Pacemaker program control data electronic acquisition, storage and management system

Abstract

The invention relates to the technical field of pacemaker control, and discloses a pacemaker program control data electronic acquisition, storage and management system, which comprises a data acquisition module, a data preprocessing module, a data analysis module and a feedback mechanism module, the data preprocessing module is used for preprocessing the first feature sequence and performing feature extraction to obtain a second feature sequence; the data analysis module is used for performing real-time optimization on the pacemaker feature data at a local end and performing long-term optimization at a cloud end; and the feedback mechanism module is used for coordinating local end optimization and cloud end optimization to form a closed-loop regulation and control system. According to the invention, through a cooperative closed-loop mechanism of real-time optimization of the local end and long-term optimization of the cloud end, in combination with fuzzy control, a gating circulation unit and reinforcement learning, personalized pacemaker parameter regulation and control are realized, and the stability, adaptability and intelligent level of the pacemaker are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of pacemaker control, and in particular relates to an electronic acquisition, storage and management system for pacemaker program control data. Background Art

[0002] Pacemaker is an important cardiac implantable medical device, widely used to treat heart diseases such as arrhythmia. Traditional pacemaker control parameters (such as pacing threshold, pacing frequency, sensing sensitivity, etc.) are usually manually adjusted by doctors during follow-up, which makes it difficult to achieve dynamic adaptation to the patient's physiological state. In addition, the existing pacemaker data acquisition and management system mainly relies on manual reading and storage, lacks efficient data analysis and intelligent optimization methods, and is difficult to meet the needs of personalized treatment. At present, some studies have proposed pacemaker remote monitoring technology, so that pacemaker data can be regularly uploaded to the cloud for analysis. However, the existing technology has the following shortcomings: 1. Poor real-time performance, cloud data processing has delays, and cannot quickly respond to changes in the patient's physiological state; 2. Lack of adaptive optimization, the adjustment of pacing parameters still depends on manual intervention by doctors, and cannot automatically make intelligent adjustments based on the patient's physiological data; 3. Low data utilization. Although some systems can collect and store patient physiological data, they lack effective analysis methods and cannot fully mine the value of data. Summary of the invention

[0003] The present invention provides an electronic acquisition, storage and management system for pacemaker programmed data, which solves the technical problems in related technologies such as deficiencies in real-time, adaptive optimization and data utilization, and difficulty in achieving rapid response, intelligent adjustment and efficient data analysis.

[0004] The present invention provides a pacemaker program-controlled data electronic collection, storage and management system, including a data collection module, a data preprocessing module, a data analysis module and a feedback mechanism module: A data acquisition module, used to collect pacemaker characteristic data, wherein the pacemaker characteristic data includes: pacing threshold, pacing frequency, sensing sensitivity, pacing mode, output energy, heart rate, heart rate variability, QT interval and activity level; Wherein, the pacemaker characteristic data is collected at a first preset time interval within a first preset time period to obtain a first characteristic sequence; The j-th sequence unit of the first feature sequence represents the pacemaker feature data collected at the j-th time point; A data preprocessing module, used for preprocessing the first feature sequence and performing feature extraction to obtain a second feature sequence; A data analysis module, used for real-time optimization of pacemaker characteristic data at the local end and long-term optimization at the cloud end, wherein the local end represents the pacemaker device and the cloud end represents the remote server, and the physiological signal of the pacemaker is analyzed at the local end by using a fuzzy control algorithm, and the first control parameter is adjusted in real time based on the first preset rule; the cloud end constructs a physiological state prediction model based on a gated cyclic unit, analyzes the second characteristic sequence, and optimizes the first control parameter of the pacemaker in combination with a reinforcement learning algorithm; wherein the physiological signal includes: heart rate, heart rate variability, QT interval and activity level, and the first control parameter includes: pacing threshold, pacing frequency, and sensory sensitivity; The feedback mechanism module is used to coordinate local optimization and cloud optimization to form a closed-loop control system.

[0005] Furthermore, the pacing modes include: single-chamber pacing, dual-chamber pacing, and adaptive pacing, and are represented by numerical codes, the heart rate variability is represented by the standard deviation of the heart rate, and the activity level is represented by the numerical code of acceleration.

