A method, apparatus, device, and storage medium for controlling a heart pump.

Abstract

This invention discloses a method, apparatus, device, and storage medium for controlling a heart pump. The method includes: acquiring a target blood flow value of a target object; inputting the target blood flow value into a pre-trained target preload prediction model to obtain a preload prediction value; and adjusting the rotational speed of the target heart pump based on the preload prediction value and a preset preload reference standard. This invention addresses the safety issues inherent in prior art where heart pump rotational speed is controlled by collecting blood pressure and blood flow signals. It allows for adjustment of the heart pump rotational speed based on the object's preload prediction value, thereby improving the safety of the heart pump rotational speed control process.

Description

Technical Field

[0001] The present invention relates to the field of artificial heart control technology, and in particular to a heart pump control method, apparatus, device and storage medium. Background Technology

[0002] The cardiac pump is a crucial instrument in the treatment and transition phase of transplantation for patients with severe heart failure. The pump's rotational speed is a vital parameter for ensuring the safety of the patient's circulatory system. Current technology uses blood pressure and blood flow signals, employs a suction reflux detector to determine the degree of reflux, and combines this with a pre-set physiological reference model to control the pump's rotational speed. However, blood pressure and blood flow are insufficient to directly reflect the heart's pressure status. Adjusting the pump's speed based solely on blood pressure and blood flow poses certain safety risks, potentially leading to dangerous events such as ventricular collapse and excessive pulmonary fluid accumulation. Summary of the Invention

[0003] This invention provides a method, apparatus, device, and storage medium for controlling a heart pump, which can adjust the speed of the heart pump accordingly based on the predicted preload value of the object, thereby improving the safety of the heart pump speed control process.

[0004] In a first aspect, embodiments of the present invention provide a method for controlling a heart pump, the method comprising:

[0005] Obtain the target blood flow value of the target object;

[0006] The target blood flow value is input into a pre-trained target preload prediction model to obtain the preload prediction value;

[0007] The rotational speed of the target heart pump is adjusted based on the predicted preload value and the preset preload reference standard.

[0008] In a second aspect, embodiments of the present invention provide a heart pump control device, the device comprising:

[0009] The blood flow value acquisition module is used to acquire the target blood flow value of the target object;

[0010] The preload prediction value determination module is used to input the target blood flow value into a pre-trained target preload prediction model to obtain the preload prediction value;

[0011] The heart pump speed adjustment module is used to adjust the speed of the target heart pump according to the predicted preload value and the preset preload reference standard.

[0012] Thirdly, embodiments of the present invention provide a heart pump control system, the system comprising:

[0013] Preload prediction subsystem, heart pump speed regulation subsystem, and heart pump;

[0014] The preload prediction subsystem includes a blood flow determination module and a preload prediction module. The blood flow determination module is used to predict the blood flow of the target object based on the cardiovascular and cardiac pump coupling model to determine the target blood flow value. The preload prediction module is used to input the target blood flow value into a pre-trained target preload prediction model to obtain a preload prediction value, and send the preload prediction value to the cardiac pump speed regulation subsystem.

[0015] The heart pump speed regulation subsystem includes a speed adjustment value determination module and a heart pump speed adjustment module; wherein, the speed adjustment value determination module is used to determine a preload deviation value based on the preload prediction value and a preset preload reference standard, and to determine the heart pump speed adjustment amount corresponding to the preload deviation value; the heart pump speed adjustment module is used to adjust the speed of the heart pump based on the heart pump speed adjustment amount.

[0016] The heart pump includes a physical quantity detection module, which is used to detect the rotational speed and current of the heart pump and send the rotational speed and current of the heart pump to the blood flow determination module, so that the blood flow determination module determines the target blood flow value based on the rotational speed and current of the heart pump.

[0017] Fourthly, embodiments of the present invention provide a computer device, the computer device comprising:

[0018] One or more processors;

[0019] Memory, used to store one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the heart pump control method described in any embodiment.

[0021] Fifthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the heart pump control method described in any embodiment.

[0022] The technical solution provided by this invention involves acquiring the target blood flow value of a target object; inputting the target blood flow value into a pre-trained target preload prediction model to obtain a preload prediction value; and adjusting the rotational speed of the target heart pump based on the preload prediction value and a preset preload reference standard. This invention solves the safety problem inherent in prior art where heart pump rotational speed is controlled by collecting blood pressure and blood flow signals. It improves the safety of heart pump rotational speed control by adjusting the rotational speed based on the object's preload prediction value. Attached Figure Description

[0023] Figure 1 This is a flowchart of a heart pump control method provided in an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of another heart pump control method provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of a cardiovascular and cardiac pump coupling model provided in an embodiment of the present invention;

[0026] Figure 4 This is a flowchart of the training process for a target preload prediction model provided in an embodiment of the present invention;

[0027] Figure 5 This is a flowchart illustrating the operation of an adaptive sliding mode controller for controlling the speed of a heart pump, as provided in an embodiment of the present invention.

