Hemodynamics-based in-aorta balloon counterpulsation system control method

Abstract

The invention provides an in-aorta balloon counterpulsation system control method based on hemodynamics, and relates to the technical field of medical system control. According to the method provided by the invention, hemodynamic monitoring signals of a target user are obtained in real time, wherein the hemodynamic monitoring signals comprise the total heart end diastole volume, the rate of variation per stroke, extravascular lung water, the heart index and the cardiac output; based on a pre-trained neural network model, determining heart indexes corresponding to multiple moments of the target user in a future time period according to the hemodynamic monitoring signal; and under the condition that the heart index corresponding to the first moment of the target user is smaller than a first threshold value, generating a first request, and in response to an input confirmation operation on the first request, starting the intra-aortic balloon counterpulsation system at the first moment. According to the method provided by the invention, the start and stop of the balloon counterpulsation system in the aorta can be accurately controlled, and the processing efficiency and accuracy are improved.

Description

Technical Field

[0001] This invention relates to the field of medical system control technology, and in particular to a control method for an intra-aortic balloon counterpulsation system based on hemodynamics. Background Technology

[0002] The intra-aortic balloon pump (IABP) system is a key component in interventional treatment of cardiovascular diseases. The IABP system controls blood flow through the user's aorta by inflating and deflating a balloon, thereby assisting the heart through counterpulsation.

[0003] Currently, IABP systems assist the heart by using electrocardiogram (ECG) triggering. ECG triggering can be understood as synchronizing the inflation and deflation of the balloon based on the user's cardiac electrophysiological activity. During each cardiac cycle, a series of ECG signals are generated. By monitoring these signals, the IABP system can accurately identify the systolic and diastolic phases of the heart and control the inflation and deflation of the balloon accordingly. Currently, the start-up and shutdown control of IABP systems is often based on static thresholds or manual operation. Static thresholds can be understood as activating or deactivating the IABP system when a certain parameter exceeds a preset threshold, or activating or deactivating the system in response to operator input. However, static threshold methods are prone to false alarms, and manual operation requires operators with extensive professional experience, thus resulting in low efficiency and poor accuracy.

[0004] Therefore, there is an urgent need for a hemodynamic-based control method for the intra-aortic balloon counterpulsation system, which can accurately control the start and stop of the intra-aortic balloon counterpulsation system, thereby improving processing efficiency and accuracy. Summary of the Invention

[0005] This invention provides a hemodynamically based method for controlling an intra-aortic balloon counterpulsation system, which enables accurate control of the start and stop of the intra-aortic balloon counterpulsation system, improving processing efficiency and accuracy.

[0006] To achieve the above objectives, the embodiments of the present invention adopt the following technical solutions: Firstly, a hemodynamic-based control method for an intra-aortic balloon counterpulsation (IACP) system is provided, applied to the IACP system. The IACP system includes a gas cylinder, a cylinder, a balloon, a hemodynamic monitoring module, a processor, and a motor; the gas cylinder, cylinder, and balloon are connected via a pneumatic circuit; the processor is electrically connected to the motor and the hemodynamic monitoring module respectively, and the motor is connected to the cylinder; the method includes: the hemodynamic monitoring module acquiring the target user's hemodynamic monitoring signals in real time, the hemodynamic monitoring signals including global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output; the processor based on pre-defined parameters... The trained neural network model determines the cardiac index of the target user at multiple moments in the future time period based on the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments in the historical time period. If the cardiac index of the target user at the first moment is less than a first threshold, the processor generates a first request to request the activation of the intra-aortic balloon counterpulsation system at the first moment, where the first moment is one of multiple moments in the future time period. In response to the input confirmation operation of the first request, the processor activates the intra-aortic balloon counterpulsation system at the first moment.

[0007] The method provided by this invention calculates multiple parameters included in the hemodynamic monitoring signal through coupling, predicts the cardiac index for a future time period based on a neural network model, and accurately activates the intra-aortic balloon counterpulsation system when the cardiac index is less than a first threshold and in response to the input confirmation operation. On the one hand, predicting through multiple parameters can effectively avoid misjudgment of a single parameter, and on the other hand, it can realize the automatic activation of the intra-aortic balloon counterpulsation system, saving manpower and time costs, and improving processing efficiency and accuracy.

[0008] In one possible implementation of the first aspect, the first threshold CI threshold The formula for determining CI is: threshold = (α1A1 + α2A2 + α3A3) × CI base ; A1 = Age / 70; Where α1 is the first weighting coefficient, α2 is the second weighting coefficient, and α3 is the third weighting coefficient; A1 is the age influence factor; Age is the target user's age; A2 is the blood pressure influence factor; BP is the target user's maximum blood pressure; A3 is the ventilation status influence factor; and when the target user's ventilation status is mechanical ventilation, A3 = 1.5, and when the target user's ventilation status is non-mechanical ventilation, A3 = 1, CI base Preset heart rate index.