[0006] Furthermore, the first feature sequence is preprocessed, and the specific steps include: S201, using the mean value in the first feature sequence to fill in the missing values; S202, performing denoising processing on the first characteristic sequence using a bandpass filtering method; S203, based on standard deviation and 3 The rule performs statistical anomaly detection on the first feature sequence, filters out outliers, and uses linear interpolation to perform replacement processing.

[0007] Furthermore, the specific steps of feature extraction include: S301, extracting a pacing frequency-energy comprehensive index feature according to the first feature sequence, the calculation formula of the pacing frequency-energy comprehensive index feature is: ,in, Indicates the pacing frequency-energy comprehensive index characteristics, Indicates the current pacing frequency. Indicates the current output energy of the pacemaker. Indicates the current pacing threshold, Indicates the current perception sensitivity. Represents a minimum value between 0 and 1. represents the number of acquisition time points within the first preset time period, i represents the index of the time point, represents the pacing frequency at the i-th time point, represents the average pacing frequency at T time points in the first preset time period; S302, extracting a heartbeat stability coefficient feature according to the first feature sequence, wherein the calculation formula of the heartbeat stability coefficient feature is: ,in, Represents the characteristics of the heart beat stability coefficient, represents a first preset time interval, represents the heart rate at the i-th time point, represents the mean heart rate at T time points in the first preset time period, Indicates the pacing mode, represents the baseline perception sensitivity, S represents the perception sensitivity, represents the QT change weight coefficient, represents the QT interval, Indicates the standard QT value; S303, extracting physiological recovery index features according to the first feature sequence, the calculation formula of the physiological recovery index features is: ,in, Represents the physiological recovery index characteristics, represents the heart rate at the i-1th time point, and represent the QT interval at the i-1th time point and the i-th time point, respectively. represents the activity level at the ith time point, represents the average activity level at T time points in the first preset time period; S304, concatenating the pacing frequency-energy comprehensive index feature, the heartbeat stability coefficient feature, and the physiological recovery index feature after the sequence unit of the first feature sequence, and normalizing them to obtain a second feature sequence.

[0008] Furthermore, the specific steps of the fuzzy control algorithm include: S401, input fuzzification step, multi-layer fuzzy mapping of physiological signals; S402, a fuzzy reasoning step, analyzing the adjustment trend of the first control parameter in a fuzzy logic framework according to a first preset rule, wherein the first preset rule is used to define the fuzzy adjustment boundaries corresponding to different physiological states; S403, a defuzzification step, after the adjustment trend is clear, converts the control quantity in the fuzzy space into an executable value and acts on the first control parameter of the pacemaker.

[0009] Furthermore, the specific steps of S402 include: S501, calculating the membership degree of the physiological signal based on the triangular membership function, where the membership degree represents the degree of belonging of the input variable in the division level; S502, calculating the activation degree of the rule triggered by the input variable according to the membership degree of the input variable; S503: Determine an adjustment trend of the first control parameter according to the activation degree of the rule.

[0010] Furthermore, the physiological state prediction model is constructed with the gated recurrent unit as the core, and the composition structure of the physiological state prediction model includes: an input layer, a feature extraction layer, and an output layer; wherein the input layer is used to input the second feature sequence; the feature extraction layer uses the gated recurrent unit to process the second feature sequence and extract cross-time step correlation features; the output layer is used to perform dimensionality reduction mapping on the extracted cross-time step correlation features, and finally generate a physiological health score.

[0011] Furthermore, a reinforcement learning model is constructed with the physiological health score as the core. The state variables of the reinforcement learning model include the parameters in the pacemaker characteristic data and the physiological health score. The action variables include the adjustment values ​​of the pacing threshold, pacing frequency and sensory sensitivity. The reward function is composed of the change value of the physiological health score and the adjustment cost of the first control parameter. During the training process, a deep deterministic policy gradient is used to optimize the first control parameter under different physiological states. The calculation formula of the reward function is:

[0012] ; in, represents the value of the reward function, represents the physiological health score at the current time step, represents the physiological health score of the previous time step, represents the first weight coefficient, , and denote the second weight coefficient, the third weight coefficient and the fourth weight coefficient respectively, Indicates the adjustment value of the pacing threshold. Indicates the adjustment value of the pacing frequency. Indicates the adjustment value of perception sensitivity.