[0028] Figure 6 This is a flowchart of a heart pump control process provided by an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram illustrating the change in aortic pressure value provided in an embodiment of the present invention;

[0030] Figure 8 This is a schematic diagram illustrating the changes in aortic pressure values ​​in another experimental group provided in this embodiment of the invention;

[0031] Figure 9 This is a schematic diagram of the structure of a heart pump control device provided in an embodiment of the present invention;

[0032] Figure 10 This is a schematic diagram of the structure of another heart pump control device provided in an embodiment of the present invention;

[0033] Figure 11 This is a schematic diagram of a heart pump control system provided in an embodiment of the present invention.

[0034] Figure 12This is a schematic diagram of another heart pump control system provided in an embodiment of the present invention;

[0035] Figure 13 This is a flowchart of a heart pump control system provided in an embodiment of the present invention;

[0036] Figure 14 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] Figure 1 This is a flowchart of a heart pump control method provided by an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where the rotational speed of a heart pump is controlled. The method can be executed by a heart pump control device, which can be implemented by software and / or hardware.

[0039] like Figure 1 As shown, the heart pump control method includes the following steps:

[0040] S110, Obtain the target blood flow value of the target object.

[0041] The target object can be any object that requires a cardiac pump to maintain pressure perfusion and provide sufficient cardiac output. The target blood flow value can be the blood flow value that needs to be used for subsequent cardiac pump control. Since the preload value needs to be calculated later, and the preload value represents the load value of the left ventricle of the heart, the blood flow value of the left ventricle can be used as the target blood flow value to simplify the processing steps.

[0042] Furthermore, the blood flow value of the target object can be detected by a preset blood flow detection device, and the target blood flow value can be obtained by acquiring the detection value of the blood flow detection device.

[0043] Furthermore, blood flow to a target object can be predicted using a pre-defined cardiovascular and cardiac pump coupling model to obtain the target blood flow value. This model comprises the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, pulmonary vein, cardiac pump, and the connecting pathways between these components. The cardiovascular and cardiac pump coupling model structure may vary depending on the type of target object. The model can predict the target blood flow value based on physical quantities such as the cardiac pump's rotational speed and current.

[0044] S120. Input the target blood flow value into the pre-trained target preload prediction model to obtain the preload prediction value.

[0045] The target preload prediction model can be a model used to predict the preload value of the target object. Preload can be the resistance or load encountered by the myocardium before contraction, that is, the volume load or pressure borne by the ventricle at end-diastole. The preload value is actually a response to the ventricular end-diastolic volume or ventricular end-diastolic wall tension, and is related to the amount of venous return. Preload value can more intuitively reflect the pressure status of the heart. Therefore, obtaining the preload value and controlling the speed of the heart pump accordingly based on the preload value can greatly reduce the occurrence of dangerous events such as ventricular collapse and excessive pulmonary fluid.

[0046] Since preload values ​​cannot be directly obtained through detection equipment, preload prediction values ​​can be made based on a pre-trained target preload prediction model. By inputting the target blood flow value into the pre-trained target preload prediction model, the predicted value of the target object's preload, i.e., the preload prediction value, can be obtained.

[0047] S130. Adjust the rotational speed of the target heart pump according to the predicted preload value and the preset preload reference standard.

[0048] The preset preload reference standard can be a preset standard range of preload values. For example, in this embodiment of the invention, the preset preload reference standard can be 3-15 mmHg. When the target object's preload value is within this standard range, it indicates that the target object's preload value is in a normal state and no adjustment is needed; while when the target object's preload value is not within this standard range, it indicates that the target object's preload value is in an abnormal state and the speed of the heart pump needs to be adjusted, thereby adjusting the target object's preload value to restore it to a normal level.

[0049] A target heart pump can be a heart pump used to maintain pressure perfusion and provide cardiac output to a target individual. After obtaining the predicted preload value, the speed of the target heart pump can be adjusted according to the predicted preload value and a preset preload reference standard.

[0050] Specifically, the preload prediction value can be compared with the maximum or minimum value of the closest preset preload reference standard to determine the preload deviation value; then, based on the preload prediction value and the preset preload reference standard, the preload deviation value is determined; according to the correspondence between the preload deviation value and the heart pump speed, the heart pump speed adjustment amount corresponding to the preload deviation value is determined; and a speed adjustment command signal is sent to the target heart pump according to the heart pump speed adjustment amount to adjust the speed of the target heart pump.

[0051] The technical solution provided by this invention involves acquiring the target blood flow value of a target object; inputting the target blood flow value into a pre-trained target preload prediction model to obtain a preload prediction value; and adjusting the rotational speed of the target heart pump based on the preload prediction value and a preset preload reference standard. This invention solves the safety problem inherent in prior art where heart pump rotational speed is controlled by collecting blood pressure and blood flow signals. It improves the safety of heart pump rotational speed control by adjusting the heart pump rotational speed based on the object's preload prediction value.

[0052] Figure 2 This is a flowchart of another heart pump control method provided by an embodiment of the present invention. This embodiment is applicable to scenarios where the rotational speed of a heart pump needs to be controlled. Based on the above embodiments, this embodiment further explains how to obtain the target blood flow value of the target object and how to adjust the rotational speed of the target heart pump according to the predicted preload value and the preset preload reference standard. This device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0053] like Figure 2 As shown, the heart pump control method includes the following steps:

[0054] S210. Construct a cardiovascular and cardiac pump coupling model based on the blood flow characteristic parameters of the target object.

