A smart control system and device based on ventricular assist device

Abstract

This application provides an intelligent control system and device based on a ventricular assist device, relating to the field of medical device technology. The system includes a ventricular assist device and a control device. The control device controls the ventricular assist device and executes the following control method: acquiring the physical measurement signal of the ventricular assist device at the current moment; based on the physical measurement signal, using a signal prediction model in the first closed loop of a dual-closed-loop control architecture to predict the patient's pressure signal and nerve signal at the next moment; based on the pressure signal and nerve signal, using a speed prediction model in the first closed loop to predict the target speed at the next moment, and using the second closed loop of the dual-closed-loop control architecture to control the ventricular assist device according to the target speed. Applying the solution provided in this embodiment enables adaptive control of the ventricular assist device.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and in particular to an intelligent control system and device based on a ventricular assist device. Background Technology

[0002] Ventricular assist devices (VADs) are devices designed to support or assist patients with heart-related conditions, such as heart failure, by helping the heart pump blood to other parts of the body. In existing technologies, control parameters and modes are typically the same for different patients, but patients are specific and possess different autonomic nervous system regulatory mechanisms. Therefore, there is an urgent need for an adaptive control method for VADs to accommodate the differences among patients. Summary of the Invention

[0003] The purpose of this application is to provide an intelligent control system and device based on a ventricular assist device, so as to achieve adaptive control of the ventricular assist device. The specific technical solution is as follows:

[0004] In a first aspect, embodiments of this application provide an intelligent control system based on a ventricular assist device. The system includes a ventricular assist device and a control device. The ventricular assist device is implanted into the patient's heart via percutaneous intervention to assist the heart in pumping blood. The control device is used to control the ventricular assist device, and the control device performs the following control methods:

[0005] The physical measurement signals of the ventricular assist device at the current moment are acquired, wherein the physical measurement signals refer to the directly measured physical signals, including aortic pressure signals, pump speed signals, and pump motor current signals;

[0006] Based on the physical measurement signals, the signal prediction model in the first closed loop of the dual closed-loop control architecture is used to predict the patient's pressure signal and nerve signal at the next moment. The pressure signal includes peripheral vascular resistance and left ventricular end-diastolic pressure, and the nerve signal includes sympathetic nerve activity and parasympathetic nerve activity.

[0007] Based on the pressure signal and nerve signal, the target rotational speed at the next moment is predicted using the rotational speed prediction model in the first closed loop, and the ventricular assist device is controlled according to the target rotational speed using the second closed loop in the dual closed-loop control architecture.

[0008] In one embodiment of this application, the above-mentioned prediction of the target rotational speed at the next moment based on the pressure signal and the neural signal, using the rotational speed prediction model in the first closed loop, includes:

[0009] Using the pressure signal and nerve signal, the predicted values ​​of the hemodynamic parameters of the speed prediction model in the first closed loop are determined. Based on the difference between the predicted values ​​and the reference values ​​of the hemodynamic parameters, a cost function of the speed prediction model is constructed. The hemodynamic parameters include the mean arterial pressure and the left ventricular end-diastolic pressure.

[0010] The constraints of the cost function are constructed, and the optimal solution of the cost function is solved based on the constraints of the cost function. The calculated optimal solution is determined as the target rotational speed.

[0011] In one embodiment of this application, the above-mentioned constraints include: the left ventricular end-diastolic pressure is greater than or equal to a preset minimum pressure threshold, the pump flow rate is greater than or equal to a minimum flow rate threshold, the pump speed is within a preset safe operating range, and the pump speed change is less than or equal to a preset change range threshold.

[0012] In one embodiment of this application, the expression for the cost function is:

[0013] ;

[0014] Where J represents the rating value, This represents the predicted value of the mean arterial pressure index. The reference value for mean arterial pressure. This represents the predicted value of left ventricular end-diastolic pressure. This represents the reference value for left ventricular end-diastolic pressure. This represents the speed difference between adjacent time points. , , These are preset coefficients.

