Heart pacing device

Abstract

A chip of the heart pace-making device adopts a BCD process, and the heart pace-making device comprises a data acquisition module used for acquiring biological simulation signals of a human body in real time; the data preprocessing module is used for converting the collected biological analog signal into a biological digital signal; the first machine learning module outputs a decision signal based on the input biological digital signal; and the digital control module is used for converting the decision signal into a digital control signal so as to execute the treatment action of the cardiac pacing device. The BCD process can realize analog and digital mixed signal functions on a single chip, and has the characteristics of low power consumption and high performance. Biological simulation signals of a human body are collected in real time through the data collection module, and working parameters of the cardiac pacing device are dynamically adjusted according to individual differences and physiological states of patients. The first machine learning module can output a decision signal based on the input biological digital signal, and the working state of the cardiac pacing device can be intelligently adjusted through the first machine learning module adopting an artificial intelligence algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a cardiac pacemaker. Background Art

[0002] A pacemaker is an electronic therapeutic device implanted in the body. It emits an electric pulse powered by a battery through a pulse generator. Through the conduction of the wire electrodes, it stimulates the myocardium that the electrodes contact, causing the heart to become excited and contracted, thereby achieving the purpose of treating cardiac dysfunction caused by certain arrhythmias. Since the first pacemaker was implanted in the human body in 1958, pacemaker manufacturing technology and processes have developed rapidly, and its functions have become increasingly perfect. While pacemakers have successfully treated slow arrhythmias and saved the lives of thousands of patients, pacemakers have also begun to be used in tachyarrhythmias and non-cardiac electrical diseases, such as preventing paroxysmal atrial tachyarrhythmias, carotid sinus syncope, and biventricular synchronization to treat drug-refractory congestive heart failure.

[0003] However, there are still many problems with the pacemakers in the prior art. Summary of the invention

[0004] The technical problem solved by the present invention is to provide a cardiac pacemaker device to increase the personalized and intelligent treatment function of the cardiac pacemaker device.

[0005] To solve the above problems, the technical solution of the present invention provides a cardiac pacemaker device, the chip of the cardiac pacemaker device adopts the BCD process, and the cardiac pacemaker device includes: a data acquisition module, which is used to collect human body's biological analog signals in real time; a data preprocessing module, which is electrically connected to the data acquisition module, and is used to convert the collected biological analog signals into biological digital signals; a first machine learning module, which is electrically connected to the data preprocessing module, and outputs a decision signal based on the input biological digital signal; a digital control module, which is electrically connected to the first machine learning module, and is used to convert the decision signal into a digital control signal to execute the treatment action of the cardiac pacemaker device.

[0006] Optionally, the data preprocessing module includes: a digital-to-analog conversion module, used to convert the collected biological analog signals into initial biological digital signals; and a data fusion module, used to perform weighted processing on each of the initial biological digital signals to generate the biological digital signals.

[0007] Optionally, the data fusion module includes: a multiplier.

[0008] Optionally, the first machine learning model embedded in the first machine learning module includes: a long short-term memory network model.

[0009] Optionally, the first machine learning model training phase and testing phase are completed before implanting the cardiac pacemaker device.

[0010] Optionally, it also includes: a communication module, electrically connected to the data preprocessing module, and used to transmit the biological digital signal to a terminal display device.

[0011] Optionally, the communication module is also electrically connected to the digital control module for feeding back the digital control signal to a terminal display device.

[0012] Optionally, it also includes: a second machine learning module, electrically connected to the data preprocessing module, for monitoring whether there is any abnormality in the biological digital signal.

[0013] Optionally, the second machine learning model embedded in the second machine learning module includes: an autoencoder model.

[0014] Optionally, the second machine learning model training phase and testing phase are completed before implanting the cardiac pacemaker device.