[0055] The target population can be patients who require a cardiac pump to maintain pressure perfusion and provide adequate cardiac output. Hemodynamic parameters can be parameters related to the target population's physical characteristics. Specifically, hemodynamic parameters may include mitral valve closure, aortic valve closure, tricuspid valve closure, and pulmonary valve closure; mitral valve resistance, aortic valve resistance, aortic resistance, peripheral systemic resistance, venous systemic resistance, tricuspid valve resistance, pulmonary valve resistance, pulmonary artery resistance, peripheral pulmonary resistance, and venous pulmonary resistance; aortic blood inertia, pulmonary artery blood inertia, etc. These hemodynamic parameters can be set by relevant experts based on the target population's physical characteristics. The accuracy of these parameters is crucial for establishing a subsequent cardiovascular-cardiac pump coupling model.

[0056] A cardiovascular-cardiac pump coupling model is a model that couples the relationship between the cardiovascular system and the cardiac pump of a target object. This model can predict blood flow values ​​in the cardiovascular system based on the rotational speed of the cardiac pump. Specifically, the components of the cardiovascular-cardiac pump coupling model include the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, pulmonary vein, cardiac pump, and the connecting pathways between these components.

[0057] For example, Figure 3 This is a schematic diagram of a cardiovascular and cardiac pump coupling model provided in an embodiment of the present invention. Figure 3 As shown, the cardiovascular and cardiac pump coupling model consists of three parts: the heart, systemic circulation, and pulmonary circulation. The four chambers of the heart are each represented by a separate elastic cavity; the systemic circulation, aorta, and arteries are each represented by separate elastic cavities; arterioles and the capillary network share a single elastic cavity; veins are represented by separate elastic cavities; and the pulmonary circulation follows the same principle.

[0058] Figure 3 In the diagram, following the blood flow direction counterclockwise, the heart consists of the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, and pulmonary vein. The uppermost part, passing through RS and returning to the left atrium from right to left, represents the entire systemic-pulmonary circulation. The dashed ellipse represents the cardiac pump, which is connected in parallel between the left ventricle and the aorta. The most important time-varying variable in the model is the volumetric characteristic of the left ventricle, reflected by a time-varying capacitance value Clv(t), which is the reciprocal of the ventricular elasticity function E(t). Where P... la (t), P lv (t), P ao (t), P sar (t), P sv (t), P ra (t), P rv (t), P pa(t), P par (t), P pv (t) represents the blood pressure in the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, and pulmonary vein, respectively; C la (t), C lv (t), C ao (t), C sar (t), C sv (t), C ra (t), C rv (t), C pa (t), C par (t), C pv (t) represent the compliance of the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, and pulmonary vein, respectively. The blood vessel walls are elastic, and compliance characterizes the degree to which blood vessel volume changes with blood pressure. Diode D mv D av D tv D pv These represent the mitral valve, aortic valve, tricuspid valve, and pulmonary valve, respectively; their patency and deactivation represent the opening and closing of the valves, respectively. R mv R av R ao R svr R sv R tv R pv R pa R pvr R pv These are, respectively, mitral valve resistance, aortic valve resistance, aortic flow resistance, peripheral systemic resistance, venous systemic resistance, tricuspid valve resistance, pulmonary valve resistance, pulmonary artery flow resistance, peripheral pulmonary resistance, and venous pulmonary resistance; L ao and L pa These represent the blood inertia of the aorta and pulmonary artery, respectively. The model of this invention includes almost all organs of the cardiovascular system, making it more realistic and accurate. This model allows for the acquisition of real-time blood flow information, i.e., a dynamic curve of blood flow over time.

[0059] S220. Based on the cardiovascular and cardiac pump coupling model, predict the blood flow of the target object to obtain the target blood flow value.

[0060] The target blood flow value can be the blood flow value needed for subsequent cardiac pump control. Since the preload value needs to be calculated later, and the preload value represents the load on the left ventricle of the heart, the blood flow value of the left ventricle can be used as the target blood flow value to simplify the calculation process. Specifically, a system of differential equations can be established for the cardiac, systemic, and pulmonary circulations, and then solved to obtain a curve showing the change in blood flow over time. The specific system of differential equations is as follows:

[0061] Left heart part:

[0062]

[0063]

[0064] Right heart region:

[0065]

[0066]

[0067] Systemic circulation:

[0068]

[0069]

[0070]

[0071]

[0072] Pulmonary circulation section:

[0073]

[0074]

[0075]

[0076]

[0077] Heart pump component:

[0078]

[0079]

[0080] Wherein, P represents blood pressure (at different sites); Q represents blood flow (at different sites); C represents compliance (at different sites); R represents blood flow resistance (at different sites); L represents blood inertia (at different sites); H represents the pressure difference between the inlet and outlet of the cardiac pump; ω represents the rotational speed of the cardiac pump; and β is the kinetic coefficient of the cardiac pump. The relationship between cardiac pump rotational speed, blood flow, and blood pressure can be analyzed from the above differential equations, laying the foundation for obtaining real-time blood flow values ​​and subsequent processing. Furthermore, since this embodiment of the invention does not require the implantation of a pressure sensor when obtaining blood flow values, it reduces the risk of infection for heart failure patients.