[0013] Furthermore, the feedback mechanism module includes: local optimization feedback, cloud optimization feedback and closed-loop feedback mechanism. The local optimization feedback is adjusted in real time through the fuzzy control algorithm and the first preset rules, and the adjustment results are uploaded to the cloud regularly for long-term learning by the cloud; the cloud optimization feedback is used to output the physiological health score through the physiological state prediction model, and use reinforcement learning to optimize the first control parameter to obtain the optimization strategy, and push it to the local end; the closed-loop feedback mechanism specifically includes: local real-time optimization, local upload feedback, cloud long-term learning, cloud push optimization strategy and local update optimization strategy.

[0014] The beneficial effects of the present invention are as follows: the present invention constructs a collaborative closed-loop mechanism of local optimization and cloud optimization; a fuzzy control algorithm is used on the local side to achieve real-time optimization of pacing threshold, pacing frequency and sensory sensitivity; a physiological state prediction model is constructed on the cloud based on a gated cyclic unit, combined with reinforcement learning for long-term optimization, and optimization strategies are regularly pushed to the local side; this hierarchical optimization architecture can not only meet short-term response requirements, but also optimize personalized regulation based on long-term trends, thereby improving the stability and adaptability of the pacemaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a module schematic diagram of the electronic acquisition, storage and management system of pacemaker program-controlled data of the present invention. DETAILED DESCRIPTION

[0016] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the contents of this specification. Each example may omit, replace or add various processes or components as needed. In addition, the features described relative to some examples may also be combined in other examples.

[0017] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in one or more embodiments of the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in one or more embodiments of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0018] like Figure 1 As shown, the electronic acquisition, storage and management system of pacemaker program control data includes: The data acquisition module 101 is used to collect pacemaker characteristic data, wherein the pacemaker characteristic data includes: pacing threshold, pacing frequency, sensing sensitivity, pacing mode, output energy, heart rate, heart rate variability, QT interval and activity level; Specifically, the pacing threshold indicates the minimum voltage required for the pacemaker to stimulate heart contraction, and is an important parameter for determining the heart's sensitivity to electrical stimulation; the pacing frequency indicates the number of stimulation pulses the pacemaker sends out per minute, and directly reflects the intensity of the device's intervention in the heart's rhythm; the sensing sensitivity indicates the minimum threshold for the pacemaker to detect the heart's intrinsic electrical signals, and determines whether the device can accurately capture the heart's natural rhythm; the pacing mode indicates the pacemaker's pacing and sensing methods for the atria and ventricles, such as single-chamber, dual-chamber, or rate response modes, reflecting the device's control strategy; the output energy indicates how often the pacemaker sends out a pulse each time. The energy transmitted is usually measured in millijoules (mJ), which affects battery life and pacing effect; heart rate refers to the number of heart beats per minute, and is a basic physiological indicator for evaluating the working state of the heart; heart rate variability reflects the regulatory ability of the autonomic nervous system on the heart through the standard deviation of adjacent heartbeat intervals; QT interval refers to the time interval from the start of the Q wave to the end of the T wave in the electrocardiogram, reflecting the heart repolarization process, and abnormalities may indicate the risk of arrhythmia; activity level is measured by an accelerometer, reflecting the patient's exercise state and physical activity intensity, which is of great significance to rate-responsive pacing; Wherein, the pacemaker characteristic data is collected by the pacemaker at a first preset time interval within a first preset time period to obtain a first characteristic sequence; The j-th sequence unit of the first feature sequence represents the pacemaker feature data collected at the j-th time point; The data preprocessing module 102 is used to preprocess the first feature sequence and perform feature extraction to obtain a second feature sequence; The data analysis module 103 is used to optimize the characteristic data of the pacemaker in real time at the local end and in the cloud for long term optimization, wherein the local end represents the pacemaker device and the cloud represents the remote server. The physiological signal of the pacemaker is analyzed at the local end by using the fuzzy control algorithm, and the first control parameter is adjusted in real time based on the first preset rule; the cloud constructs a physiological state prediction model based on the gated cyclic unit, analyzes the second characteristic sequence, and optimizes the first control parameter of the pacemaker in combination with the reinforcement learning algorithm; wherein the physiological signal includes: heart rate, heart rate variability, QT interval and activity level, and the first control parameter includes: pacing threshold, pacing frequency, and sensing sensitivity; The feedback mechanism module 104 is used to coordinate local optimization and cloud optimization to form a closed-loop control system.