[0015] Compared with the prior art, the technical solution of the present invention has the following advantages:

[0016] In the cardiac pacemaker device of the technical solution of the present invention, the chip of the cardiac pacemaker device adopts the BCD process. The BCD process can realize analog and digital mixed signal functions on a single chip, and has the characteristics of low power consumption and high performance. The chip application of the BCD process provides an ideal platform for the personalization and intelligence of the cardiac pacemaker device. The data acquisition module collects the biological analog signals of the human body in real time, and the working parameters of the cardiac pacemaker device can be dynamically adjusted according to the individual differences and physiological states of the patients to meet the personalized treatment needs of different patients. The first machine learning module can output a decision signal based on the input biological digital signal. By using the first machine learning module of the artificial intelligence algorithm, the working state of the cardiac pacemaker device, such as pacing frequency, pacing mode, etc., can be intelligently adjusted to adapt to the different physiological states and activity levels of patients, thereby improving the treatment effect and the quality of life of patients.

[0017] Furthermore, it also includes: a communication module, which is electrically connected to the data preprocessing module and is used to transmit the biological digital signal to the terminal display device; the communication module is also electrically connected to the digital control module and is used to feed back the digital control signal to the terminal display device. The patient's physiological parameters and the working status of the cardiac pacemaker are continuously monitored, and timely adjustments are made according to real-time changes to ensure that the working status of the cardiac pacemaker is synchronized with the patient's status. At the same time, the information on the working status adjustment is fed back to medical staff so that they can intervene and adjust in time.

[0018] Furthermore, it also includes: a second machine learning module, which is electrically connected to the data preprocessing module and is used to monitor whether the biological digital signal has an abnormality. Fault diagnosis is performed by the second machine learning module, thereby achieving real-time monitoring and abnormality detection of the working state of the cardiac pacemaker. By analyzing and comparing the data collected by the data acquisition module, possible faults and abnormalities of the cardiac pacemaker can be discovered in time, thereby improving the reliability and safety of the cardiac pacemaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic structural diagram of a cardiac pacemaker device according to an embodiment of the present invention;

[0020] Figure 2 It is a structural schematic diagram of a data preprocessing module in a cardiac pacemaker device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] As described in the background art, there are still many problems with the pacemakers in the prior art, which will be described in detail below.

[0022] Currently, the more advanced pacemakers have the following main features: a dual-chamber design, including a ventricular chamber and an atrial chamber, which can monitor the activity of the atria and ventricles and pace them separately, thereby better simulating the rhythm of the natural heart and improving heart function and the patient's quality of life; equipped with adaptive heart rate sensing technology, which can automatically adjust the pacing rate according to the patient's activity level and physical needs, and provide personalized treatment plans to better adapt to the patient's lifestyle and changes in heart function; equipped with atrial fibrillation detection and treatment functions, which can promptly identify atrial fibrillation and take corresponding treatment measures, such as pacing or electric shock, to maintain normal heart rhythm; equipped with remote monitoring and data management functions, which can communicate with doctors or medical teams in real time through wireless networks, so that doctors can remotely monitor the patient's heart health status, adjust the treatment plan in time, and improve the treatment effect and the patient's quality of life; using advanced battery technology and low-power design, with a long battery life and low energy consumption, can reduce the frequency of pacemaker replacement and reduce the surgical risks and inconvenience of patients.

[0023] However, the chips in current pacemakers usually use CMOS technology, which has a relatively low integration level, which limits the functional complexity that the device can achieve. Moreover, because the chip is limited by the CMOS technology, it is difficult to achieve complex functions and operations in a small space, which leads to certain limitations in meeting the personalized needs of patients and providing intelligent treatment. For example:

[0024] Limitations of fixed parameter settings: Current pacemakers usually use fixed parameter settings and cannot be adjusted in real time according to individual differences and changing physiological states of patients. This leads to certain limitations in personalized treatment and cannot meet the needs of patients to the greatest extent;

[0025] Lack of data collection and intelligent control: Current pacemaker technology lacks intelligent control and cannot make corresponding adjustments based on the patient's real-time condition. This, to some extent, limits the flexibility and adaptability in responding to different physiological conditions of patients, which may affect the treatment effect and the patient's quality of life.

