Method and application of intelligent cardiac pacemaker equipment based on biofeedback regulation

Abstract

The invention relates to the technical field of medical instruments, and discloses a method and application of intelligent cardiac pacemaker equipment based on biofeedback regulation, the intelligent cardiac pacemaker equipment based on biofeedback regulation comprises a shell, the interior of the shell is provided with a pulse generator, the pulse generator is used for conducting an electrical stimulation signal to cardiac tissue, and the pulse generator is connected with a cathode and an anode through a control module; the storage battery is mounted on one side in the shell and is used for supplying power to the pulse generator; the control module comprises an information acquisition module used for acquiring physiological information of a user in real time; the signal processing module is used for receiving and preprocessing the physiological signals; and the intelligent regulation and control module is combined with the output data of the signal processing module to regulate and control the working state of the pulse generator. By integrating the information acquisition module, the signal processing module and the intelligent regulation and control module, physiological information of a user is monitored in real time, and the working state of the pulse generator is accurately regulated, so that effective electrical stimulation on the heart is realized, and normal physiological rhythm of the heart is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a method and application of an intelligent cardiac pacemaker device based on biofeedback regulation. Background Art

[0002] A pacemaker is an important medical device, mainly used to treat patients with abnormal heart rhythm. By providing a stable electrical stimulation signal, a pacemaker can effectively regulate the heart's beating frequency, help patients maintain a normal heart rhythm, prevent the heart from beating too slowly or irregularly, and ensure the normal circulation of blood. It is widely used in patients with heart disease or other conditions that cause abnormal heart rhythm. Pacemakers can replace the heart's work when the heart's autonomous function is insufficient, ensuring the patient's life safety and quality of life.

[0003] Most existing pacemakers are implanted in the human body, with electrodes directly contacting the heart tissue, sending electrical stimulation signals to the heart, causing the heart muscles to contract, thereby achieving the effect of regulating the heartbeat.

[0004] Existing pacemakers lack the ability to fully analyze and dynamically respond to real-time physiological signals and can often only provide a fixed stimulation frequency, so they cannot adjust according to the patient's movement, emotions or other physiological changes. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method and application of an intelligent cardiac pacemaker device based on biofeedback regulation, which solves the problem in the prior art that the existing cardiac pacemakers lack the ability to comprehensively analyze and dynamically respond to real-time physiological signals, can only provide a fixed stimulation frequency, and cannot be adjusted according to the patient's movement, emotions or other physiological changes.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent cardiac pacemaker based on biofeedback regulation, comprising:

[0007] A housing, in which a pulse generator is installed for transmitting electrical stimulation signals to cardiac tissue, wherein the pulse generator is connected to the cathode and the anode through a control module;

[0008] A battery, which is installed on one side of the housing and is used to supply power to the pulse generator;

[0009] The control module includes:

[0010] An information collection module, which is used to collect the user's physiological information in real time;

[0011] A signal processing module, used for receiving physiological signals and performing pre-processing;

[0012] The intelligent control module controls the working state of the pulse generator in combination with the output data of the signal processing module.

[0013] Preferably, the information collection module includes:

[0014] An ECG sensor, which is located at the end of the anode and is used to collect changes in the user's heart rhythm;

[0015] A blood oxygen sensor, which is located on one side of the housing and is used to collect the user's blood oxygen data;

[0016] A breathing sensor, which is located on the other side of the housing and is used to collect the user's breathing and lung activity data;

[0017] A blood pressure sensor, which is located on one side of the housing and is used to collect blood pressure data of the user;

[0018] The acceleration sensor is located inside the housing and is used to collect the user's movement conditions.

[0019] Preferably, the signal processing module is used to receive the physiological signal collected by the information collection module to perform noise elimination, signal filtering and feature extraction. The noise elimination adopts an adaptive filter model and uses the following formula:

[0020] y[n]=x[n]-μ·e[n]

[0021] Where y[n] is the output signal, x[n] is the input signal, μ is the step size factor, and e[n] is the error signal;

[0022] The signal filtering uses FIR filter to smooth the signal, and the formula is:

[0023]

[0024] Among them, y[n] is the output signal, M is the order of the filter, and x[nk] is the input signal;

[0025] The feature extraction extracts signal features through wavelet transform, and the formula is:

[0026]

[0027] Among them, C j,k is the wavelet coefficient, f(t) is the input signal, ψ j,k (t) is the wavelet basis function.