[0081] S230. Input the target blood flow value into the pre-trained target preload prediction model to obtain the preload prediction value.

[0082] The target preload prediction model can be a model used to predict the preload value of a target object. Preload can be the resistance or load encountered by the myocardium before contraction, that is, the volume load or pressure borne by the ventricle at end-diastole. The preload value is actually a response to the ventricular end-diastolic volume or ventricular end-diastolic wall tension, and is related to the amount of venous return. Preload value can more intuitively reflect the pressure status of the heart. Therefore, obtaining the preload value and controlling the speed of the heart pump accordingly based on the preload value can greatly reduce the occurrence of dangerous events such as ventricular collapse and excessive pulmonary fluid. However, since the preload value cannot be directly detected by the detection equipment, the preload prediction value can be predicted based on a pre-trained target preload prediction model. By inputting the target blood flow value into the pre-trained target preload prediction model, the predicted value of the target object's preload, i.e., the preload prediction value, can be obtained.

[0083] The training process of the target preload prediction model includes: acquiring a preset blood flow sample set; inputting the preset blood flow sample set into the initial preload prediction model to obtain preload prediction sample values; determining the model loss function value based on the preload prediction sample value and the preset preload sample value in the preset blood flow sample set; and adjusting the parameter values ​​of the initial preload prediction model based on the model loss function value to obtain the target preload prediction model.

[0084] For example, Figure 4 This is a flowchart illustrating the training process of a target preload prediction model provided in an embodiment of the present invention. Figure 4As shown, the training process of the target preload prediction model includes: First, the periodic cardiac pumping blood flow signal is used as training samples to input a heuristic peak detector to identify the peak value of cardiac pumping blood flow. Since the blood flow peak is located at the inflection point of the blood flow curve and shows significant change, it is a prominent feature of the left ventricle pumping blood into the aorta and is most suitable as a feature vector input into the initial preload prediction model. Second, the processed samples are input into convolutional layers, where the filter sizes of the four convolutional layers are 30×3, 20×3, 10×5, and 7×10, respectively, and each convolutional layer includes a batch normalization layer. Third, the data processed in the second step is input into max pooling layers, where the filter sizes are 7×10 and 5×10, with a stride of 2. Fourth, the data processed in the third step is input into two convolutional layers, both with a filter size of 3×10. Finally, fully connected layers with 100 and 20 neurons, a LeakyReLU activation function, and a lossy layer with a probability of 20% are used to estimate the preload.

[0085] S240. Determine the preload deviation value based on the predicted preload value and the preset preload reference standard.

[0086] The preset preload reference standard can be a preset standard range of preload values. For example, in this embodiment of the invention, the preset preload reference standard can be 3-15 mmHg. When the target object's preload value is within this standard range, it indicates that the target object's preload value is in a normal state and no adjustment is needed; conversely, when the target object's preload value is outside this standard range, it indicates that the target object's preload value is in an abnormal state and the heart pump speed needs to be adjusted to restore the target object's preload value to a normal level. The preload deviation value can be the deviation between the predicted preload value and the preset preload reference standard. Specifically, the preload deviation value can be determined by subtracting the predicted preload value from the maximum or minimum value of the closest preset preload reference standard.

[0087] S250. Based on the correspondence between the preload deviation value and the heart pump speed, determine the amount of heart pump speed to be adjusted corresponding to the preload deviation value.

[0088] The adjustable amount of the heart pump speed can be the value by which the heart pump speed needs to be adjusted. Specifically, the adjustable amount of the heart pump speed corresponding to the preload deviation value can be determined based on the correspondence between the preload deviation value and the heart pump speed. For example, the pseudo-order of the controller can be determined first based on multiple heart pump speed values ​​collected at preset time intervals; the pseudo-gradient of the controller can be determined based on the pseudo-order of the controller and the speed increments corresponding to the multiple heart pump speed values; and the adjustable amount of the heart pump speed can be determined based on the pseudo-order of the controller, the pseudo-gradient of the controller, and the preload deviation value. The pseudo-order of the controller can be the pseudo-order of the controller controlling the heart pump speed. The pseudo-gradient of the controller can be the pseudo-gradient of the controller controlling the heart pump speed. To improve the control efficiency of the heart pump speed, a synovial controller can be used as the controller for the heart pump speed.

[0089] The steps for determining the adjustment amount of the heart pump speed corresponding to the preload deviation value, based on the correspondence between the preload deviation value and the heart pump speed, are as follows:

[0090] a. Determine the pseudo-order L of the controller y and L u Construct the input and output data sequences using the following formula:

[0091]

[0092] In the formula, y(k) represents the controller output at time k, and Δy(k) represents the increment between two adjacent times; u(k) represents the controller input at time k, and Δu(k) represents the increment between two adjacent times; T represents matrix transpose; L y and L u This is called the pseudo-order of the controller; H Ly,Lu (k) is a vector defined according to the nonparametric dynamic linearization theory of the SISO controller, and its expression is:

[0093]

[0094] In the formula, ΔH Ly,Lu (k) represents two adjacent times H Ly,Lu The increment vector of vector (k).

[0095] b. Estimate the pseudo-gradient of the controller using the following formula (the time-varying parameter vector of the controller pseudo-gradient is generally defined).