[0009] The method provided by this invention can determine the corresponding first threshold based on the different states and types of the target user by setting a dynamic first threshold, and then achieve accurate control of the intra-aortic balloon counterpulsation system of the target user through the first threshold, so as to meet the different usage needs of different users and enhance the adaptability of the intra-aortic balloon counterpulsation system.

[0010] In one possible implementation of the first aspect, the formula for determining the first weighting coefficient α1, the second weighting coefficient α2, and the third weighting coefficient is α3: Where S1 is the cardiac index deviation rate, S2 is the rate of change of global end-diastolic volume, S3 is the lung water volume ratio, and μ is the sensitivity coefficient.

[0011] The method provided by this invention dynamically determines multiple weighting coefficients, which can fully consider the influence of cardiac index deviation rate, global end-diastolic volume and lung water volume ratio on the first threshold corresponding to the target user when determining the first threshold. In this way, the method can accurately control the intra-aortic balloon counterpulsation system of the target user through the first threshold, meet the different usage needs of different users, and enhance the adaptability of the intra-aortic balloon counterpulsation system.

[0012] In one possible implementation of the first aspect, the method further includes: when the processor generates a second request if the cardiac index corresponding to the target user during the target time period is greater than a second threshold, the second request is used to request the control of the intra-aortic balloon counterpulsation system to be turned off at a second moment, wherein the target time period is located in the future time period and the second moment is the end time of the target time period; in response to the input confirmation operation of the second request, the processor turns off the intra-aortic balloon counterpulsation system at the second moment.

[0013] The method provided by this invention calculates multiple parameters included in the hemodynamic monitoring signal and predicts the cardiac index for a future time period based on a neural network model. When the cardiac index is greater than a second threshold and continues for a target time period, the method controls the shutdown of the intra-aortic balloon counterpulsation system in response to the input confirmation operation. On the one hand, predicting through multiple parameters can effectively avoid misjudgment of a single parameter. On the other hand, it can realize the automatic shutdown of the intra-aortic balloon counterpulsation system, saving manpower and time costs and improving processing efficiency and accuracy.

[0014] In one possible implementation of the first aspect, the method further includes: when the fluctuation range of the cardiac index of the target user at multiple moments in a future time period is greater than ±15%, the processor generates a first alarm message, which is used to indicate an abnormality in the intra-aortic balloon counterpulsation system.

[0015] The method provided by this invention effectively monitors the fluctuation range of cardiac indexes and generates a first alarm message when the fluctuation range of cardiac indexes exceeds a preset range, so that operators can take timely action, thereby improving the safety and stability of the intra-aortic balloon counterpulsation system and enhancing the user experience.

[0016] In one possible implementation of the first aspect, before the processor generates the first request or the second request, the method further includes: the processor determining the target user's cardiac index offset rate; and the processor generating a second alarm message if the target user's cardiac index offset rate is greater than 15%, the second alarm message being used to indicate an abnormality in the reliability of the hemodynamic monitoring signal. The formula for determining the target user's cardiac index offset rate C is: CI1 represents the cardiac index included in the hemodynamic monitoring signal of the target user; CI2 represents the cardiac index obtained from the echocardiogram of the target user.

[0017] The method provided by this invention verifies the reliability of cardiac indices included in hemodynamic monitoring signals by using cardiac indices obtained from echocardiography. It can generate a second alarm message when the cardiac index deviation rate is greater than a preset range, so that operators can take timely action and avoid controlling the intra-aortic balloon counterpulsation system based on data with low reliability. This improves the safety and stability of the intra-aortic balloon counterpulsation system and enhances the user experience.

[0018] In one possible implementation of the first aspect, before the processor generates the first request or the second request, the method further includes: the processor determining the cylinder pressure fluctuation rate of the intra-aortic balloon counterpulsation system; and the processor generating a third alarm message when the cylinder pressure fluctuation rate of the intra-aortic balloon counterpulsation system is greater than 20%, the third alarm message being used to indicate an airtightness abnormality of the intra-aortic balloon counterpulsation system. The formula for determining the cylinder pressure fluctuation rate P is: Among them, P t Let P be the cylinder pressure at time t, and max(P) t ) represents the maximum cylinder pressure within the time window, min(P) t ) represents the minimum cylinder pressure within the time window, mean(P) t The average cylinder pressure within the time window is denoted as .

[0019] The method provided by this invention monitors the fluctuation rate of cylinder pressure and generates a third alarm message when the fluctuation rate is abnormal. This allows the operator to check the airtightness of the intra-aortic balloon counterpulsation system's cylinder, avoiding the need to control the intra-aortic balloon counterpulsation system to start or stop when the cylinder airtightness is compromised. This improves the safety and stability of the intra-aortic balloon counterpulsation system and enhances the user experience.