[0028] Preferably, the intelligent control module generates a pacing frequency control signal based on a multi-source data fusion algorithm and combines the output data of the signal processing module, and uses a model based on the Bayesian algorithm for inference, through the formula:

[0029]

[0030] Among them, P(H|E) is the probability of observing physiological signal E when physiological signal E is observed, P(E|H) is the probability of observing physiological signal E when hypothesis H is true, P(H) is the prior probability of hypothesis H, and P(E) is the marginal probability of signal E.

[0031] Preferably, the training data of the Bayesian algorithm is based on physiological data collected over a long period of time, and the model optimizes weights through a back-propagation algorithm so that the output of each neuron is calculated by the following formula:

[0032] a (l) =f(z (l) )=f(W (l) a (l-1) +b (l) )

[0033] Among them, a (l) It represents the signal processed by the activation function, which is passed to the next layer as the output of this layer. (l) ) is the activation function, which is used to introduce nonlinear characteristics, z (l) represents the total input received by the neurons in this layer when calculating the next step, W (l) represents the weight matrix of the lth layer, a (l-1) Represents the output of the previous layer of neurons as the input of the current layer of neurons, b (l) Represents the bias term of the lth layer.

[0034] Preferably, the control module also includes:

[0035] Remote monitoring module for transmitting physiological data to external devices in real time;

[0036] The adaptive learning module is used to dynamically optimize the working parameters of the pacemaker based on historical data, monitor and learn the patient's physiological changes over a long period of time, and form an adaptive adjustment mechanism.

[0037] Preferably, the remote monitoring module realizes secure data transmission through an encrypted communication protocol, and uses the following formula to calculate the data transmission delay:

[0038]

[0039] Where D is the amount of data transmitted, C is the control overhead of the communication protocol, and R is the actual transmission rate;

[0040] The adaptive learning module dynamically adjusts the pacing frequency using historical physiological data and adjusts the patient's heart rate using the following formula:

[0041] f new =f old+Δf·(1+β)

[0042] Among them, f new is the new frequency, f old is the original frequency, Δf is the adjustment increment, and β is the response coefficient, which represents the patient's sensitivity to frequency changes.

[0043] The method for using the above device comprises the following steps:

[0044] A: The information acquisition module collects the patient's physiological signals in real time and transmits them to the signal processing module;

[0045] B: The signal processing module receives and pre-processes the physiological signals;

[0046] C: The intelligent control module performs data fusion on the data processed by the signal processing module and generates personalized pacing frequency control instructions according to the acquired physiological signals;

[0047] D: The remote monitoring module uploads physiological data to the cloud and performs real-time monitoring and remote control through the doctor platform.

[0048] Preferably, in step C, a deep learning algorithm is used to analyze the patient's long-term physiological data, and the model output is generated by the following formula:

[0049] y=f(Wx+b)

[0050] Among them, y is the model output, W is the weight matrix, x is the input feature, b is the bias term, and f is the activation function, which is used to enhance the nonlinear fitting ability of the model;

[0051] In step D, an abnormal event notification mechanism is used. When the physiological signal exceeds the preset threshold, the following formula is used to determine and trigger an alarm:

[0052]

[0053] Among them, S t is the current physiological signal value, T is the upper threshold, L is the lower threshold, if S t If it exceeds T or falls below L, an alarm is triggered.

[0054] The above equipment is used for long-term monitoring and treatment of heart disease patients.

[0055] Working principle: When in use, the anode is installed on the inner wall of the right atrium or right ventricle, and the cathode is installed at the far end of the heart, opposite to the position of the anode. After the device is installed in the patient's body and in operation, the pulse generator generates an electrical stimulation signal based on the received physiological signal, and sends electrical stimulation to the heart through the anode to promote the normal rhythm of the heart. The electrical stimulation signal is transmitted between the anode and the heart, stimulating the electrophysiological activity of the heart tissue, thereby stimulating the heart. The sensor in the information acquisition module monitors the heart's electrical activity, blood oxygen level, breathing, blood pressure, and movement status and other physiological data in real time. The signal processing module performs noise elimination, signal filtering, and feature extraction on these data, while the intelligent control module generates personalized pacing frequency control signals based on the output data of the signal processing module using a multi-source data fusion algorithm, and infers through the Bayesian algorithm to dynamically adjust the output of the pulse generator to ensure that the heart receives appropriate stimulation. The remote monitoring module uploads the physiological data to the external device in real time, and the monitoring module uses an encrypted communication protocol to achieve secure data transmission during operation, ensuring real-time update and privacy protection of physiological data. By continuously monitoring the patient's physiological changes, the purpose of timely adjusting the parameters of the pulse generator is achieved.