[0019] In one embodiment of the present invention, the pacing modes include: single-chamber pacing, dual-chamber pacing, and adaptive pacing, and are represented by numerical codes, for example, single-chamber pacing is coded as 1, dual-chamber pacing is coded as 2, and adaptive pacing is coded as 3. The heart rate variability is represented by the standard deviation of the heart rate, and the activity level is represented by the numerical code of acceleration. In one embodiment of the present invention, in order to ensure the consistency of pacemaker characteristic data and make it suitable for physiological state prediction models, all data need to be in unified units. Specifically, the unit of pacing threshold is millivolt, the unit of pacing frequency is times per minute, the unit of sensor sensitivity is millivolt, the unit of output energy is millijoule, the unit of heart rate is times per minute, the unit of heart rate variability is milliseconds, the unit of QT interval is milliseconds, and the unit of activity level is meters per second squared.

[0020] In one embodiment of the present invention, the first feature sequence is preprocessed, and the specific steps include: S201, using the mean value in the first feature sequence to fill in the missing values. Specifically, for each feature, the average value of all collected values ​​in the first preset time period is calculated, and then all missing values ​​are replaced with the average value, so as to ensure sequence continuity and data integrity; S202, using a bandpass filtering method to perform denoising on the first feature sequence, which can effectively remove noise caused by electromyographic noise, electromagnetic interference, etc., thereby improving signal clarity and accuracy of subsequent feature extraction; S203, based on standard deviation and 3 The rule performs statistical anomaly detection on the first feature sequence, screens out abnormal values, and uses linear interpolation to perform replacement processing. Specifically, the mean and standard deviation of the pacemaker feature data within the first preset time period are calculated to obtain 3 The data beyond the range are regarded as outliers and replaced by linear interpolation to ensure the smoothness and continuity of the first feature sequence.

[0021] In one embodiment of the present invention, the specific steps of feature extraction include: S301, extracting a pacing frequency-energy comprehensive index feature according to the first feature sequence, the calculation formula of the pacing frequency-energy comprehensive index feature is: ,in, It indicates the pacing frequency-energy comprehensive index characteristics. If FESI is too high, it means that the pacing frequency is high and the energy consumption is large, which may lead to energy waste and the sensing sensitivity needs to be optimized. If FESI is too low, it means that the pacing frequency of the pacemaker is low or the energy output is insufficient, which may lead to insufficient regulation of the patient's heart rhythm. Indicates the current pacing frequency. Indicates the current output energy of the pacemaker. Indicates the current pacing threshold, Indicates the current perception sensitivity. represents a minimum value between 0 and 1, preferably, Set to , represents the number of acquisition time points within the first preset time period, i represents the index of the time point, represents the pacing frequency at the i-th time point, represents the average pacing frequency at T time points in the first preset time period; S302, extracting a heartbeat stability coefficient feature according to the first feature sequence, wherein the calculation formula of the heartbeat stability coefficient feature is: ,in, Indicates the heart rate stability coefficient feature, which is used to measure the stability of the heart rate. If the HSF is too high, it means that the heart rate fluctuates greatly and the pacemaker's control effect is not stable enough. If the HSF is too low, it means that the heart rate is relatively stable and the pacemaker's control effect is good. represents a first preset time interval, represents the heart rate at the i-th time point, represents the mean heart rate at T time points in the first preset time period, Indicates the pacing mode, represents the baseline sensing sensitivity, i.e. the preset initial value of the pacemaker sensing sensitivity, S represents the sensing sensitivity, represents the QT change weight coefficient, represents the QT interval, It represents the standard QT value, that is, the QT interval value under normal physiological conditions; S303, extracting physiological recovery index features according to the first feature sequence, the calculation formula of the physiological recovery index features is: ,in, Represents the physiological recovery index feature, which is used to measure the patient's physiological adaptability. If the PRI is too high, it means that the patient's heart has a strong adaptability to physiological activities. If the PRI is too low, it means that the patient's heart has a poor adaptability. represents the heart rate at the i-1th time point, and represent the QT interval at the i-1th time point and the i-th time point, respectively. represents the activity level at the ith time point, represents the average activity level at T time points in the first preset time period; S304, concatenating the pacing frequency-energy comprehensive index feature, the heartbeat stability coefficient feature, and the physiological recovery index feature after the sequence unit of the first feature sequence, and normalizing them to obtain a second feature sequence.