[0015] In one embodiment of this application, the sampling frequency of the first closed loop is lower than that of the second closed loop.

[0016] Secondly, embodiments of this application provide an intelligent control device based on a ventricular assist device, the device comprising:

[0017] The signal acquisition module is used to acquire the physical measurement signals of the ventricular assist device at the current moment. The physical measurement signals refer to the directly measured physical signals, including aortic pressure signals, pump speed signals, and pump motor current signals.

[0018] The signal prediction module is used to predict the patient's pressure signal and nerve signal at the next moment based on the physical measurement signal and the signal prediction model in the first closed loop of the dual closed-loop control architecture. The pressure signal includes peripheral vascular resistance and left ventricular end-diastolic pressure, and the nerve signal includes sympathetic nerve activity and parasympathetic nerve activity.

[0019] The speed control module is used to predict the target speed at the next moment based on the pressure signal and the nerve signal, using the speed prediction model in the first closed loop, and to control the ventricular assist device according to the target speed using the second closed loop in the dual closed loop control architecture.

[0020] In one embodiment of this application, the speed control module includes:

[0021] The function construction submodule is used to determine the predicted values ​​of the hemodynamic parameters of the speed prediction model in the first closed loop using the pressure signal and the nerve signal. Based on the difference between the predicted values ​​and the reference values ​​of the hemodynamic parameters, the cost function of the speed prediction model is constructed. The hemodynamic parameters include the mean arterial pressure index and the left ventricular end-diastolic pressure index.

[0022] The rotational speed calculation submodule is used to construct the constraints of the cost function, and based on the constraints of the cost function, solve for the optimal solution of the cost function, and determine the calculated optimal solution as the target rotational speed.

[0023] In one embodiment of this application, the above-mentioned constraints include: the left ventricular end-diastolic pressure is greater than or equal to a preset minimum pressure threshold, the pump flow rate is greater than or equal to a minimum flow rate threshold, the pump speed is within a preset safe operating range, and the pump speed change is less than or equal to a preset change range threshold.

[0024] In one embodiment of this application, the expression for the cost function is:

[0025] ;

[0026] Where J represents the rating value, This represents the predicted value of the mean arterial pressure index. The reference value for mean arterial pressure. This represents the predicted value of left ventricular end-diastolic pressure. This represents the reference value for left ventricular end-diastolic pressure. This represents the speed difference between adjacent time points. , , These are preset coefficients.

[0027] In one embodiment of this application, the sampling frequency of the first closed loop is lower than that of the second closed loop.

[0028] Thirdly, embodiments of this application provide an electronic medical device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0029] Memory, used to store computer programs;

[0030] When a processor executes a program stored in memory, it implements the intelligent control method described in the first aspect above.

[0031] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the intelligent control method described in the first aspect.

[0032] As can be seen from the above, the solution provided in this application has two advantages. First, it employs a dual-closed-loop control architecture. The first closed loop is responsible for iteratively updating the target rotational speed, while the second closed loop is responsible for execution control. The hierarchical collaboration between the first and second closed loops achieves stable regulation of the ventricular assist device, ensuring the stability of its operation. Second, the first closed loop converts directly measured physical signals into pressure and nerve signals, which are difficult to measure. The target rotational speed predicted using these pressure and nerve signals adapts to the patient's current autonomic nervous system regulation mechanism and blood pressure changes, making the device operation conform to the patient's actual physiological state and improving adaptability. In summary, the above solution enables stable, precise, and adaptive control of the ventricular assist device.

[0033] Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0035] Figure 1a A schematic diagram of the structure of an intelligent control system for a ventricular assist device provided in this application embodiment;

[0036] Figure 1b This is a schematic diagram of the structure of a ventricular assist device provided in an embodiment of this application;

[0037] Figure 2A flowchart illustrating the first intelligent control method provided in this application embodiment;

[0038] Figure 3 A flowchart illustrating the second intelligent control method provided in this application embodiment;

[0039] Figure 4 A schematic diagram of the structure of the first intelligent control device based on a ventricular assist device provided in this application embodiment;

[0040] Figure 5 A schematic diagram of the structure of a second type of intelligent control device based on a ventricular assist device provided in this application embodiment;

[0041] Figure 6 This is a schematic diagram of the structure of an electronic medical device provided in an embodiment of this application. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of this application.