[0056] The present invention provides a method and application of an intelligent cardiac pacemaker device based on biofeedback regulation, which has the following beneficial effects:

[0057] 1. The present invention integrates an information acquisition module, a signal processing module and an intelligent control module to monitor the user's physiological information in real time and accurately adjust the working state of the pulse generator, thereby achieving effective electrical stimulation of the heart and ensuring that the heart maintains a normal physiological rhythm.

[0058] 2. The present invention adopts a multi-source data fusion algorithm combined with a Bayesian algorithm for intelligent regulation, so that the pacing frequency can be dynamically adjusted according to the patient's physiological changes, providing a personalized treatment plan and enhancing the adaptability and flexibility of the pacemaker.

[0059] 3. If the remote monitoring module of the present invention can transmit physiological data to an external device in real time, it is convenient for doctors to monitor and control, ensure that the patient's health management and data privacy are protected through encrypted communication protocols, and improve the safety and reliability of medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a schematic diagram of the three-dimensional structure of the present invention;

[0061] Figure 2 It is a front cross-sectional view of the housing of the present invention;

[0062] Figure 3 for Figure 2 A in the enlarged view;

[0063] Figure 4 It is a system structure diagram of the present invention.

[0064] Among them, 1. Shell; 2. Pulse generator; 3. Anode; 4. Cathode; 5. Control module; 51. ECG sensor; 52. Blood oxygen sensor; 53. Respiration sensor; 54. Blood pressure sensor; 55. Acceleration sensor; 6. Battery. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Please see attached Figure 1 -Attached Figure 4 The embodiment of the present invention provides an intelligent cardiac pacemaker based on biofeedback regulation, including: a shell 1, in which a pulse generator 2 is installed, which is used to transmit electrical stimulation signals to cardiac tissue, and the pulse generator 2 is connected to the cathode 4 and the anode 3 through a control module 5; a battery 6, which is installed on one side of the shell 1 and is used to supply power to the pulse generator 2; the control module 5 includes: an information acquisition module, which is used to collect the user's physiological information in real time; a signal processing module, which is used to receive and pre-process physiological signals; an intelligent control module, which controls the working state of the pulse generator 2 in combination with the output data of the signal processing module.

[0067] In the present invention, a pulse generator 2 is installed inside the housing 1. The main function of the pulse generator 2 is to transmit the electrical stimulation signal to the heart tissue. The pulse generator 2 is connected to the cathode 4 and the anode 3 through the control module 5 to ensure that the current can flow smoothly in the heart. In order to provide continuous power, a battery 6 is installed on one side inside the housing 1, which is specifically used to power the pulse generator 2 to ensure that it will not be interrupted during the entire working process;

[0068] The control module 5 includes an information acquisition module, which can collect the user's physiological information in real time to ensure that the system can obtain the latest data on the patient's health status. The functions of the information acquisition module include monitoring heart rate, blood oxygen level, respiratory rate and other physiological parameters through sensors. The signal processing module is responsible for receiving physiological signals obtained from the information acquisition module and preprocessing these signals, including noise elimination, signal filtering and feature extraction, to improve the accuracy and reliability of the signals;

[0069] At the same time, the intelligent control module is the core part of the system. It combines the output data of the signal processing module to intelligently control the working state of the pulse generator 2. By analyzing the patient's physiological signals, the intelligent control module can dynamically generate electrical stimulation signals suitable for the patient's individual needs, thereby effectively maintaining the normal rhythm of the heart and ensuring the health and safety of the patient. At the same time, it realizes efficient biofeedback regulation, providing heart disease patients with more advanced and personalized treatment options.

[0070] The ECG sensor 51 is located at the end of the anode 3 and is used to collect the user's heart rhythm changes; the blood oxygen sensor 52 is located on one side of the shell 1 and is used to collect the user's blood oxygen data; the breathing sensor 53 is located on the other side of the shell 1 and is used to collect the user's breathing and lung activity data; the blood pressure sensor 54 is located on one side of the shell 1 and is used to collect the user's blood pressure data; the acceleration sensor 55 is located inside the shell 1 and is used to collect the user's movement conditions.