[0022] In one embodiment of the present invention, the local end uses a fuzzy control algorithm to analyze the pacing threshold, pacing frequency and sensing sensitivity of the pacemaker, and implements real-time adjustment based on the first preset rule to optimize the physiological adaptability of the pacemaker and improve the patient's cardiac function stability.

[0023] In one embodiment of the present invention, the specific steps of the fuzzy control algorithm include: S401, input fuzzification step, perform multi-layer fuzzy mapping on physiological signals, specifically, divide the heart rate into three levels: low, normal and high, divide the heart rate variability into three levels: low, normal and high, divide the QT interval into three levels: short, normal and long, divide the activity level into four levels: rest, light activity, exercise and intense exercise, and fuzzify them to corresponding levels according to specific values ​​and actual conditions, which can enhance robustness and reduce computational complexity; S402, a fuzzy reasoning step, analyzing the adjustment trend of the first control parameter in a fuzzy logic framework according to a first preset rule, wherein the first preset rule is used to define the fuzzy adjustment boundaries corresponding to different physiological states; The first preset rule includes but is not limited to: When it is detected that the heart rate is higher than a first preset threshold and the heart rate variability decreases, the pacing frequency is reduced, preferably, the first preset threshold is 130 bpm; When it is detected that the heart rate is lower than a second preset threshold and the QT interval is prolonged, the pacing frequency is increased, preferably, the second preset threshold is 50 bpm; When it is detected that the QT interval is prolonged beyond a third preset threshold, lowering the pacing threshold to reduce overstimulation, preferably, the third preset threshold is 480ms; When it is detected that the heart rate is higher than a fourth preset threshold and the activity level is higher than a fifth preset threshold, the pacing frequency is increased to adapt to physiological needs, preferably, the fourth preset threshold is 100 bpm; S403, the defuzzification step, after the adjustment trend is clear, converts the control quantity in the fuzzy space into an executable value and acts on the first control parameter of the pacemaker to ensure the accuracy of execution and optimize the control output.

[0024] In one embodiment of the present invention, the specific steps of S402 include: S501, calculating the membership of the physiological signal based on the triangular membership function, the membership indicates the degree of belonging of the input variable in the division level, for example, the heart rate is 100bpm, the heart rate classification standard is: low: ,normal: ,high: , R represents the heart rate, for , at the "high" level, when the heart rate is 90, the membership is 0, when the heart rate is 120, the membership is 1, when the heart rate is 150 and above, the membership is 0, and the membership for a heart rate of 100 is: ; This step can eliminate the uncertainty of the data and make the pacemaker suitable for the individual differences of different patients; S502, calculate the activation degree of the rule triggered by the input variable according to the membership degree of the input variable, ensure decision flexibility, and prevent fixed threshold misjudgment. Specifically, for the input variables involved in the triggered rule, calculate their membership degree, and take the minimum value of the membership degree as the activation degree of the triggered rule. For example, the current heart rate input variable is 100bpm, and the current activity level input variable is 2 , the rule triggered by the input variable is: when the heart rate is detected to be higher than the fourth preset threshold and the activity level is higher than the fifth preset threshold, the pacing frequency is increased; the membership of high heart rate is calculated to be 0.33, and the membership of intense exercise is 0.67. By taking the minimum value operation, the activation degree of the triggered rule is obtained to be 0.33, indicating that the applicability of the rule is 33%; S503, determine the adjustment trend according to the activation degree of the rule, and be compatible with multiple rule conflicts. Specifically, synthesize the activated rule results to obtain a fuzzy adjustment trend, for example: the pacing frequency should be increased, the sensor sensitivity should be increased, and for multiple identical adjustment trends, take the trigger rule with a lower activation degree.

