heart and lung sounds according to claim 1, characterized in that: The adaptive filtering process in step 3 includes the following steps: Step 3.1: Initialize the adaptive filter parameters; Step 3.2: Collect and analyze environmental noise data in real time; Step 3.3: Dynamically adjust the filter parameters according to the environmental noise to optimize the filtering effect.

3. The auscultation method for digital storage and analysis of heart and lung sounds according to claim 1, characterized in that: In step 5, the deep learning algorithm identifies and removes environmental noise, including the following steps: Step 5.1: Input the preprocessed digital signal into the pre-trained deep learning model; Step 5.2: The model identifies and removes noise based on the learned noise features; Step 5.3: Output the purified cardiopulmonary sound signal.

4. The auscultation method for digital storage and analysis of heart and lung sounds according to claim 1, characterized in that: The fast Fourier transform analysis in step 6 includes the following steps: Step 6.1: Windowing the digital signal; Step 6.2: Apply FFT transform to the windowed signal; Step 6.3: Extract spectrum features and store them in a local storage device.

5. The auscultation method for digital storage and analysis of heart and lung sounds according to claim 1, characterized in that: During the data transmission process, an industrial-grade security encryption chip is used to perform data encryption processing, and a multiple identity authentication mechanism is included to ensure the security of data access.

6. The auscultation method for digital storage and analysis of heart and lung sounds according to claim 1, characterized in that: When abnormal cardiopulmonary sound signals are detected, an abnormality report is automatically generated and a reminder message is sent to the doctor via a mobile device. Based on the historical records and analysis results of the cardiopulmonary sound data, personalized health management suggestions and treatment plans are provided, and an AI-based predictive model is included to identify potential health problems in advance.

7. An auscultation system for digital storage and analysis of heart and lung sounds, applicable to the auscultation method for digital storage and analysis of heart and lung sounds as claimed in any one of claims 1 to 6, characterized in that: include: Sound pickup module, analog-to-digital conversion module, signal preprocessing module, microcontroller unit, storage module, wireless transmission module, playback module, deep learning module, data encryption module and remote server; The output end of the sound pickup module is connected to the input end signal of the analog-to-digital conversion module, the output end of the analog-to-digital conversion module is connected to the input end signal of the signal preprocessing module, the output end of the signal preprocessing module is connected to the input end signal of the microcontroller unit, the output end of the microcontroller unit is respectively connected to the input end signal of the storage module, the wireless transmission module and the playback module, and the output end of the wireless transmission module is connected to the input end signal of the remote server; The signal preprocessing module includes a deep learning module, which is used for noise identification and removal. The wireless transmission module includes a data encryption module, which is used for encryption processing during data transmission.

8. The auscultation system for digital storage and analysis of heart and lung sounds according to claim 7, characterized in that: The sound pickup module is used to collect the patient's cardiopulmonary sound signals and transmit them to the analog-to-digital conversion module; The analog-to-digital conversion module is used to convert analog cardiopulmonary sound signals into digital signals; The signal preprocessing module includes an adaptive filter for dynamically adjusting filter parameters according to environmental noise, and a bandpass filter for limiting the frequency range of the audio signal.

9. The auscultation system for digital storage and analysis of heart and lung sounds according to claim 7, characterized in that: The deep learning module is used to identify and remove environmental noise; The microcontroller unit includes a fast Fourier transform analysis function for extracting the characteristic spectrum of the heart and lung sounds; The storage module is used to store the analysis results in a local storage device in a digital format; The wireless transmission module is used to transmit the digital signal of cardiopulmonary sound to a remote server via Wi-Fi, and includes a data encryption module to ensure the security during data transmission.

Images