[0043] Before introducing the embodiments of this application, firstly, in conjunction with Figure 1a The intelligent control system of the ventricular assist device provided in the embodiments of this application will be described.

[0044] The intelligent control system for the ventricular assist device includes a control device 11 and a ventricular assist device 12. The ventricular assist device 12 is implanted into the patient's heart via percutaneous intervention to assist the patient's heart in pumping blood; the control device 11 is used to control the operation of the ventricular assist device 12.

[0045] The aforementioned ventricular assist device can be a left ventricular assist device. Taking a left ventricular assist device as an example, the above-mentioned ventricular assist device will be explained. See [link to documentation]. Figure 1b , Figure 1b A schematic diagram of the left ventricular assist device is shown.

[0046] Figure 1b The ventricular assist device shown is a left ventricular catheter pump, which is used to cross the aortic valve and pump blood from the left ventricle into the aorta to assist the heart in pumping blood. Of course, in addition to the left ventricular catheter pump, the ventricular catheter pump in this application can also be a right ventricular catheter pump, a biventricular catheter pump, etc., and there is no limitation in this regard.

[0047] The left ventricular catheter pump includes a motor 101, an impeller 102, a bleeding port 103, and a blood inlet 104. The high-speed rotation of the motor 101 drives the impeller 102 to rotate, generating suction to pump blood from the blood inlet 104 into the bleeding port 103. The blood inlet 104 is located in the patient's left ventricle, and the bleeding port 103 is located in the patient's aorta, thus assisting the patient's heart in pumping blood.

[0048] The following describes the intelligent control scheme implemented by the control equipment.

[0049] See Figure 2 , Figure 2 This is a flowchart illustrating the first intelligent control method provided in the embodiments of this application. The method includes the following steps S201-S203.

[0050] Step S201: Obtain the physical measurement signal at the current moment.

[0051] The aforementioned physical measurement signals are physical signals obtained by using sensors integrated into the ventricular assist device. All of these physical measurement signals are detected when the ventricular assist device is operating inside the patient's body.

[0052] The aforementioned physical signals include equipment operation signals and patient physiological signals, such as aortic pressure signals, pump speed signals, and pump motor current signals. The aortic pressure signal represents the changes in the patient's aortic pressure, the pump speed signal represents the changes in the rotational speed of the ventricular assist device, and the pump motor current signal represents the actual changes in the motor current of the ventricular assist device.

[0053] Step S202: Based on the physical measurement signal, the signal prediction model in the first closed loop of the dual closed-loop control architecture is used to predict the patient's pressure signal and nerve signal at the next moment.

[0054] The aforementioned dual-loop control architecture refers to the control architecture adopted by the control device. The dual loops include a first loop and a second loop, which achieve stable regulation of the ventricular assist device through hierarchical collaboration. The first loop is used to estimate neural signals and iteratively update the target rotational speed; the second loop controls the operation of the ventricular assist device based on the target rotational speed updated by the first loop.

[0055] In one embodiment of this application, the sampling frequency of the first closed loop is lower than that of the second closed loop. The sampling period of the first closed loop is between 1 and 5 seconds, while the sampling period of the second closed loop is between 100 and 200 ms. Because the two closed loops use different sampling frequencies, the first closed loop handles slow-changing physiological signal prediction, while the second closed loop achieves rapid speed control. This design balances long-term physiological trend tracking with short-term precise adjustment, improving overall response efficiency.

[0056] The aforementioned pressure signals include peripheral vascular resistance and left ventricular end-diastolic pressure. The aforementioned neural signals include sympathetic and parasympathetic activity. Sympathetic activity reflects the degree of stress, tension, or excitement in the body, while parasympathetic activity reflects the degree of calm, rest, or recovery in the body. These neural signals reflect the dynamic response changes of the patient's nervous system.