[0020] In one possible implementation of the first aspect, before the processor determines the cardiac index of the target user at multiple moments in a future time period based on the global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments within a historical time period, the method further includes: the processor acquiring multiple training samples, each training sample including the global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output of the sample user at multiple moments within a historical time period, and the cardiac index of the sample user at a target moment after the historical time period; the processor iteratively training the neural network model based on the multiple training samples to obtain the pre-trained neural network model.

[0021] The method provided in this invention iteratively trains a neural network model using training samples composed of various parameters, which can effectively improve the accuracy of the neural network model in predicting cardiac indices, effectively avoid misjudgment of a single parameter, and enable the automatic activation of the intra-aortic balloon counterpulsation system based on the cardiac indices predicted by the neural network model, saving manpower and time costs and improving processing efficiency and accuracy.

[0022] In one possible implementation of the first aspect, when the hemodynamic monitoring module and the balloon are placed in the same artery of the target user, after the hemodynamic monitoring module acquires the hemodynamic monitoring signal of the target user in real time, the method further includes: the processor filtering signals in the hemodynamic monitoring signal with a frequency less than or equal to a preset threshold.

[0023] The method provided by this invention, when the hemodynamic monitoring module and the balloon are placed in the same artery of the target user, allows the processor to filter signals with frequencies less than or equal to a preset threshold. This effectively avoids interference from noise generated by mechanical vibration during the operation of the intra-aortic balloon counterpulsation system on the hemodynamic monitoring signal, improves the accuracy of the hemodynamic monitoring signal, and thus enhances the accuracy and safety of the control of the intra-aortic balloon counterpulsation system.

[0024] Secondly, embodiments of the present invention provide a hemodynamic-based intra-aortic balloon counterpulsation (IACP) system control system, applied to an IACP system. The IACP system includes a gas cylinder, a cylinder, a balloon, a hemodynamic monitoring module, a processor, and a motor. The gas cylinder, cylinder, and balloon are connected via a pneumatic circuit. The processor is electrically connected to both the motor and the hemodynamic monitoring module, and the motor is connected to the cylinder. The hemodynamic monitoring module is used to: acquire real-time hemodynamic monitoring signals from the target user, including global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output. The processor is used to... Based on a pre-trained neural network model, the system determines the cardiac index of the target user at multiple moments in the future time period based on the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments within a historical time period. If the cardiac index of the target user at a first moment is less than a first threshold, a first request is generated. The first request is used to request the activation of the intra-aortic balloon counterpulsation system at the first moment, where the first moment is one of multiple moments within the future time period. In response to the input confirmation operation of the first request, the intra-aortic balloon counterpulsation system is activated at the first moment.

[0025] Understandably, the beneficial effects that the system of the second aspect described above can achieve can be referenced from the beneficial effects of the first aspect and any of its possible design methods, which will not be repeated here. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of the structure of an intra-aortic balloon counterpulsation system according to an embodiment of the present invention; Figure 2 This is a schematic flowchart illustrating a control method for an intra-aortic balloon counterpulsation system according to an embodiment of the present invention; Figure 3 This is a schematic flowchart illustrating another control method for an intra-aortic balloon counterpulsation system according to an embodiment of the present invention. Figure 4 This is a schematic flowchart illustrating another control method for an intra-aortic balloon counterpulsation system according to an embodiment of the present invention; Figure 5 This is a schematic flowchart illustrating another control method for an intra-aortic balloon counterpulsation system according to an embodiment of the present invention; Figure 6 This is a schematic flowchart illustrating another control method for an intra-aortic balloon counterpulsation system according to an embodiment of the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be described below with reference to the accompanying drawings. In the description of the present invention, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can represent A or B. The "or" in the present invention is merely a description of the relationship between the related objects, indicating that three relationships can exist. For example, A or B can represent: A alone, A and B simultaneously, and B alone. A and B can be singular or plural. Furthermore, in the description of the present invention, unless otherwise stated, "multiple" refers to two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items.

[0028] Furthermore, to facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0029] In this embodiment of the invention, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this embodiment of the invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner for ease of understanding.

[0030] The intra-aortic balloon pump (IABP) system is a key component in interventional treatment of cardiovascular diseases. The IABP system controls blood flow through the user's aorta by inflating and deflating a balloon, thereby assisting the heart through counterpulsation.

[0031] Currently, IABP systems assist the heart by using electrocardiogram (ECG) triggering. ECG triggering can be understood as synchronizing the inflation and deflation of the balloon based on the user's cardiac electrophysiological activity. During each cardiac cycle, a series of ECG signals are generated. By monitoring these signals, the IABP system can accurately identify the systolic and diastolic phases of the heart and control the inflation and deflation of the balloon accordingly. Currently, the start-up and shutdown control of IABP systems is often based on static thresholds or manual operation. Static thresholds can be understood as activating or deactivating the IABP system when a certain parameter exceeds a preset threshold, or activating or deactivating the system in response to operator input. However, static threshold methods are prone to false alarms, and manual operation requires operators with extensive professional experience, thus resulting in low efficiency and poor accuracy.