[0096] Meaning Φ f,Ly,Lu (k)):

[0097]

[0098] In the formula, η represents the estimated value of the pseudo gradient at time k; μ represents the step size factor; and μ represents the weight factor.

[0099] c. Calculate the control input increment Δu(k) using the following formula:

[0100]

[0101] In the formula, λ v denoted as adaptive weight factor; s(k) is the sliding surface, defined as s(k)=k1Δy(k)+k2e(k), where k1 and k2 represent adjustable parameters of the sliding surface, e(k) is the tracking error, e(k)=y(k)-r(k), where r(k) is the reference value; Represents the pseudo-partial derivative; h is the discrete period; q1, q2 and α are the sliding mode controller parameters, 0 <q1h<1,0<q2h<1,0<α<1;sig α (s(k))=sgn(s(k))·|s(k)| α sgn() is the sign function. Here, Δu(k) is the amount of heart pump speed to be adjusted.

[0102] S260. Send a speed adjustment command signal to the target heart pump according to the heart pump speed adjustment amount, so as to adjust the speed of the target heart pump.

[0103] The target heart pump can be a heart pump used to maintain pressure perfusion and provide cardiac output for the target subject. The speed adjustment command signal can be a command signal used to adjust the speed of the target heart pump. After determining the amount of speed adjustment to be made for the heart pump, a speed adjustment command signal can be sent to the target heart pump according to the amount of speed adjustment to adjust the speed of the target heart pump.

[0104] In one optional implementation, the motor used in the target heart pump is a bearingless permanent magnet motor, and the speed control method of the bearingless permanent magnet motor is a dual closed-loop feedback control. Before sending the speed adjustment command signal to the target heart pump, the speed adjustment command signal can be first transformed by IPARK (converting the rotating dq coordinate system to the stationary αβ coordinate system), then sent to the inverter through Space Vector Pulse Width Modulation (SVPWM), and finally acted on the bearingless permanent magnet motor inside the target heart pump. The rotor of the bearingless permanent magnet motor drives the impeller of the target heart pump to rotate to complete the pumping and physiological regulation. Through adaptive adjustment of the speed, the preload control is finally completed.

[0105] For example, Figure 5 This is a flowchart illustrating the workflow of an adaptive sliding mode controller for controlling the speed of a heart pump, as provided in an embodiment of the present invention. Figure 5As shown, the workflow of the adaptive sliding mode controller controlling the speed of the heart pump includes: firstly, the estimated value of the preload is subtracted from the expected value of the preload (3-15 mmHg), and the resulting deviation value is input into the controller. This deviation value is then used as a reference input into the controller, which calculates the control input (using a built-in model formula) and transmits it to the heart pump motor to control its speed. Simultaneously, the real-time speed information output by the heart pump is fed back to the controller, forming a closed-loop control to ensure that the preload is controlled within the expected value (3-15 mmHg) in real time. This invention uses a model-free adaptive sliding mode controller to achieve preload control. Compared to other adaptive controllers (such as artificial neural networks and fuzzy controllers), it has a simpler structure, reduces computational burden and time, and improves the system's response speed.

[0106] For example, Figure 6 This is a flowchart illustrating a process for controlling a heart pump, as provided in an embodiment of the present invention. Figure 6 As shown, the workflow for controlling the heart pump includes: Step 1: Establishing a coupling model between the cardiovascular system and the heart pump; Step 2: Designing a deep convolutional neural network to obtain the estimated preload value; Step 3: Designing a model-free parameter adaptive sliding mode controller to import the estimated and expected preload values ​​into the controller; Step 4: After processing the calculation, the controller issues a pump speed adjustment command to change the speed so that the preload value can track the expected value.

[0107] To verify the effectiveness of the technical solution provided in the embodiments of the present invention, experiments were conducted based on the above-described cardiac pump control method. For example, Figure 7 This is a schematic diagram illustrating the change in aortic pressure value provided by an embodiment of the present invention. In this embodiment, the control method and the cardiovascular-cardiac pump coupling system model are simulated using Simulink modeling and m-file encoding. After setting the parameters, the simulation model is run to obtain the hemodynamics of the cardiac pump and the changes in preload with time and pump speed. The hemodynamics are represented only by the important cardiovascular indicator—aortic pressure; heart rate and cardiac output are not analyzed. The aortic pressure results are as follows... Figure 7 As shown, when the heart pump controlled by the present invention is used in the heart failure heart, the aortic pressure ranges from 88 to 119 mmHg, and the average aortic pressure can be maintained at around 100 mmHg, which are all within the normal physiological range. This indicates that the heart pump controlled by the present invention can help patients with damaged hearts obtain sufficient blood perfusion.