[0057] The aforementioned signal prediction model is pre-trained and used to predict neural signals characterizing the patient's autonomic nervous system regulation mechanism and pressure signals characterizing the patient's blood pressure. Specifically, the prediction model includes the mapping relationship between physical signals, pressure signals, and neural signals. By inputting the aforementioned physical measurement signals into the signal prediction model, the pressure signals and neural signals output by the signal prediction model are obtained.

[0058] Step S203: Based on the pressure signal and nerve signal, the target rotational speed is predicted at the next moment using the rotational speed prediction model in the first closed loop, and the ventricular assist device is controlled according to the target rotational speed using the second closed loop in the dual closed loop control architecture.

[0059] The target rotational speed mentioned above refers to the rotational speed that the ventricular assist device is expected to reach in the next moment. The rotational speed prediction model mentioned above is a pre-trained model used to predict the target rotational speed of the ventricular assist device.

[0060] Pressure signals and nerve signals are input into the speed prediction model to obtain the target speed output by the model. The target speed is then input into the second closed loop, which controls the ventricular assist device according to the target speed. Specifically, a PID control strategy can be used to make the speed of the ventricular assist device reach the target speed.

[0061] As can be seen from the above, the solution provided in this embodiment has two advantages. First, it employs a dual-closed-loop control architecture. The first closed loop is responsible for iteratively updating the target rotational speed, while the second closed loop is responsible for execution control. The hierarchical collaboration between the first and second closed loops achieves stable regulation of the ventricular assist device, ensuring the stability of its operation. Second, the first closed loop converts directly measured physical signals into pressure and nerve signals, which are difficult to measure. The target rotational speed predicted using these pressure and nerve signals adapts to the patient's current autonomic nervous system regulation mechanism and blood pressure changes, making the device operation conform to the patient's actual physiological state and improving adaptability. In summary, the above solution enables stable, precise, and adaptive control of the ventricular assist device.

[0062] The foregoing Figure 2 In the corresponding step S203, the specific implementation method for predicting the target rotational speed can be achieved using the following steps S303-S304. Based on this, see [link to relevant documentation]. Figure 3 , Figure 3The flowchart illustrates the control method for the second type of ventricular assist device provided in this application, which includes the following steps S301-S305.

[0063] Step S301: Obtain the physical measurement signal at the current moment.

[0064] The physical measurement signals mentioned above refer to the physical signals obtained by direct measurement, including aortic pressure signals, pump speed signals, and pump motor current signals.

[0065] Step S302: Based on the physical measurement signal, the signal prediction model in the first closed loop of the dual closed-loop control architecture is used to predict the patient's pressure signal and nerve signal at the next moment.

[0066] The pressure signals mentioned above include peripheral vascular resistance and left ventricular end-diastolic pressure, and the nerve signals include sympathetic nerve activity and parasympathetic nerve activity.

[0067] The steps S301-S302 described above are the same as the steps S201-S202 described above, and will not be repeated here.

[0068] Step S303: Using pressure signals and nerve signals, determine the predicted values ​​of hemodynamic parameters of the speed prediction model in the first closed loop. Based on the difference between the predicted values ​​and the target values ​​of the hemodynamic parameters, construct the cost function of the speed prediction model.

[0069] The aforementioned hemodynamic parameters include mean arterial pressure and left ventricular end-diastolic pressure. These hemodynamic parameters are the target parameters that the rotational speed prediction model aims to optimize, bringing them closer to their optimal values.

[0070] The left ventricular end-diastolic pressure in the predicted pressure signal is determined as the predicted value of the left ventricular end-diastolic pressure index.

[0071] In one embodiment of this application, the predicted value of the mean arterial pressure index is calculated according to the following expression:

[0072] ;

[0073] MAP represents the predicted value of the mean arterial pressure index. It indicates peripheral vascular resistance; LVEDP represents left ventricular end-diastolic pressure. This represents the motor current at the current moment. This represents the motor current at the initial moment. This represents the initial value of the mean arterial pressure index, and v represents the measurement noise. , , These represent the preset constant coefficients.