[0032] Therefore, there is an urgent need for a hemodynamic-based control method for the intra-aortic balloon counterpulsation system, which can accurately control the start and stop of the intra-aortic balloon counterpulsation system, thereby improving processing efficiency and accuracy.

[0033] In view of this, embodiments of the present invention provide a control method for an intra-aortic balloon counterpulsation system based on hemodynamics, applied to an intra-aortic balloon counterpulsation system. The intra-aortic balloon counterpulsation system includes a gas cylinder, a cylinder, a balloon, a hemodynamic monitoring module, a processor, and a motor; the gas cylinder, cylinder, and balloon are connected via a gas path; the processor is electrically connected to the motor and the hemodynamic monitoring module respectively, and the motor is connected to the cylinder; the above method includes: the hemodynamic monitoring module acquiring the hemodynamic monitoring signals of the target user in real time, the hemodynamic monitoring signals including global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output; the processor... Based on a pre-trained neural network model, the processor determines the cardiac index of the target user at multiple moments in the future time period according to the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments in the historical time period. If the cardiac index of the target user at the first moment is less than a first threshold, the processor generates a first request, which requests the activation of the intra-aortic balloon counterpulsation system at the first moment, where the first moment is one of multiple moments in the future time period. In response to the input confirmation operation of the first request, the processor activates the intra-aortic balloon counterpulsation system at the first moment.

[0034] The method provided in this invention calculates multiple parameters included in the hemodynamic monitoring signal by coupling and predicting the cardiac index for a future time period based on a neural network model. When the cardiac index is less than a first threshold and a confirmation operation is received in response to the input, the intra-aortic balloon counterpulsation system is accurately activated. On the one hand, predicting by multiple parameters can effectively avoid misjudgment of a single parameter. On the other hand, it can realize the automatic activation of the intra-aortic balloon counterpulsation system, saving manpower and time costs and improving processing efficiency and accuracy.

[0035] In some embodiments, the control method of the intra-aortic balloon counterpulsation system provided in this invention can be executed by the intra-aortic balloon counterpulsation system 100 (hereinafter referred to as the counterpulsation system 100). See also Figure 1 , Figure 1 This is a schematic diagram of an intra-aortic balloon counterpulsation system according to an embodiment of the present invention. The counterpulsation system 100 includes a gas cylinder 110, a cylinder 120, a balloon 130, a hemodynamic monitoring module 140, a processor 150, and a motor 160. The gas cylinder 110, cylinder 120, and balloon 130 are connected via a gas path. The processor 150 is electrically connected to both the motor 160 and the hemodynamic monitoring module 140, and the motor 160 is connected to the cylinder 120. The method includes: the hemodynamic monitoring module 140 acquiring the hemodynamic monitoring signals of the target user in real time, including global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output. The processor 150, based on a pre-trained neural network model, determines the cardiac index of the target user at multiple moments in the future time period according to the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments in the historical time period. If the cardiac index of the target user at a first moment is less than a first threshold, the processor 150 generates a first request, which requests the activation of the intra-aortic balloon counterpulsation system at the first moment, wherein the first moment is one of multiple moments in the future time period. In response to the input confirmation operation of the first request, the processor 150 activates the intra-aortic balloon counterpulsation system at the first moment.

[0036] It should be noted that, in combination Figure 1 The counterpulsation system 100 also includes a voltage regulator 170, a solenoid valve 180, and an electrocardiogram monitoring module 190; the voltage regulator 170 is located between the gas cylinder 110 and the solenoid valve 180, and is used to control the gas pressure output from the gas cylinder 110 within a preset gas pressure threshold range; the processor 150 and the electrocardiogram monitoring module 190 are electrically connected, and the motor 160 is connected to the cylinder 160, wherein... Figure 1 The dashed lines in the diagram represent gas passages, while the solid lines represent electrical connections.

[0037] The processor 160 is also used to send the target user's electrocardiogram (ECG) signal to the processor 150 based on the ECG signal acquired by the ECG monitoring module 190, and to determine the target user's target cardiac cycle; the processor 160 is also used to generate control commands based on the target user's target cardiac cycle; and to control the motor 160 to operate according to the control commands, so that the motor 160 adjusts the internal pressure of the cylinder 120 to complete the contraction and expansion of the balloon 130; wherein, the target user's cardiac cycle is a time series composed of the time interval between two consecutive heartbeats of the target user.