[0025] In one embodiment of the present invention, in S403, the adjustment trend of the first control parameter is converted into an accurate value, specifically including: multiplying the activation degree of the rule triggered by the input variable by the adjustment value corresponding to the preset adjustment trend to obtain the final adjustment value. For example, for the pacing frequency, the adjustment trend of the triggered rule is "increase the pacing frequency", the activation degree is 0.7, and the preset adjustment value of "increase the pacing frequency" is +3bpm, then the final adjustment value is: .

[0026] In one embodiment of the present invention, local optimization is based on real-time pacemaker characteristic data, combined with a fuzzy control algorithm, to achieve rapid adaptive adjustment of the first control parameter, ensuring the stability of the heart state and the real-time response of the pacemaker. Through input fuzzification, fuzzy reasoning and defuzzification steps, the adjustment of the first control parameter has high sensitivity and low computational burden, and is suitable for low-power devices. Local optimization avoids the delay problem of cloud data transmission, improves the instant adaptability of the patient's physiological state, and forms a closed loop with long-term optimization in the cloud, improving the robustness and personalized adaptability of the overall system.

[0027] In one embodiment of the present invention, the physiological state prediction model is constructed with the gated recurrent unit as the core, and the composition structure of the physiological state prediction model includes: an input layer, a feature extraction layer, and an output layer; wherein the input layer is used to input the second feature sequence; the feature extraction layer uses the gated recurrent unit to process the second feature sequence and extract cross-time step correlation features; the output layer is used to perform dimensionality reduction mapping on the extracted cross-time step correlation features, and finally generate a physiological health score.

[0028] In one embodiment of the present invention, the physiological state prediction model uses a mean square error function as a loss function. The mean square error function is used to calculate the average value of the square error between the predicted physiological health score and the actual physiological health score. The smaller the function result, the smaller the loss value, which means that the model prediction is more accurate. By minimizing the function result, the predicted physiological health score is close to the actual physiological health score.

[0029] In one embodiment of the present invention, a reinforcement learning model is constructed with the physiological health score as the core, the state variables of the reinforcement learning model include parameters in the pacemaker characteristic data and the physiological health score, the action variables include the adjustment values ​​of the pacing threshold, the pacing frequency and the sensory sensitivity, and the reward function is composed of the physiological health score change value and the first control parameter adjustment cost; during the training process, a deep deterministic policy gradient is used to optimize the first control parameter under different physiological states to maximize the physiological health score; according to the trained reinforcement learning model, the first control parameter is adjusted in real time at the pacemaker device end to optimize the patient's heart health state; wherein the calculation formula of the reward function is:

[0030] ; in, represents the value of the reward function, represents the physiological health score at the current time step, represents the physiological health score of the previous time step, represents the first weight coefficient, , and denote the second weight coefficient, the third weight coefficient and the fourth weight coefficient respectively, Indicates the adjustment value of the pacing threshold. Indicates the adjustment value of the pacing frequency. Indicates the adjustment value of perception sensitivity.

[0031] In one embodiment of the present invention, in the state variables of reinforcement learning, the physiological health score of the previous time step is used as the current state variable, and the action variable adopts a dynamic step adjustment mechanism. The step adjustment is based on the current physiological health score change trend to avoid the inadaptability caused by too fast parameter adjustment.

[0032] In one embodiment of the present invention, the cloud has stronger data storage and computing capabilities than the local end, and can mine long-term physiological trends through deep learning to improve the global optimality of parameter adjustment. In addition, the cloud uses a deep deterministic policy gradient optimization reinforcement learning strategy to provide a dynamic, adaptive personalized pacing solution, and periodically pushes the optimization strategy to the local end to improve the long-term adaptability and stability of the pacemaker.