[0074] In one embodiment of this application, the expression for the cost function is:

[0075] ;

[0076] Where J represents the rating value, This represents the predicted value of the mean arterial pressure index. The reference value for mean arterial pressure. This represents the predicted value of left ventricular end-diastolic pressure. This represents the reference value for left ventricular end-diastolic pressure. This represents the speed difference between adjacent time points. , , These are preset coefficients.

[0077] The reference values ​​for the above hemodynamic parameters are pre-set, such as those determined in advance based on the patient's physical condition.

[0078] The aforementioned cost function employs a multi-objective collaborative optimization strategy, considering changes in mean arterial pressure, left ventricular end-diastolic pressure, and rotational speed. This approach optimizes rotational speed from multiple perspectives to maintain stable blood pressure and stable rotational speed fluctuations, thereby avoiding other problems that may arise from pursuing a single objective.

[0079] Step S304: Construct the constraints of the cost function, and based on the constraints of the cost function, solve for the optimal solution of the cost function, and determine the calculated optimal solution as the target rotational speed.

[0080] In one embodiment of this application, the above-mentioned constraints include: the left ventricular end-diastolic pressure is greater than or equal to a preset minimum pressure threshold, the pump flow rate is greater than or equal to a minimum flow rate threshold, the pump speed is within a preset safe operating range, and the pump speed change is less than or equal to a preset change range threshold.

[0081] Left ventricular end-diastolic pressure greater than or equal to a preset minimum pressure threshold is used to prevent aspiration events. Pump flow rate greater than or equal to a minimum flow rate threshold is used to ensure a minimum blood supply. Pump speed is within a preset safe operating range to ensure safe operation of the equipment. Pump speed variation less than or equal to a preset variation range threshold is used to ensure smooth pump changes and avoid sudden changes that could have a huge impact on the cardiovascular system.

[0082] The above constraints constitute the bottom line of the cost function to ensure that the output rotational speed simultaneously meets the above constraints, thereby reducing the risk of common complications.

[0083] The optimal solution obtained from the above calculation represents the rotational speed that maintains the optimal mean arterial pressure and left ventricular end-diastolic pressure, and has the most stable rotational speed variation.

[0084] The optimal solution mentioned above can be the optimal control sequence on a preset time scale. The first rotational speed in the sequence is determined as the target rotational speed, and the other rotational speeds are used for the rolling prediction of the next optimization.

[0085] Step S305: Using the second closed loop in the dual closed-loop control architecture, control the ventricular assist device according to the target rotational speed.

[0086] As can be seen from the above, in this embodiment, the use of a cost function to calculate the target rotational speed can maintain the patient's key blood pressure indicators at an ideal level, providing cyclical support that better meets individual needs. In addition, setting constraints constitutes the baseline for rotational speed prediction, ensuring that the output rotational speed meets the safety criteria represented by the constraints, thereby improving the safety of equipment operation.

[0087] Corresponding to the above-mentioned intelligent control system based on ventricular assist device, this application embodiment also provides an intelligent control device based on ventricular assist device.

[0088] See Figure 4 , Figure 4 The first intelligent control device based on a ventricular assist device provided in the embodiments of this application includes 401-403.

[0089] The signal acquisition module 401 is used to acquire the physical measurement signals of the ventricular assist device at the current moment, wherein the physical measurement signals refer to the physical signals obtained by direct measurement, and the physical measurement signals include aortic pressure signals, pump speed signals, and pump motor current signals;

[0090] The signal prediction module 402 is used to predict the patient's pressure signal and nerve signal at the next moment based on the physical measurement signal and using the signal prediction model in the first closed loop of the dual closed-loop control architecture. The pressure signal includes peripheral vascular resistance and left ventricular end-diastolic pressure, and the nerve signal includes sympathetic nerve activity and parasympathetic nerve activity.

[0091] The speed control module 403 is used to predict the target speed at the next moment based on the pressure signal and the nerve signal, using the speed prediction model in the first closed loop, and to control the ventricular assist device according to the target speed using the second closed loop in the dual closed loop control architecture.