[0038] For example, processor 150 may include one or more processing cores. Processor 150 connects to various parts within counterpulsation system 100 using various interfaces and lines, and performs various functions of counterpulsation system 100 and processes data by running or executing instructions, programs, code sets, or instruction sets, and by calling data. Optionally, processor 150 may be implemented using at least one of the following hardware forms: Central Processing Unit (CPU), Graphics Processing Unit (GPU), Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA).

[0039] The following description, in conjunction with the accompanying drawings, illustrates a hemodynamically based intra-aortic balloon counterpulsation system control method provided by an embodiment of the present invention.

[0040] Figure 2 This is a flowchart illustrating a hemodynamically based intra-aortic balloon counterpulsation system control method provided in an embodiment of the present invention. Optionally, this method can be... Figure 1 The counterpulsation system 100 shown is executed. This method may include the following steps: S1, the hemodynamic monitoring module acquires the target user's hemodynamic monitoring signals in real time.

[0041] The hemodynamic monitoring signals include global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output. It should be noted that global end-diastolic volume is the total blood volume in all chambers of the target user's heart (left and right atria + ventricles) at end-diastole, reflecting overall cardiac preload. Stroke variability is the maximum rate of change in arterial pulse pressure during a respiratory cycle, reflecting the heart's sensitivity to preload. Extravascular lung water is the amount of fluid (including interstitium and alveoli) accumulating outside the pulmonary vessels, quantifying the degree of pulmonary edema. The cardiac index is the cardiac output per unit body surface area, characterizing cardiac pumping efficiency.

[0042] Specifically, the hemodynamic monitoring module includes an arterial catheter based on pulse-induced contour cardiac output (PiCCO) technology (hereinafter referred to as PiCCO catheter). The PiCCO catheter is placed inside the target user's artery and can acquire the target user's hemodynamic monitoring signals.

[0043] It should be understood that the above implementation of the hemodynamic monitoring module is only an example. The hemodynamic monitoring module can also use other technologies or devices to acquire hemodynamic monitoring signals. The embodiments of the present invention do not impose any particular restrictions on the specific implementation of the hemodynamic monitoring module to acquire hemodynamic monitoring signals.

[0044] In some embodiments, where the hemodynamic monitoring module and the balloon are positioned in the same artery as the target user, after S1, the method further includes: the processor filtering signals in the hemodynamic monitoring signal with frequencies less than or equal to a preset threshold.

[0045] It should be understood that during the measurement process of the hemodynamic monitoring module, the noise generated by the intra-aortic balloon counterpulsation system can affect the accuracy of the hemodynamic monitoring signal. However, the frequency of the hemodynamic monitoring signal is relatively high, while the frequency of the mechanical noise generated by the intra-aortic balloon counterpulsation system is relatively low. Therefore, filtering out the lower-frequency signals in the hemodynamic monitoring signal through a filter can effectively prevent the mechanical noise generated by the intra-aortic balloon counterpulsation system from interfering with the hemodynamic monitoring signal.

[0046] It should be noted that the preset threshold of the signal frequency can be flexibly set according to the actual working scenario, and the embodiments of the present invention do not impose any special restrictions on this.

[0047] The method provided in this embodiment of the invention, when the hemodynamic monitoring module and the balloon are placed in the same artery of the target user, allows the processor to filter signals with frequencies less than or equal to a preset threshold. This effectively avoids interference from noise generated by mechanical vibration during the operation of the intra-aortic balloon counterpulsation system on the hemodynamic monitoring signal, improves the accuracy of the hemodynamic monitoring signal, and thus enhances the accuracy and safety of the control of the intra-aortic balloon counterpulsation system.

[0048] S2. The processor, based on a pre-trained neural network model, determines the cardiac index of the target user at multiple moments in the future time period based on the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments in the historical time period. In one possible implementation, the above S2 specifically includes: The processor, based on a pre-trained neural network model, determines the cardiac index of the target user at multiple moments in the future time period, according to the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments in the historical time period.

[0049] Specifically, the preset frequency is once per hour.

[0050] The method provided in this invention determines the cardiac index of a target user at multiple times within a future time period once per hour, enabling hourly-level control of the intra-aortic balloon counterpulsation system. This allows for automated activation of the intra-aortic balloon counterpulsation system, saving manpower and time costs, and improving processing efficiency and accuracy.

[0051] In some embodiments, see Figure 3 Prior to S2 above, the method provided in this embodiment of the invention further includes: S21. The processor acquires multiple training samples. Each training sample includes the whole heart end-diastolic volume, stroke variability, extravascular lung water, cardiac index and cardiac output of the sample user at multiple moments within the historical time period, as well as the cardiac index of the sample user at the target moment after the historical time period. S22. The processor iteratively trains the neural network model based on multiple training samples to obtain a pre-trained neural network model.