[0071] In the present invention, the ECG sensor 51 is located at the end of the anode 3, and is mainly used to collect the user's heart rhythm changes in real time. The sensor adopts an electrocardiogram sensor module of model AD8232, which has the characteristics of high sensitivity and low power consumption, and can accurately capture the electrocardiogram signal and provide real-time heart rate data, thereby supporting the electrical stimulation regulation of the pulse generator 2;

[0072] The blood oxygen sensor 52 is installed on one side of the housing 1. The MAX30100 blood oxygen sensor 52 module is used. It combines the photoelectric volumetric pulse wave technology and can effectively measure the blood oxygen saturation (SpO2) and heart rate. It has the advantages of strong anti-interference ability and fast response, and is suitable for applications in dynamic environments.

[0073] The breathing sensor 53 is located on the other side of the housing 1 and uses a MS5837-30BA air pressure sensor to measure the pressure changes in the chest cavity to calculate the user's breathing frequency and lung activity. It has the characteristics of high accuracy and fast response and can effectively monitor the user's breathing state;

[0074] The blood pressure sensor 54 is also located on one side of the housing 1. The MCP3208 blood pressure monitoring module is selected. It has the characteristics of high precision and low power consumption. It can collect the user's blood pressure data in real time to ensure that the pacemaker can refer to accurate blood pressure information during the regulation process.

[0075] The acceleration sensor 55 is located inside the housing 1 and uses a three-axis accelerometer module of model ADXL345, which can monitor the user's movement and posture changes. The sensor has the characteristics of low power consumption and high precision, and is suitable for real-time monitoring in a mobile environment;

[0076] Therefore, through the comprehensive application of the above sensors, the intelligent pacemaker can monitor the patient's physiological state in all aspects and provide important data support for subsequent intelligent regulation, thereby ensuring heart health and the effectiveness of treatment.

[0077] The signal processing module is used to receive the physiological signals collected by the information acquisition module for noise elimination, signal filtering and feature extraction. The noise elimination adopts an adaptive filter model using the following formula:

[0078] y[n]=x[n]-μ·e[n]

[0079] Where y[n] is the output signal, x[n] is the input signal, μ is the step size factor, and e[n] is the error signal;

[0080] Signal filtering uses FIR filter to smooth the signal, the formula is:

[0081]

[0082] Among them, y[n] is the output signal, M is the order of the filter, and x[nk] is the input signal;

[0083] Feature extraction extracts signal features through wavelet transform, the formula is:

[0084]

[0085] Among them, C j,k is the wavelet coefficient, f(t) is the input signal, ψ j,k (t) is the wavelet basis function.

[0086] The intelligent control module generates a pacing frequency control signal based on a multi-source data fusion algorithm and combines the output data of the signal processing module. It uses a model based on the Bayesian algorithm for inference, using the formula:

[0087]

[0088] Among them, P(H|E) is the probability of observing physiological signal E when physiological signal E is observed, P(E|H) is the probability of observing physiological signal E when hypothesis H is true, P(H) is the prior probability of hypothesis H, and P(E) is the marginal probability of signal E.

[0089] In the present invention, the signal processing module is responsible for receiving physiological signals from the information acquisition module and conducting in-depth analysis of these signals to improve the reliability and accuracy of the signals. First, the module implements noise elimination and adopts an adaptive filter model. This method can effectively remove random noise and interference in the signal, ensuring the clarity and effectiveness of the signal used in subsequent processing;

[0090] After noise elimination, the signal filtering process uses a finite impulse response (FIR) filter to smooth the signal. This process aims to reduce the volatility of the signal and improve the stability of the signal, thereby providing more accurate basic data for further feature extraction.

[0091] Feature extraction is performed through wavelet transform technology, which can effectively capture the instantaneous characteristics and frequency domain information in the signal. This method can provide multi-resolution analysis when extracting signal features, thereby identifying key features and patterns in physiological signals, providing rich information basis for subsequent decision-making of the intelligent control module;

[0092] The intelligent control module uses a multi-source data fusion algorithm and combines the clear data output by the signal processing module to generate a personalized pacing frequency control signal. Through inference based on the Bayesian algorithm model, the module can evaluate the correlation between the physiological state and the hypothetical conditions in real time when observing physiological signals, thereby forming an intelligent control of the patient's cardiac stimulation. This process ensures that the pacemaker can dynamically adjust the output according to the patient's actual physiological changes, improving the accuracy and effectiveness of treatment.