[0026] On this basis, the present invention provides a cardiac pacemaker device, the chip of which adopts the BCD process. The BCD process can realize analog and digital mixed signal functions on a single chip, and has the characteristics of low power consumption and high performance. The chip application of the BCD process provides an ideal platform for the personalization and intelligence of the cardiac pacemaker device. The data acquisition module collects the biological analog signals of the human body in real time, and the working parameters of the cardiac pacemaker device can be dynamically adjusted according to the individual differences and physiological states of the patients to meet the personalized treatment needs of different patients. The first machine learning module can output a decision signal based on the input biological digital signal. By using the first machine learning module of the artificial intelligence algorithm, the working state of the cardiac pacemaker device, such as pacing frequency, pacing mode, etc., can be intelligently adjusted to adapt to the different physiological states and activity levels of the patients, thereby improving the treatment effect and the quality of life of the patients.

[0027] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] Figure 1 is a schematic structural diagram of a cardiac pacemaker device according to an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a data preprocessing module in a cardiac pacemaker device according to an embodiment of the present invention.

[0029] Please refer to Figure 1 , a cardiac pacemaker device, the chip of the cardiac pacemaker device adopts the BCD process, and the cardiac pacemaker device comprises: a data acquisition module 100, used to collect biological analog signals of the human body in real time; a data preprocessing module 101, electrically connected to the data acquisition module 100, used to convert the collected biological analog signals into biological digital signals; a first machine learning module 102, electrically connected to the data preprocessing module 101, outputting a decision signal based on the input biological digital signal; a digital control module 103, electrically connected to the first machine learning module 102, used to convert the decision signal into a digital control signal to execute the treatment action of the cardiac pacemaker device.

[0030] The chip of the cardiac pacemaker adopts the BCD process, which can realize analog and digital mixed signal functions on a single chip, and has the characteristics of low power consumption and high performance. The chip application of the BCD process provides an ideal platform for the personalization and intelligence of the cardiac pacemaker.

[0031] By collecting the biological simulation signals of the human body in real time through the data acquisition module 100, the working parameters of the cardiac pacemaker can be dynamically adjusted according to the individual differences and physiological states of the patients to meet the personalized treatment needs of different patients.

[0032] The first machine learning module 102 can output a decision signal based on the input biological digital signal. By adopting the artificial intelligence algorithm, the first machine learning module 102 can intelligently adjust the working state of the cardiac pacemaker, such as pacing frequency, pacing mode, etc., to adapt to the different physiological states and activity levels of the patient, thereby improving the treatment effect and the patient's quality of life.

[0033] It should be noted that the BCD process, namely the Bipolar-CMOS-DMOS process, is an integrated circuit manufacturing technology that combines bipolar, complementary metal oxide semiconductor (CMOS) and bipolar field effect transistor (DMOS) technologies to manufacture high-performance, low-power electronic devices.

[0034] In this embodiment, the data acquisition module 100 is various sensors (such as heart rate sensors, blood pressure sensors, body temperature sensors, etc.), which are integrated in the cardiac pacemaker device to be responsible for real-time acquisition of the human body's bio-analog signals, including electrocardiogram signals, heart rate changes, movement status, etc.

[0035] The relatively weak biological simulation signal collected needs to be amplified so that it can be analyzed more accurately in the subsequent processing steps and the cardiac pacemaker device can adjust filtering and noise reduction. Filtering technology is used to remove high-frequency noise and other interference to obtain a smoother signal and ensure the accuracy of the operation of the cardiac pacemaker device. Sampling is also required for continuous simulation waveforms, collecting data points at certain time intervals, and holding operations are performed before sampling to stabilize the signal and ensure the accuracy of sampling.

[0036] Please refer to Figure 2 In this embodiment, the data preprocessing module 101 includes: a digital-to-analog conversion module 1011, which is used to convert the collected biological analog signals into initial biological digital signals; a data fusion module 1012, which is used to perform weighted processing on each of the initial biological digital signals to generate the biological digital signals.