[0033] In one embodiment of the present invention, the feedback mechanism module includes: local optimization feedback, cloud optimization feedback and closed-loop feedback mechanism. The local optimization feedback is adjusted in real time through the fuzzy control algorithm and the first preset rule, and the adjustment result is uploaded to the cloud regularly for long-term learning in the cloud; the cloud optimization feedback is used to output the physiological health score through the physiological state prediction model, and the first control parameter is optimized by reinforcement learning to obtain the optimization strategy, and push it to the local end; the closed-loop feedback mechanism specifically includes: local real-time optimization, local upload feedback, cloud long-term learning, cloud push optimization strategy and local update optimization strategy. The feedback mechanism reduces manual intervention, improves the intelligence level of the pacemaker, and enables patients to obtain accurate and efficient heart regulation solutions under different physiological conditions.

[0034] The above describes an embodiment of the present embodiment, but the present embodiment is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present embodiment, ordinary technicians in this field can also make many forms, all of which are within the protection of the present embodiment.

Claims

1. A system for electronically collecting, storing and managing pacemaker program control data, characterized in that: Including data acquisition module, data preprocessing module, data analysis module and feedback mechanism module: A data acquisition module, used to collect pacemaker characteristic data, wherein the pacemaker characteristic data includes: pacing threshold, pacing frequency, sensing sensitivity, pacing mode, output energy, heart rate, heart rate variability, QT interval and activity level; Wherein, the pacemaker characteristic data is collected at a first preset time interval within a first preset time period to obtain a first characteristic sequence; The j-th sequence unit of the first feature sequence represents the pacemaker feature data collected at the j-th time point; A data preprocessing module, used for preprocessing the first feature sequence and performing feature extraction to obtain a second feature sequence; A data analysis module, used for real-time optimization of pacemaker characteristic data at the local end and long-term optimization at the cloud end, wherein the local end represents the pacemaker device and the cloud end represents the remote server, and the physiological signal of the pacemaker is analyzed at the local end by using a fuzzy control algorithm, and the first control parameter is adjusted in real time based on the first preset rule; the cloud end constructs a physiological state prediction model based on a gated cyclic unit, analyzes the second characteristic sequence, and optimizes the first control parameter of the pacemaker in combination with a reinforcement learning algorithm; wherein the physiological signal includes: heart rate, heart rate variability, QT interval and activity level, and the first control parameter includes: pacing threshold, pacing frequency, and sensory sensitivity; The feedback mechanism module is used to coordinate local optimization and cloud optimization to form a closed-loop control system.

2. The electronic pacemaker program data collection, storage and management system according to claim 1, characterized in that: Pacing modes include single-chamber pacing, dual-chamber pacing, and adaptive pacing, which are represented by numerical coding. Heart rate variability is represented by the standard deviation of heart rate, and activity level is represented by the numerical coding of acceleration.

3. The electronic acquisition, storage and management system for pacemaker program control data according to claim 1, characterized in that: The first feature sequence is preprocessed, and the specific steps include: S201, using the mean value in the first feature sequence to fill in the missing values; S202, performing denoising processing on the first characteristic sequence using a bandpass filtering method; S203, based on standard deviation and 3 The rule performs statistical anomaly detection on the first feature sequence, filters out outliers, and uses linear interpolation to perform replacement processing.