[0093] The training data of the Bayesian algorithm is based on physiological data collected over a long period of time. The model optimizes the weights through the back-propagation algorithm so that the output of each neuron is calculated by the following formula:

[0094] a (l) =f(z (l) )=f(W (l) a (l-1) +b (l) )

[0095] Among them, a (l) It represents the signal processed by the activation function, which is passed to the next layer as the output of this layer. (l) ) is the activation function, which is used to introduce nonlinear characteristics, z (l) represents the total input received by the neurons in this layer when calculating the next step, W (l) represents the weight matrix of the lth layer, a (l-1) Represents the output of the previous layer of neurons as the input of the current layer of neurons, b (l) Represents the bias term of the lth layer.

[0096] In the present invention, the training data of the Bayesian algorithm relies on physiological data collected over a long period of time. These data provide the model with rich sample information, ensuring that the algorithm can accurately reflect the patient's physiological state and its changing trends. By analyzing historical data, the Bayesian algorithm can learn the correlation between different physiological signals and cardiac stimulation, thereby providing a basis for personalized pacing frequency regulation, and uses a back-propagation algorithm to optimize the weights of neurons during the model training process. The back-propagation algorithm calculates the error and feeds it back to each layer of neurons, adjusting the weights layer by layer, thereby continuously improving the prediction accuracy of the model. This process ensures that the signal output by each neuron can be accurately passed to the next layer after being processed by the activation function, and has a positive impact on the learning ability of the overall network;

[0097] In addition, the introduction of the activation function provides the model with nonlinear characteristics, enabling it to capture complex physiological signal patterns. This nonlinear characteristic enables the model to not only process linear relationships, but also identify more complex interactions and changes in physiological data, thereby enhancing the adaptability and robustness of the model in the face of diverse physiological signals. Therefore, through these mechanisms, the intelligent control module can generate accurate pacing frequency control signals based on input signals and learned knowledge to adapt to the patient's real-time physiological needs, thereby achieving effective cardiac stimulation and improving the treatment effect. At the same time, it improves the intelligence level of the intelligent pacemaker, enabling it to better meet the medical needs of individual patients.

[0098] The control module 5 also includes:

[0099] The remote monitoring module is used to transmit physiological data to external devices in real time. The adaptive learning module is used to dynamically optimize the working parameters of the pacemaker based on historical data, monitor and learn the patient's physiological changes over a long period of time, and form an adaptive adjustment mechanism.

[0100] The remote monitoring module uses an encrypted communication protocol to achieve secure data transmission and uses the following formula to calculate the data transmission delay:

[0101]

[0102] Among them, d is the amount of data transmitted, C is the control overhead of the communication protocol, and R is the actual transmission rate;

[0103] The adaptive learning module uses historical physiological data to dynamically adjust the pacing frequency and the patient's heart rate using the following formula:

[0104] f new =f old +Δf·(1+β)

[0105] Among them, f new is the new frequency, f oldis the original frequency, Δf is the adjustment increment, and β is the response coefficient, which represents the patient's sensitivity to frequency changes.

[0106] In the present invention, the control module 5 also includes a remote monitoring module and an adaptive learning module. The main function of the remote monitoring module is to transmit the physiological data collected in real time to an external device to ensure that doctors and medical teams can obtain the patient's health information in a timely manner. Through the encrypted communication protocol, not only the data is transmitted securely, but also the privacy of the patient is effectively protected, avoiding the risks and leakage that may be encountered during the data transmission process;

[0107] The adaptive learning module focuses on dynamically optimizing the working parameters of the pacemaker based on historical physiological data. This module can form an adaptive adjustment mechanism by monitoring and learning the patient's physiological changes for a long time. It can analyze the changes in the patient's physiological signals, identify specific patterns, and automatically adjust the pacing frequency according to these patterns to meet the patient's needs. In this process, the adaptive learning module can generate new pacing frequency settings through the analysis of historical data to optimize the patient's heart rate. This module will take into account the patient's sensitivity to frequency changes, so that each adjustment can be more in line with the patient's actual physiological state, thereby improving the treatment effect and the patient's quality of life. Therefore, the combination of the remote monitoring module and the adaptive learning module not only enhances the real-time monitoring capability of the intelligent pacemaker, but also improves its ability to respond to the individual needs of patients, forming a more intelligent and efficient medical device.