[0108] Figure 8 This is a schematic diagram illustrating the changes in aortic pressure values ​​in another experimental group provided in an embodiment of the present invention. (See diagram below.) Figure 8As shown, to highlight the effectiveness of preload estimation, a set of measurement experiments was added for comparison. Simultaneously, to verify the response of the method of this invention to different patient states, the process was divided into two segments by modifying some parameter values ​​of the cardiovascular system and cardiac pump coupling model: the first half represents the exercise state, and the second half represents the resting state. From... Figure 8 As can be seen, in the first half, the estimated and measured values ​​of preload largely overlap, indicating that the deep convolutional neural network model has a good estimation effect. At this time, the heart pump speed fluctuates within a small range to maintain preload. After transitioning from exercise to rest, the estimated preload curve fluctuates to some extent relative to the measured curve, but the preload value can still be controlled within the range of 3-15 mmHg. Moreover, the fluctuation stabilizes and tracks the measured curve after a brief adjustment. At this time, the heart pump speed also continuously decreases to maintain preload and remains stable after modulation, indicating that the method of this invention has a strong adjustment capability in response to emergencies. In summary, the method of this invention can accurately control the preload value within the range of 3-15 mmHg and can adjust according to changes in the patient's condition. It can effectively avoid aspiration and pulmonary hemorrhage in different states, maintain adequate blood perfusion, and improve the quality of life of heart failure patients.

[0109] The technical solution provided by this invention constructs a cardiovascular and cardiac pump coupling model based on the blood flow characteristic parameters of the target object; predicts the blood flow of the target object according to the cardiovascular and cardiac pump coupling model to obtain the target blood flow value; inputs the target blood flow value into a pre-trained target preload prediction model to obtain the preload prediction value; determines the preload deviation value based on the preload prediction value and a preset preload reference standard; determines the cardiac pump speed adjustment amount corresponding to the preload deviation value according to the correspondence between the preload deviation value and the cardiac pump speed; and sends a speed adjustment command signal to the target cardiac pump according to the cardiac pump speed adjustment amount to adjust the speed of the target cardiac pump. This invention solves the safety problem of insufficient control of cardiac pump speed by collecting blood pressure and blood flow signals in the prior art, and improves the safety of cardiac pump speed control by adjusting the cardiac pump speed based on the object's preload prediction value.

[0110] Figure 9 This is a schematic diagram of a heart pump control device provided in an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where the speed of a heart pump is controlled. The device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0111] like Figure 9 As shown, the heart pump control device includes: a blood flow value acquisition module 310, a preload prediction value determination module 320, and a heart pump speed adjustment module 330.

[0112] The system includes a blood flow value acquisition module for acquiring the target blood flow value of the target object; a preload prediction value determination module for inputting the target blood flow value into a pre-trained target preload prediction model to obtain the preload prediction value; and a heart pump speed adjustment module for adjusting the speed of the target heart pump based on the preload prediction value and a preset preload reference standard.

[0113] The technical solution provided by this invention involves acquiring the target blood flow value of a target object; inputting the target blood flow value into a pre-trained target preload prediction model to obtain a preload prediction value; and adjusting the rotational speed of the target heart pump based on the preload prediction value and a preset preload reference standard. This invention solves the safety problem inherent in prior art where heart pump rotational speed is controlled by collecting blood pressure and blood flow signals. It improves the safety of heart pump rotational speed control by adjusting the heart pump rotational speed based on the object's preload prediction value.

[0114] In one optional implementation, the blood flow value acquisition module 310 is specifically used to: construct a cardiovascular and cardiac pump coupling model based on the blood flow characteristic parameters of the target object; predict the blood flow of the target object according to the cardiovascular and cardiac pump coupling model to obtain the target blood flow value.

[0115] In one alternative implementation, the components of the cardiovascular and cardiac pump coupling model include the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, pulmonary vein, cardiac pump, and connecting pathways between the components.

[0116] In one optional implementation, the heart pump speed adjustment module 330 is specifically used to: determine a preload deviation value based on the preload prediction value and a preset preload reference standard; determine the heart pump speed adjustment amount corresponding to the preload deviation value according to the correspondence between the preload deviation value and the heart pump speed; and send a speed adjustment command signal to the target heart pump according to the heart pump speed adjustment amount to adjust the speed of the target heart pump.

[0117] In one optional implementation, the heart pump speed adjustment module 330 is specifically used to: determine the pseudo-order of the controller based on multiple heart pump speed values ​​collected at a preset time interval; determine the pseudo-gradient of the controller based on the pseudo-order of the controller and the speed increments corresponding to the multiple heart pump speed values; and determine the amount of heart pump speed to be adjusted based on the pseudo-order of the controller, the pseudo-gradient of the controller, and the preload deviation value.

[0118] In one optional embodiment, the heart pump control device further includes: a preload prediction model training module, used to: acquire a preset blood flow sample set; input the preset blood flow sample set into an initial preload prediction model to obtain preload prediction sample values; determine the model loss function value based on the preload prediction sample value and the preset preload sample value in the preset blood flow sample set, and adjust the parameter values ​​of the initial preload prediction model based on the model loss function value to obtain a target preload prediction model.

[0119] To verify the feasibility of the above method, for example, Figure 10 This is a schematic diagram of another heart pump control device provided in an embodiment of the present invention. Figure 10 As shown, the control device includes a system monitoring interface, a cardiovascular simulation device, a computer, a controller, a drive board, a heart pump, a flow meter, a pressure sensor, a resistance regulator, and connecting tubing. The controller of this device incorporates the control method and system proposed in this invention. After activating the control device and the independently developed heart pump, hemodynamic information can be obtained, thereby completing the preliminary verification of the clinical application of the heart pump and the control method of this invention.