[0037] The digital-to-analog conversion module 1011 converts the continuous bio-analog signal into a discrete initial bio-digital signal, usually in binary form, for the convenience of digital signal processing. The digital signal processing stage also involves various operations on the initial bio-digital signal, such as filtering, denoising, feature extraction, etc., to extract useful information to provide a more accurate basis for subsequent cardiac pacemaker operation and patient monitoring.

[0038] The data fusion module 1012 is used to fuse the data collected by different sensors to generate comprehensive patient physiological state information, providing a basis for the subsequent decision-making of the first machine learning module 102.

[0039] Assume that there are three types of sensor data inputs: ECG data (X1): used to monitor cardiac electrical activity, with a weight set to W1; blood oxygen data (X2): used to detect the oxygen content in the blood, with a weight set to W2; accelerometer data (X3): used to monitor the patient's motion state, with a weight set to W3. After being processed by the data fusion module 1012, the biological digital signal obtained is: X1*W1+X2*W2+X3*W3.

[0040] Among them, W1, W2 and W3 are the weights of different sensors, indicating the contribution of each sensor data to the final fusion result. The weight setting is usually adjusted according to the importance or accuracy of the sensor, and the sum of the weights is generally 1.

[0041] In this embodiment, the data fusion module 1012 uses a multiplier, wherein the weight is manually set and is fixed in the multiplier when it is set, and cannot be adjusted later.

[0042] In this embodiment, the first machine learning model embedded in the first machine learning module 102 can adopt a long short-term memory network model (Long Short-Term Memory, LSTM).

[0043] In other embodiments, the first machine learning model embedded in the first machine learning module 102 may also be other artificial intelligence technologies that can be used to predict and make decisions on the working state of the cardiac pacemaker, such as a deep neural network model (DNN), a convolutional neural network model (CNN), etc.

[0044] Specifically, the patient's physiological parameter data is collected in real time, including heart rate, blood pressure, activity status (such as stillness, light activity, moderate activity, high activity), sleep status, etc. Features are extracted from the collected physiological parameter data, such as heart rate change rate, exercise intensity, sleep depth, etc., as input features. The extracted features are input into the trained LSTM model, and the LSTM model predicts the most suitable working state of the cardiac pacemaker in real time according to the current state of the patient, including pacing frequency, pacing mode, etc. According to the prediction results of the LSTM model, the working state of the cardiac pacemaker is adjusted in real time to optimally meet the patient's current physiological needs. For example, when the patient's activities are more intense, the pacing frequency is increased to meet the heart's needs; when the patient enters a sleep state, the pacing frequency is reduced to keep the heart rate stable.

[0045] In this embodiment, before implanting the cardiac pacemaker, the first machine learning model training phase and testing phase are completed based on human historical big data.

[0046] It should be noted that the first machine learning model will be converted into a form suitable for embedded devices and solidified in the Flash or EEPROM memory in the chip through code (such as C / C++) or hardware description language. The first machine learning model only has a software part, but hardware support is required to start the first machine learning model.

[0047] In this embodiment, since the decision signal output by the first machine learning module is based on the output of the software algorithm, if it is to be converted into a signal that can control the operation of the hardware, it is necessary to convert it through the digital control module 103 into the digital control signal that can control the cardiac pacemaker device to perform treatment actions.

[0048] Please continue to refer to Figure 1 The cardiac pacemaker device also includes: a communication module 104, which is electrically connected to the data preprocessing module 101 and is used to transmit the biological digital signal to the terminal display device; the communication module 104 is also electrically connected to the digital control module 103 and is used to feed back the digital control signal to the terminal display device.

[0049] By continuously monitoring the patient's physiological parameters and the working state of the cardiac pacemaker, and adjusting in time according to real-time changes, it is ensured that the working state of the cardiac pacemaker is synchronized with the patient's state. At the same time, the information of the working state adjustment is fed back to medical staff so that they can make timely intervention and adjustments.