[0108] The present invention provides a method for using the above device, comprising the following steps:

[0109] A: The information acquisition module collects the patient's physiological signals in real time and transmits them to the signal processing module;

[0110] B: The signal processing module receives and pre-processes the physiological signals;

[0111] C: The intelligent control module performs data fusion on the data processed by the signal processing module and generates personalized pacing frequency control instructions according to the acquired physiological signals;

[0112] D: The remote monitoring module uploads physiological data to the cloud and performs real-time monitoring and remote control through the doctor platform.

[0113] In step C, a deep learning algorithm is used to analyze the patient's long-term physiological data and generate the model output using the following formula:

[0114] y=f(Wx+b)

[0115] Among them, y is the model output, W is the weight matrix, x is the input feature, b is the bias term, and f is the activation function, which is used to enhance the nonlinear fitting ability of the model;

[0116] Adopting abnormal event notification mechanism, when the physiological signal exceeds the preset threshold, the following formula is used to judge and trigger the alarm:

[0117]

[0118] Among them, S t is the current physiological signal value, T is the upper threshold, L is the lower threshold, if S t If it exceeds T or falls below L, an alarm is triggered.

[0119] In step A, the information acquisition module collects the patient's physiological signals in real time, including important physiological parameters such as heart rate, blood oxygen level, and respiratory rate. The accurate collection of these data provides a basis for subsequent analysis, ensuring that the system can obtain real and reliable information;

[0120] In step B, the signal processing module receives the collected physiological signals and performs preprocessing. This process includes noise elimination, signal smoothing, and feature extraction to improve the quality and usability of the signal. After processing, the signal will be more representative, making subsequent analysis more accurate;

[0121] Step C involves the intelligent control module fusing the data output by the signal processing module. This module uses a deep learning algorithm to analyze the patient's long-term physiological data, identify patterns under different physiological states, and generate personalized pacing frequency control instructions. This intelligent adjustment capability ensures that the pacemaker can perform optimal electrical stimulation based on the patient's real-time condition to maintain normal heart rhythm;

[0122] In step D, the remote monitoring module uploads real-time physiological data to the cloud, and doctors can conduct real-time monitoring and remote control through a dedicated platform. This mechanism enables medical staff to understand the patient's health status at the first time, adjust the treatment plan in time, and enhance the patient's safety;

[0123] Throughout the entire process, the abnormal event notification mechanism used can promptly detect whether physiological signals exceed the preset threshold. When an abnormal signal is detected, the system automatically triggers an alarm to notify doctors or relevant personnel for further intervention. This function not only improves the response speed, but also ensures the health and safety of patients.

[0124] The present invention is applied to long-term monitoring and treatment of patients with heart disease.

[0125] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent cardiac pacemaker based on biofeedback regulation, characterized in that: include: A housing (1) having a pulse generator (2) installed therein for transmitting electrical stimulation signals to cardiac tissue, wherein the pulse generator (2) is connected to a cathode (4) and an anode (3) via a control module (5); A storage battery (6) is installed on one side of the housing (1) and is used to supply power to the pulse generator (2); The control module (5) comprises: An information collection module, which is used to collect the user's physiological information in real time; A signal processing module, used for receiving physiological signals and performing pre-processing; The intelligent control module controls the working state of the pulse generator (2) in combination with the output data of the signal processing module.

2. The intelligent cardiac pacemaker based on biofeedback regulation according to claim 1, characterized in that: The information collection module includes: An ECG sensor (51), which is located at the end of the anode (3) and is used to collect changes in the user's heart rhythm; A blood oxygen sensor (52), which is located on one side of the housing (1) and is used to collect blood oxygen data of the user; A breathing sensor (53), which is located on the other side of the housing (1) and is used to collect the user's breathing and lung activity data; A blood pressure sensor (54), located on one side of the housing (1) and used to collect blood pressure data of a user; An acceleration sensor (55) is located inside the housing (1) and is used to collect movement conditions of the user.