[0120] The heart pump control device provided in the embodiments of the present invention can execute the heart pump control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0121] Figure 11 This is a schematic diagram of a heart pump control system provided by an embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where the speed of the heart pump is controlled. The device can be implemented by software and / or hardware and integrated into a computer device with application development capabilities.

[0122] like Figure 11 As shown, the heart pump control system includes: a preload prediction subsystem, a heart pump speed regulation subsystem, and a heart pump.

[0123] The preload prediction subsystem includes a blood flow determination module and a preload prediction module. The blood flow determination module is used to predict the blood flow of the target object based on the cardiovascular and cardiac pump coupling model to determine the target blood flow value. The preload prediction module is used to input the target blood flow value into the preload prediction model that has been pretrained to obtain the preload prediction value, and then send the preload prediction value to the cardiac pump speed regulation subsystem.

[0124] The cardiac pump speed regulation subsystem includes a speed adjustment value determination module and a cardiac pump speed adjustment module. The speed adjustment value determination module is used to determine the preload deviation value based on the preload prediction value and the preset preload reference standard, and to determine the cardiac pump speed adjustment amount corresponding to the preload deviation value. The cardiac pump speed adjustment module is used to adjust the speed of the cardiac pump based on the cardiac pump speed adjustment amount.

[0125] The heart pump includes a physical quantity detection module, which detects the heart pump's rotational speed and current, and sends the heart pump's rotational speed and current to a blood flow determination module, so that the blood flow determination module can determine a target blood flow value based on the heart pump's rotational speed and current.

[0126] For example, Figure 12 This is a schematic diagram of another heart pump control system provided in an embodiment of the present invention. Figure 12 As shown, the heart pump control system includes a detection module, a calculation module, and an execution module. The detection module includes a cardiovascular circulatory system coupled with a heart pump and a deep convolutional neural network model. The deep convolutional neural network model is used to detect and estimate the blood flow curve output by the cardiovascular circulatory system coupled with the heart pump. The calculation module includes a model-free parameter adaptive sliding mode controller and input / output, used for precise control of the preload value. The execution module includes the heart pump, used to receive control commands from the model-free parameter adaptive sliding mode controller and modulate the pump speed.

[0127] For example, Figure 13 This is a flowchart illustrating the operation of a heart pump control system according to an embodiment of the present invention. Figure 13 As shown, the workflow of the heart pump control system includes: First, acquiring the speed and current of the bearingless permanent magnet motor used in the heart pump; inputting the speed and current into a cardiovascular system-heart pump coupling model to obtain a blood flow curve; then inputting the blood flow curve into a deep convolutional neural network for preload value prediction to obtain a preload estimate; subsequently, a model-free parameter adaptive sliding mode controller determines the speed adjustment signal based on the expected and estimated preload values; then, the speed adjustment signal undergoes IPARK transformation; the IPARK-transformed signal is then processed sequentially through an SVPWM module and an inverter; finally, the processed signal is sent to the bearingless permanent magnet motor used in the heart pump to adjust the speed of the heart pump. This process is repeated continuously, acquiring the speed and current of the bearingless permanent magnet motor used in the heart pump to control the speed of the heart pump.

[0128] Figure 14 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Figure 14 A block diagram of an exemplary computer device 12 suitable for implementing embodiments of the present invention is shown. Figure 14 The computer device 12 shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. The computer device 12 can be any terminal device with computing capabilities and can be integrated into a heart pump control device.

[0129] like Figure 14 As shown, the computer device 12 is represented in the form of a general-purpose computing device. The components of the computer device 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and a bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0130] Bus 18 can be one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0131] Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0132] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 14 Not shown; usually referred to as a "hard drive"). Although Figure 14 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0133] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0134] Computer device 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with the computer device 12, and / or with any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, computer device 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18. It should be understood that, although... Figure 14 As not shown, it can be used in conjunction with computer device 12 with other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0135] Processing unit 16 executes various functional applications and data processing by running programs stored in system memory 28, such as implementing the heart pump control method provided in this embodiment, which includes:

[0136] Obtain the target blood flow value of the target object;

[0137] The target blood flow value is input into a pre-trained target preload prediction model to obtain the preload prediction value;

[0138] The rotational speed of the target heart pump is adjusted based on the predicted preload value and the preset preload reference standard.

[0139] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the heart pump control method as provided in any embodiment of the present invention, including:

[0140] Obtain the target blood flow value of the target object;

[0141] The target blood flow value is input into a pre-trained target preload prediction model to obtain the preload prediction value;

[0142] The rotational speed of the target heart pump is adjusted based on the predicted preload value and the preset preload reference standard.

[0143] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0144] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0145] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0146] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0147] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0148] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A heart pump control device, characterized in that, include: The blood flow value acquisition module is used to acquire the target blood flow value of the target object; The preload prediction value determination module is used to input the target blood flow value into a pre-trained target preload prediction model to obtain the preload prediction value; The heart pump speed adjustment module is used to determine the preload deviation value based on the preload prediction value and the preset preload reference standard; and to determine the pseudo-order of the controller based on multiple heart pump speed values ​​collected at preset time intervals. The pseudo-gradient of the controller is determined based on the pseudo-order of the controller and the speed increments corresponding to the multiple heart pump speed values. The adjustment amount of the heart pump speed is determined based on the controller pseudo-order, the controller pseudo-gradient, and the preload deviation value; a speed adjustment command signal is sent to the heart pump based on the adjustment amount of the heart pump speed to adjust the speed of the heart pump; wherein, the preset preload reference standard is a preset standard range of preload values; The pseudo-order of the controller is the pseudo-order of the controller that controls the speed of the heart pump; the pseudo-gradient of the controller is the pseudo-gradient of the controller that controls the speed of the heart pump.