[0052] As can be seen from S21-S22 above, the method provided by the embodiments of the present invention can effectively improve the accuracy of the neural network model in predicting cardiac indices by iteratively training the neural network model with training samples composed of various different parameters, effectively avoid misjudgment of a single parameter, and realize the automatic start of the intra-aortic balloon counterpulsation system based on the cardiac indices predicted by the neural network model, saving manpower and time costs, and improving processing efficiency and accuracy.

[0053] S3. If the heart rate index of the target user is less than the first threshold at the first moment, the processor generates the first request.

[0054] Specifically, the first request is used to request the activation of the intra-aortic balloon counterpulsation system at a first moment, wherein the first moment is one of multiple moments within a future time period.

[0055] In one possible implementation, the first threshold CI threshold The formula for determining it is: CI threshold = (α1A1 + α2A2 + α3A3) × CI base ; A1 = Age / 70; Where α1 is the first weighting coefficient, α2 is the second weighting coefficient, and α3 is the third weighting coefficient; A1 is the age influence factor; Age is the target user's age; A2 is the blood pressure influence factor; BP is the target user's maximum blood pressure; A3 is the ventilation status influence factor; and when the target user's ventilation status is mechanical ventilation, A3 = 1.5, and when the target user's ventilation status is non-mechanical ventilation, A3 = 1, CI base Preset heart rate index.

[0056] Furthermore, the formula for determining the first weighting coefficient α1, the second weighting coefficient α2, and the third weighting coefficient is α3: Where S1 is the cardiac index deviation rate, S2 is the rate of change of global end-diastolic volume, S3 is the lung water volume ratio, and μ is the sensitivity coefficient.

[0057] As described above, the method provided by this invention, by setting a dynamic first threshold, can determine the corresponding first threshold based on different states and types of the target user, thereby achieving accurate control of the intra-aortic balloon counterpulsation system for the target user through the first threshold. Furthermore, by dynamically determining multiple weighting coefficients, the method provided by this invention can fully consider the influence of cardiac index deviation rate, global end-diastolic volume, and lung water volume ratio on the first threshold corresponding to the target user when determining the first threshold, thereby achieving accurate control of the intra-aortic balloon counterpulsation system for the target user through the first threshold, meeting the different usage needs of different users, and enhancing the adaptability of the intra-aortic balloon counterpulsation system.

[0058] S4. In response to the confirmation operation of the input first request, the processor activates the intra-aortic balloon counterpulsation system at the first moment.

[0059] As can be seen from S1-S4 above, the method provided by the embodiments of the present invention calculates multiple parameters included in the hemodynamic monitoring signal by coupling, predicts the cardiac index for a future time period based on a neural network model, and accurately starts the intra-aortic balloon counterpulsation system when the cardiac index is less than a first threshold and responds to the input confirmation operation. On the one hand, predicting by multiple parameters can effectively avoid misjudgment of a single parameter, and on the other hand, it can realize the automatic start of the intra-aortic balloon counterpulsation system, saving manpower and time costs, and improving processing efficiency and accuracy.

[0060] In one possible implementation, see Figure 4 The method provided in this embodiment of the invention further includes: S51. If the processor generates a second request when the heart index of the target user is greater than the second threshold within the target time period.

[0061] Specifically, the second request is used to request the control of the intra-aortic balloon counterpulsation system to be turned off at a second time, wherein the target time period is located within a future time period, and the second time period is the end time of the target time period; In one example, the second threshold is 2.5 L / min / m 2 The target time period is 30 minutes. This can also be understood as the target user's cardiac index remaining above 2.5 L / min / m² for 30 minutes. 2 In this case, the second time point is the end time of 30 minutes.

[0062] S52, In response to the input confirmation operation of the second request, the processor shuts down the intra-aortic balloon counterpulsation system at the second moment.

[0063] The method provided in this invention calculates multiple parameters included in the hemodynamic monitoring signal and predicts the cardiac index for a future time period based on a neural network model. When the cardiac index is greater than a second threshold and continues for a target time period, the method controls the shutdown of the intra-aortic balloon counterpulsation system in response to the input confirmation operation. On the one hand, predicting through multiple parameters can effectively avoid misjudgment of a single parameter. On the other hand, it can realize the automatic shutdown of the intra-aortic balloon counterpulsation system, saving manpower and time costs and improving processing efficiency and accuracy.

[0064] In some embodiments, the method provided by the present invention further includes: If the processor generates a first alarm message when the fluctuation range of the target user's cardiac index is greater than ±15% at multiple times in the future time period, the first alarm message is used to indicate an abnormality in the intra-aortic balloon counterpulsation system.