[0092] As can be seen from the above, the solution provided in this embodiment has two advantages. First, it employs a dual-closed-loop control architecture. The first closed loop is responsible for iteratively updating the target rotational speed, while the second closed loop is responsible for execution control. The hierarchical collaboration between the first and second closed loops achieves stable regulation of the ventricular assist device, ensuring the stability of its operation. Second, the first closed loop converts directly measured physical signals into pressure and nerve signals, which are difficult to measure. The target rotational speed predicted using these pressure and nerve signals adapts to the patient's current autonomic nervous system regulation mechanism and blood pressure changes, making the device operation conform to the patient's actual physiological state and improving adaptability. In summary, the above solution enables stable, precise, and adaptive control of the ventricular assist device.

[0093] See Figure 5 , Figure 5 This is a schematic diagram of the structure of a second type of intelligent control device based on a ventricular assist device provided in an embodiment of this application. The device includes:

[0094] The signal acquisition module 401 is used to acquire the physical measurement signals of the ventricular assist device at the current moment, wherein the physical measurement signals refer to the physical signals obtained by direct measurement, and the physical measurement signals include aortic pressure signals, pump speed signals, and pump motor current signals;

[0095] The signal prediction module 402 is used to predict the patient's pressure signal and nerve signal at the next moment based on the physical measurement signal and using the signal prediction model in the first closed loop of the dual closed-loop control architecture. The pressure signal includes peripheral vascular resistance and left ventricular end-diastolic pressure, and the nerve signal includes sympathetic nerve activity and parasympathetic nerve activity.

[0096] The function construction submodule 4031 is used to determine the predicted values ​​of the hemodynamic parameters of the speed prediction model in the first closed loop using the pressure signal and the nerve signal, and to construct the cost function of the speed prediction model based on the difference between the predicted values ​​and the reference values ​​of the hemodynamic parameters, wherein the hemodynamic parameters include the mean arterial pressure index and the left ventricular end-diastolic pressure index.

[0097] The rotational speed calculation submodule 4032 is used to construct the constraints of the cost function, and based on the constraints of the cost function, solve the optimal solution of the cost function, and determine the calculated optimal solution as the target rotational speed.

[0098] The speed control submodule 4033 is used to control the ventricular assist device according to the target speed using the second closed loop in the dual closed-loop control architecture.

[0099] As can be seen from the above, in this embodiment, the use of a cost function to calculate the target rotational speed can maintain the patient's key blood pressure indicators at an ideal level, providing cyclical support that better meets individual needs. In addition, setting constraints constitutes the baseline for rotational speed prediction, ensuring that the output rotational speed meets the safety criteria represented by the constraints, thereby improving the safety of equipment operation.

[0100] In one embodiment of this application, the above-mentioned constraints include: the left ventricular end-diastolic pressure is greater than or equal to a preset minimum pressure threshold, the pump flow rate is greater than or equal to a minimum flow rate threshold, the pump speed is within a preset safe operating range, and the pump speed change is less than or equal to a preset change range threshold.

[0101] In one embodiment of this application, the expression for the cost function is:

[0102] ;

[0103] Where J represents the rating value, This represents the predicted value of the mean arterial pressure index. The reference value for mean arterial pressure. This represents the predicted value of left ventricular end-diastolic pressure. This represents the reference value for left ventricular end-diastolic pressure. This represents the speed difference between adjacent time points. , , These are preset coefficients.

[0104] In one embodiment of this application, the sampling frequency of the first closed loop is lower than that of the second closed loop.

[0105] Corresponding to the aforementioned intelligent control system based on ventricular assist devices, embodiments of this application provide an electronic medical device. See also... Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic medical device provided in an embodiment of this application. The electronic medical device includes a processor 601, a communication interface 602, a memory 603, and a communication bus 604. The processor 601, the communication interface 602, and the memory 603 communicate with each other through the communication bus 604.