3. The intelligent cardiac pacemaker based on biofeedback regulation according to claim 2, characterized in that: The signal processing module is used to receive the physiological signal collected by the information collection module to perform noise elimination, signal filtering and feature extraction. The noise elimination adopts an adaptive filter model and uses the following formula: y[n]=x[n]-μ·e[n] Where y[n] is the output signal, x[n] is the input signal, μ is the step size factor, and e[n] is the error signal; The signal filtering uses FIR filter to smooth the signal, and the formula is: Among them, y[n] is the output signal, M is the order of the filter, and x[nk] is the input signal; The feature extraction extracts signal features through wavelet transform, and the formula is: Among them, C j,k is the wavelet coefficient, f(t) is the input signal, ψ j,k (t) is the wavelet basis function.

4. The intelligent cardiac pacemaker based on biofeedback regulation according to claim 3, characterized in that: The intelligent control module generates a pacing frequency control signal based on a multi-source data fusion algorithm and the output data of the signal processing module, and uses a model based on the Bayesian algorithm for inference, through the formula: Among them, P(H|E) is the probability of observing physiological signal E when physiological signal E is observed, P(E|H) is the probability of observing physiological signal E when hypothesis H is true, P(H) is the prior probability of hypothesis H, and P(E) is the marginal probability of signal E.

5. The intelligent cardiac pacemaker based on biofeedback regulation according to claim 4, characterized in that: The training data of the Bayesian algorithm is based on long-term collected physiological data. The model optimizes the weights through the back-propagation algorithm so that the output of each neuron is calculated by the following formula: a (l) =f(z (l) )=f(W (l) a (l-1) +b (l) ) Among them, a (l) It represents the signal processed by the activation function, which is passed to the next layer as the output of this layer. (l) ) is the activation function, which is used to introduce nonlinear characteristics, z (l) represents the total input received by the neurons in this layer when calculating the next step, W (l) represents the weight matrix of the lth layer, a (l-1) Represents the output of the previous layer of neurons as the input of the current layer of neurons, b (l) Represents the bias term of the lth layer.

6. The intelligent cardiac pacemaker based on biofeedback regulation according to claim 1, characterized in that: The control module (5) further comprises: Remote monitoring module for transmitting physiological data to external devices in real time; The adaptive learning module is used to dynamically optimize the working parameters of the pacemaker based on historical data, monitor and learn the patient's physiological changes over a long period of time, and form an adaptive adjustment mechanism.

7. The intelligent cardiac pacemaker device based on biofeedback regulation according to claim 6, characterized in that: The remote monitoring module realizes secure data transmission through an encrypted communication protocol and uses the following formula to calculate the data transmission delay: Where D is the amount of data transmitted, C is the control overhead of the communication protocol, and R is the actual transmission rate; The adaptive learning module dynamically adjusts the pacing frequency using historical physiological data and adjusts the patient's heart rate using the following formula: f new =f old +Δf·(1+β) Among them, f new is the new frequency, f old is the original frequency, Δf is the adjustment increment, and β is the response coefficient, which characterizes the patient's sensitivity to frequency changes.

8. A method for using an intelligent cardiac pacemaker based on biofeedback regulation, based on the intelligent cardiac pacemaker based on biofeedback regulation according to any one of claims 1 to 7, characterized in that: The following steps are involved: A: The information acquisition module collects the patient's physiological signals in real time and transmits them to the signal processing module; B: The signal processing module receives and pre-processes the physiological signals; C: The intelligent control module performs data fusion on the data processed by the signal processing module and generates personalized pacing frequency control instructions according to the acquired physiological signals; D: The remote monitoring module uploads physiological data to the cloud and performs real-time monitoring and remote control through the doctor platform.

9. The method for using the intelligent cardiac pacemaker based on biofeedback regulation according to claim 8, characterized in that: In step C, a deep learning algorithm is used to analyze the patient's long-term physiological data, and the model output is generated by the following formula: y=f(Wx+b) Among them, y is the model output, W is the weight matrix, x is the input feature, b is the bias term, and f is the activation function, which is used to enhance the nonlinear fitting ability of the model; In step D, an abnormal event notification mechanism is used. When the physiological signal exceeds the preset threshold, the following formula is used to determine and trigger an alarm: Among them, S t is the current physiological signal value, T is the upper threshold, L is the lower threshold, if S t If it exceeds T or falls below L, an alarm is triggered.

10. The intelligent cardiac pacemaker device based on biofeedback regulation according to claim 1, characterized in that: The device is used for long-term monitoring and treatment of heart disease patients.

Images