[0065] For example, the target user's cardiac index at time i within a future time period is 2.2 L / min / m. 2 The target user's cardiac index at time i+1 within a future time period is 2.4 L / min / m. 2 In this case, if the target user's cardiac index fluctuates by 8% across multiple moments in the future time period, the processor will not generate the first alarm message. In another example, the target user's cardiac index at the i-th moment in the future time period is 2 L / min / m. 2 The target user's cardiac index at time i+1 within a future time period is 2.5 L / min / m. 2 If the fluctuation range of the target user's heart index at multiple moments in the future time period is 20%, the processor will generate the first alarm message.

[0066] The method provided in this invention effectively monitors the fluctuation range of cardiac indexes and generates a first alarm message when the fluctuation range of cardiac indexes exceeds a preset range, so that operators can handle the situation in a timely manner, thereby improving the safety and stability of the intra-aortic balloon counterpulsation system and enhancing the user experience.

[0067] In other embodiments, the processor refers to [reference needed] before generating the first request or the second request. Figure 5 The method provided in this embodiment of the invention further includes: S61, The processor determines the target user's cardiac index offset rate.

[0068] Specifically, the formula for determining the target user's cardiac index offset rate C is as follows: CI1 represents the cardiac index included in the hemodynamic monitoring signal of the target user; CI2 represents the cardiac index obtained from the echocardiogram of the target user.

[0069] In one possible implementation, the counterpulsation system 100 further includes an electrocardiogram monitoring module for acquiring an echocardiogram of the target user and determining the target user's cardiac index based on the echocardiogram.

[0070] S62. If the target user's cardiac index deviation rate is greater than 15%, the processor generates a second alarm message. The second alarm message is used to indicate that the reliability of the hemodynamic monitoring signal is abnormal.

[0071] As can be seen from the above, the method provided by the embodiments of the present invention verifies the credibility of cardiac indices included in hemodynamic monitoring signals by using cardiac indices obtained from echocardiography. When the cardiac index deviation rate is greater than a preset range, a second alarm message is generated, enabling operators to handle the situation in a timely manner. This avoids controlling the intra-aortic balloon counterpulsation system based on data with low credibility, thereby improving the safety and stability of the intra-aortic balloon counterpulsation system and enhancing the user experience.

[0072] In some other embodiments, see Figure 6 Before the processor generates the first request or the second request, the method provided in this embodiment of the invention further includes: S71, The processor determines the cylinder pressure fluctuation rate of the intra-aortic balloon counterpulsation system.

[0073] Specifically, the formula for determining the cylinder pressure fluctuation rate P is: Among them, P t Let P be the cylinder pressure at time t, and max(P) t ) represents the maximum cylinder pressure within the time window, min(P) t ) represents the minimum cylinder pressure within the time window, mean(P) t The average cylinder pressure within the time window is denoted as .

[0074] S72. When the cylinder pressure fluctuation rate of the intra-aortic balloon counterpulsation system is greater than 20%, the processor generates a third alarm message. The third alarm message is used to indicate the abnormal air tightness of the intra-aortic balloon counterpulsation system.

[0075] As can be seen from S71-S72 above, the method provided by the embodiments of the present invention monitors the fluctuation rate of cylinder pressure and can generate a third alarm message when the fluctuation rate is abnormal. This allows the operator to check the airtightness of the cylinder of the intra-aortic balloon counterpulsation system, avoiding the need to control the start or stop of the intra-aortic balloon counterpulsation system when the airtightness of the cylinder is problematic. This improves the safety and stability of the intra-aortic balloon counterpulsation system and enhances the user experience.

[0076] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A control method for an intra-aortic balloon counterpulsation system based on hemodynamics, characterized in that, An intra-aortic balloon counterpulsation system is used, comprising an air cylinder, an air cylinder, an air balloon, a hemodynamic monitoring module, a processor, and a motor; the air cylinder, air cylinder, and air balloon are connected via an air circuit. The processor is electrically connected to the motor and the hemodynamic monitoring module respectively, and the motor is connected to the cylinder; The method includes: The hemodynamic monitoring module acquires the target user's hemodynamic monitoring signals in real time, including global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output. The processor, based on a pre-trained neural network model, determines the cardiac index of the target user at multiple moments in the future time period according to the target user's total end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output at multiple moments in the historical time period. If the processor generates a first request when the cardiac index of the target user at a first moment is less than a first threshold, the first request is used to request the activation of the intra-aortic balloon counterpulsation system at the first moment, wherein the first moment is one of a plurality of moments within the future time period; In response to the input confirmation operation of the first request, the processor activates the intra-aortic balloon counterpulsation system at the first moment.

2. The method according to claim 1, characterized in that, The first threshold CI threshold The formula for determining it is: CI threshold =(α1A1+α2A2+α3A3)×CI base ; A1 = Age / 70; Where α1 is the first weighting coefficient, α2 is the second weighting coefficient, and α3 is the third weighting coefficient; A1 is the age influence factor; Age is the target user's age; A2 is the blood pressure influence factor; BP is the target user's maximum blood pressure; A3 is the ventilation status influence factor; and when the target user's ventilation status is mechanical ventilation, A3 = 1.5, and when the target user's ventilation status is non-mechanical ventilation, A3 = 1, CI base Preset heart rate index.