2. The apparatus of claim 1, wherein, The acquisition of the target blood flow value of the target object includes: A cardiovascular and cardiac pump coupling model is constructed based on the blood flow characteristic parameters of the target object; The blood flow of the target object is predicted based on the cardiovascular and cardiac pump coupling model to obtain the target blood flow value.

3. The apparatus of claim 2, wherein, The cardiovascular and cardiac pump coupling model comprises the left atrium, left ventricle, aorta, artery, systemic circulation, right atrium, right ventricle, pulmonary artery, pulmonary circulation, pulmonary vein, cardiac pump, and the connecting pathways between the components.

4. The apparatus of claim 1, wherein, The training process of the target preload prediction model includes: Obtain a preset blood flow sample set; The preset blood flow sample set is input into the initial preload prediction model to obtain the preload prediction sample value; The model loss function value is determined based on the predicted preload sample value and the preset preload sample value in the preset blood flow sample set, and the parameter values ​​of the initial preload prediction model are adjusted based on the model loss function value to obtain the target preload prediction model.

5. A heart pump control system, characterized by, The system includes: Preload prediction subsystem, heart pump speed regulation subsystem, and heart pump; The preload prediction subsystem includes a blood flow determination module and a preload prediction module. The blood flow determination module is used to predict the blood flow of the target object based on the cardiovascular and cardiac pump coupling model to determine the target blood flow value. The preload prediction module is used to input the target blood flow value into a pre-trained target preload prediction model to obtain a preload prediction value, and send the preload prediction value to the cardiac pump speed regulation subsystem. The heart pump speed regulation subsystem includes a speed adjustment value determination module and a heart pump speed adjustment module. The speed adjustment value determination module determines a preload deviation value based on the predicted preload value and a preset preload reference standard; determines a controller pseudo-order based on multiple heart pump speed values ​​collected at preset time intervals; determines a controller pseudo-gradient based on the controller pseudo-order and the speed increments corresponding to the multiple heart pump speed values; and determines the heart pump speed adjustment amount based on the controller pseudo-order, the controller pseudo-gradient, and the preload deviation value. The heart pump speed adjustment module adjusts the heart pump speed based on the heart pump speed adjustment amount. The preset preload reference standard is a preset standard range of preload values; the controller pseudo-order is the pseudo-order of the controller controlling the heart pump speed; and the controller pseudo-gradient is the pseudo-gradient of the controller controlling the heart pump speed. The heart pump includes a physical quantity detection module, which is used to detect the rotational speed and current of the heart pump and send the rotational speed and current of the heart pump to the blood flow determination module, so that the blood flow determination module determines the target blood flow value based on the rotational speed and current of the heart pump.

6. A server device, characterized by The server device includes: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, causing the one or more processors to implement a heart pump control method, the heart pump control method includes: Obtain the target blood flow value of the target object; The target blood flow value is input into a pre-trained target preload prediction model to obtain the preload prediction value; The preload deviation value is determined based on the predicted preload value and the preset preload reference standard; the pseudo-order of the controller is determined based on multiple heart pump speed values ​​collected at preset time intervals; the pseudo-gradient of the controller is determined based on the pseudo-order of the controller and the speed increments corresponding to the multiple heart pump speed values; the amount to be adjusted for the heart pump speed is determined based on the pseudo-order of the controller, the pseudo-gradient of the controller, and the preload deviation value; a speed adjustment command signal is sent to the heart pump based on the amount to be adjusted for the heart pump speed; wherein, the preset preload reference standard is a preset standard range of preload values; the pseudo-order of the controller is the pseudo-order of the controller controlling the heart pump speed; and the pseudo-gradient of the controller is the pseudo-gradient of the controller controlling the heart pump speed.

7. A computer-readable storage medium having stored thereon a computer program, characterized in that When executed by a processor, this program implements a heart pump control method, which includes: Obtain the target blood flow value of the target object; The target blood flow value is input into a pre-trained target preload prediction model to obtain the preload prediction value; The preload deviation value is determined based on the predicted preload value and the preset preload reference standard; the pseudo-order of the controller is determined based on multiple heart pump speed values ​​collected at preset time intervals; the pseudo-gradient of the controller is determined based on the pseudo-order of the controller and the speed increments corresponding to the multiple heart pump speed values; the amount to be adjusted for the heart pump speed is determined based on the pseudo-order of the controller, the pseudo-gradient of the controller, and the preload deviation value; a speed adjustment command signal is sent to the heart pump based on the amount to be adjusted for the heart pump speed; wherein, the preset preload reference standard is a preset standard range of preload values; the pseudo-order of the controller is the pseudo-order of the controller controlling the heart pump speed; and the pseudo-gradient of the controller is the pseudo-gradient of the controller controlling the heart pump speed.

Images