4. The electronic acquisition, storage and management system for pacemaker program control data according to claim 1, characterized in that: The specific steps of feature extraction include: S301, extracting a pacing frequency-energy comprehensive index feature according to the first feature sequence, the calculation formula of the pacing frequency-energy comprehensive index feature is: ,in, Indicates the pacing frequency-energy comprehensive index characteristics, Indicates the current pacing frequency. Indicates the current output energy of the pacemaker. Indicates the current pacing threshold, Indicates the current perception sensitivity. Represents a minimum value between 0 and 1. represents the number of acquisition time points within the first preset time period, i represents the index of the time point, represents the pacing frequency at the i-th time point, represents the average pacing frequency at T time points in the first preset time period; S302, extracting a heartbeat stability coefficient feature according to the first feature sequence, wherein the calculation formula of the heartbeat stability coefficient feature is: ,in, Represents the characteristics of the heart beat stability coefficient, represents a first preset time interval, represents the heart rate at the i-th time point, represents the mean heart rate at T time points in the first preset time period, Indicates the pacing mode, represents the baseline perception sensitivity, S represents the perception sensitivity, represents the QT change weight coefficient, represents the QT interval, Indicates the standard QT value; S303, extracting physiological recovery index features according to the first feature sequence, the calculation formula of the physiological recovery index features is: ,in, Represents the physiological recovery index characteristics, represents the heart rate at the i-1th time point, and represent the QT interval at the i-1th time point and the i-th time point, respectively. represents the activity level at the i-th time point, represents the average activity level at T time points in the first preset time period; S304, concatenating the pacing frequency-energy comprehensive index feature, the heartbeat stability coefficient feature, and the physiological recovery index feature after the sequence unit of the first feature sequence, and normalizing them to obtain a second feature sequence.

5. The electronic acquisition, storage and management system for pacemaker program control data according to claim 1, characterized in that: The specific steps of the fuzzy control algorithm include: S401, input fuzzification step, multi-layer fuzzy mapping of physiological signals; S402, a fuzzy reasoning step, analyzing the adjustment trend of the first control parameter in a fuzzy logic framework according to a first preset rule, wherein the first preset rule is used to define the fuzzy adjustment boundaries corresponding to different physiological states; S403, a defuzzification step, after the adjustment trend is clear, converts the control quantity in the fuzzy space into an executable value and acts on the first control parameter of the pacemaker.

6. The electronic acquisition, storage and management system for pacemaker program control data according to claim 5, characterized in that: The specific steps of S402 include: S501, calculating the membership degree of the physiological signal based on the triangular membership function, where the membership degree represents the degree of belonging of the input variable in the division level; S502, calculating the activation degree of the rule triggered by the input variable according to the membership degree of the input variable; S503: Determine an adjustment trend of the first control parameter according to the activation degree of the rule.

7. The electronic acquisition, storage and management system for pacemaker program control data according to claim 1, characterized in that: The physiological state prediction model is built with the gated recurrent unit as the core. The structure of the physiological state prediction model includes: input layer, feature extraction layer, and output layer; among them, the input layer is used to input the second feature sequence; the feature extraction layer uses the gated recurrent unit to process the second feature sequence and extract cross-time step correlation features; the output layer is used to perform dimensionality reduction mapping on the extracted cross-time step correlation features, and finally generate a physiological health score.

8. The electronic acquisition, storage and management system for pacemaker program control data according to claim 7, characterized in that: A reinforcement learning model is constructed with the physiological health score as the core. The state variables of the reinforcement learning model include the parameters in the pacemaker characteristic data and the physiological health score. The action variables include the adjustment values ​​of the pacing threshold, pacing frequency and sensory sensitivity. The reward function is composed of the change value of the physiological health score and the adjustment cost of the first control parameter. During the training process, the deep deterministic policy gradient is used to optimize the first control parameter under different physiological states. The calculation formula of the reward function is: ； in, represents the value of the reward function, represents the physiological health score at the current time step, represents the physiological health score of the previous time step, represents the first weight coefficient, , and denote the second weight coefficient, the third weight coefficient and the fourth weight coefficient respectively, Indicates the adjustment value of the pacing threshold. Indicates the adjustment value of the pacing frequency. Indicates the adjustment value of perception sensitivity.

9. The electronic acquisition, storage and management system for pacemaker program control data according to claim 8, characterized in that: The feedback mechanism module includes: local optimization feedback, cloud optimization feedback and closed-loop feedback mechanism. The local optimization feedback is adjusted in real time through the fuzzy control algorithm and the first preset rules, and the adjustment results are uploaded to the cloud regularly for long-term learning by the cloud; the cloud optimization feedback is used to output the physiological health score through the physiological state prediction model, and use reinforcement learning to optimize the first control parameter to obtain the optimization strategy, and push it to the local end; the closed-loop feedback mechanism specifically includes: local real-time optimization, local upload feedback, cloud long-term learning, cloud push optimization strategy and local update optimization strategy.

Images