3. The method according to claim 2, characterized in that, The formula for determining the first weighting coefficient α1, the second weighting coefficient α2, and the third weighting coefficient is α3: Where S1 is the cardiac index deviation rate, S2 is the rate of change of global end-diastolic volume, S3 is the lung water volume ratio, and μ is the sensitivity coefficient.

4. The method according to claim 3, characterized in that, The method further includes: If the processor generates a second request when the cardiac index of the target user is greater than a second threshold during the target time period, the second request is used to request the control of the intra-aortic balloon counterpulsation system to be turned off at a second moment, wherein the target time period is located within the future time period, and the second moment is the end time of the target time period; In response to the input confirmation operation of the second request, the processor shuts down the intra-aortic balloon counterpulsation system at the second moment.

5. The method according to claim 4, characterized in that, The method further includes: If the processor generates a first alarm message when the fluctuation range of the target user's cardiac index at multiple times in the future time period is greater than ±15%, the first alarm message is used to indicate that the intra-aortic balloon counterpulsation system is abnormal.

6. The method according to claim 5, characterized in that, Before the processor generates the first request or the processor generates the second request, the method further includes: The processor determines the target user's cardiac index offset rate; If the processor generates a second alarm message when the target user's cardiac index deviation rate is greater than 15%, the second alarm message is used to indicate that the reliability of the hemodynamic monitoring signal is abnormal. The formula for determining the target user's cardiac index offset rate C is as follows: Wherein, CI1 is the cardiac index included in the hemodynamic monitoring signal of the target user; CI2 is the cardiac index obtained from the echocardiogram of the target user.

7. The method according to claim 6, characterized in that, Before the processor generates the first request or the processor generates the second request, the method further includes: The processor determines the cylinder pressure fluctuation rate of the intra-aortic balloon counterpulsation system. When the cylinder pressure fluctuation rate of the intra-aortic balloon counterpulsation system is greater than 20%, the processor generates a third alarm message, which is used to indicate an abnormality in the air tightness of the intra-aortic balloon counterpulsation system. The formula for determining the cylinder pressure fluctuation rate P is: Among them, P t Let P be the cylinder pressure at time t, and max(P) t ) represents the maximum cylinder pressure within the time window, min(P) t ) represents the minimum cylinder pressure within the time window, mean(P) t The average cylinder pressure within the time window is denoted as .

8. The method according to claim 7, characterized in that, Before the processor determines the cardiac index of the target user at multiple moments in a future time period based on a pre-trained neural network model, according to the target user's total end-diastolic volume, stroke variability, extravascular pulmonary edema, cardiac index, and cardiac output at multiple moments within a historical time period, the method further includes: The processor acquires multiple training samples. Each training sample includes the whole heart end-diastolic volume, stroke variability, extravascular lung water, cardiac index and cardiac output of the sample user at multiple moments within a historical time period, as well as the cardiac index of the sample user at a target moment after the historical time period. The processor iteratively trains the neural network model based on the multiple training samples to obtain the pre-trained neural network model.

9. The method according to claim 8, characterized in that, When the hemodynamic monitoring module and the balloon are positioned within the same artery of the target user, after the hemodynamic monitoring module acquires the target user's hemodynamic monitoring signal in real time, the method further includes: The processor filters out signals in the hemodynamic monitoring signal whose frequency is less than or equal to a preset threshold.

10. A control system for an intra-aortic balloon counterpulsation system based on hemodynamics, characterized in that, An intra-aortic balloon counterpulsation system is used, comprising an air cylinder, an air cylinder, an air balloon, a hemodynamic monitoring module, a processor, and a motor; the air cylinder, air cylinder, and air balloon are connected via an air circuit; the processor is electrically connected to the motor and the hemodynamic monitoring module respectively, and the motor is connected to the air cylinder; The hemodynamic monitoring module is used for: Real-time acquisition of hemodynamic monitoring signals of the target user, including global end-diastolic volume, stroke variability, extravascular lung water, cardiac index, and cardiac output; The processor is used for: Based on a pre-trained neural network model, the cardiac index of the target user is determined according to the total end-diastolic volume, stroke variability, extravascular lung water, cardiac index and cardiac output of the target user at multiple moments in the historical time period. If the cardiac index of the target user at a first moment is less than a first threshold, a first request is generated. The first request is used to request the activation of the intra-aortic balloon counterpulsation system at the first moment, wherein the first moment is one of a plurality of moments within the future time period. In response to the input confirmation operation of the first request, the intra-aortic balloon counterpulsation system is activated at the first moment.

Images