[0050] Please continue to refer to Figure 1The cardiac pacemaker device also includes: a second machine learning module 105, which is electrically connected to the data preprocessing module 101 and is used to monitor whether there is any abnormality in the biological digital signal.

[0051] In this embodiment, the second machine learning model embedded in the second machine learning module 105 adopts an autoencoder model.

[0052] In other embodiments, in addition to the method based on the autoencoder model, other fault diagnosis techniques may be used to monitor and analyze the state of the cardiac pacemaker device, such as a rule-based fault diagnosis method, a statistics-based fault diagnosis method, etc.

[0053] Specifically, the sensor data of the cardiac pacemaker device is collected in real time, including electrocardiogram signals, pulse waveforms, battery power, etc. Features are extracted from the sensor data, such as spectral features, time domain features, etc., as inputs to the abnormality detection model: the Autoencoder model is trained using historical data (completed before implanting the cardiac pacemaker device), and the normal mode of the working state of the cardiac pacemaker device and the modes under different abnormal conditions are established. The sensor data collected in real time is input into the trained Autoencoder model, and the model will output an abnormality score. According to the abnormality score, it can be judged whether there is an abnormal situation at present. When the abnormality score exceeds the preset threshold, the system triggers a fault warning, issues an alarm and notifies medical staff. The warning information may include the type of abnormality, possible causes of the fault and recommended countermeasures. The sensor data and abnormality detection results are continuously monitored, and the threshold and parameters of the fault warning are adjusted according to the real-time situation to ensure the accuracy and timeliness of the warning system. At the same time, the fault warning information is fed back to the medical staff so that they can take corresponding countermeasures to avoid serious faults or accidents and improve the reliability and safety of the cardiac pacemaker device.

[0054] In this embodiment, it also includes: a power management module 106, which is electrically connected to each module to provide a stable power supply to ensure the normal operation of the cardiac pacemaker.

[0055] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined by the claims.

Claims

1. A cardiac pacemaker device, characterized in that: The chip of the cardiac pacemaker adopts the BCD process, and the cardiac pacemaker comprises: Data acquisition module, used to collect biological simulation signals of the human body in real time; A data preprocessing module, electrically connected to the data acquisition module, and used for converting the acquired biological analog signal into a biological digital signal; A first machine learning module, electrically connected to the data preprocessing module, outputting a decision signal based on the input biological digital signal; A digital control module is electrically connected to the first machine learning module and is used to convert the decision signal into a digital control signal to execute the treatment action of the cardiac pacemaker.

2. The cardiac pacemaker device according to claim 1, characterized in that: The data preprocessing module includes: a digital-to-analog conversion module for converting the collected biological analog signals into initial biological digital signals; and a data fusion module for performing weighted processing on each of the initial biological digital signals to generate the biological digital signals.

3. The cardiac pacemaker device according to claim 2, characterized in that: The data fusion module includes: a multiplier.

4. The cardiac pacemaker device according to claim 1, wherein: The first machine learning model embedded in the first machine learning module includes: a long short-term memory network model.

5. The cardiac pacemaker device according to claim 4, characterized in that: Before implanting the cardiac pacemaker device, the first machine learning model training phase and testing phase are completed.

6. The cardiac pacemaker device according to claim 1, characterized in that: Also includes: The communication module is electrically connected to the data preprocessing module and is used to transmit the biological digital signal to a terminal display device.

7. The cardiac pacemaker device according to claim 6, characterized in that: The communication module is also electrically connected to the digital control module and is used to feed back the digital control signal to the terminal display device.

8. The cardiac pacemaker device according to claim 1, wherein: Also includes: The second machine learning module is electrically connected to the data preprocessing module and is used to monitor whether the biological digital signal has an abnormality.

9. The cardiac pacemaker device according to claim 8, characterized in that: The second machine learning model embedded in the second machine learning module includes: an autoencoder model.

10. The cardiac pacemaker device according to claim 8, characterized in that: Before implanting the cardiac pacemaker device, the second machine learning model training phase and testing phase are completed.

Images