[0106] Memory 603 is used to store computer programs;

[0107] When the processor 601 executes the program stored in the memory 603, it implements the aforementioned steps of the intelligent control method based on the ventricular assist device.

[0108] The communication bus mentioned in the controller above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0109] The communication interface is used for communication between the aforementioned controller and other devices.

[0110] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0111] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0112] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the aforementioned steps of the intelligent control method based on a ventricular assist device.

[0113] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to execute the aforementioned intelligent control method steps based on a ventricular assist device.

[0114] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0115] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0116] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, electronic medical devices, and computer-readable storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0117] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. A smart control system based on a ventricular assist device, characterized in that, The system comprises a ventricular assist device implanted in a patient's heart by percutaneous intervention to assist the patient's heart in pumping blood, and a control device for controlling the ventricular assist device, which executes the following control method: a physical measurement signal of the ventricular assist device at the current time is acquired, wherein the physical measurement signal refers to a directly measured physical signal, and the physical measurement signal comprises an aortic pressure signal, a pump rotation speed signal, and a pump motor current signal; based on the physical measurement signal, a signal prediction model in a first closed loop of a double closed loop control architecture is used to predict a pressure signal and a neural signal of the patient at the next time, wherein the pressure signal comprises peripheral vascular resistance and left ventricular end-diastolic pressure, and the neural signal comprises sympathetic nervous activity and parasympathetic nervous activity; based on the pressure signal and the neural signal, a rotation speed prediction model in the first closed loop is used to predict a target rotation speed at the next time, and a second closed loop in the double closed loop control architecture is used to control the ventricular assist device according to the target rotation speed.

2. The system of claim 1, wherein, The method comprises the following steps: the pressure signal and the neural signal are used to determine a predicted value of a hemodynamic index of the rotation speed prediction model in the first closed loop, a cost function of the rotation speed prediction model is constructed based on a difference between the predicted value and a reference value of the hemodynamic index, wherein the hemodynamic index comprises mean arterial pressure and left ventricular end-diastolic pressure; a constraint condition of the cost function is constructed, and an optimal solution of the cost function is solved based on the constraint condition, and the calculated optimal solution is determined as the target rotation speed.

3. The system of claim 2, wherein, The constraint condition comprises that the left ventricular end-diastolic pressure is greater than or equal to a preset minimum pressure threshold, the pump flow is greater than or equal to a minimum flow threshold, the pump rotation speed is within a preset safe working range, and the pump rotation speed change is less than or equal to a preset change range threshold.

4. The system of claim 2 or 3, wherein, The expression of the cost function is as follows: ； wherein J represents a score value, represents a predicted value of the mean arterial pressure indicator, represents a reference value of the mean arterial pressure indicator, represents a predicted value of the left ventricular end diastolic pressure, represents a reference value of the left ventricular end diastolic pressure, represents a difference in rotational speed between adjacent time instants, are preset coefficients, respectively.​​ 5. The system of any one of claims 1-3, wherein, The sampling frequency of the first closed loop is lower than that of the second closed loop.

6. A smart control device based on a ventricular assist device, characterized in that The device comprises: a signal acquisition module for acquiring a physical measurement signal of the ventricular assist device at the current time, wherein the physical measurement signal refers to a directly measured physical signal, and the physical measurement signal comprises an aortic pressure signal, a pump rotation speed signal, and a pump motor current signal; a signal prediction module for using a signal prediction model in a first closed loop of a double closed loop control architecture to predict a pressure signal and a neural signal of the patient at the next time based on the physical measurement signal, wherein the pressure signal comprises peripheral vascular resistance and left ventricular end-diastolic pressure, and the neural signal comprises sympathetic nervous activity and parasympathetic nervous activity; a rotation speed control module for using a rotation speed prediction model in the first closed loop to predict a target rotation speed at the next time based on the pressure signal and the neural signal, and using a second closed loop in the double closed loop control architecture to control the ventricular assist device according to the target rotation speed.

7. The apparatus of claim 6, wherein, The rotation speed control module comprises: A function construction submodule is configured to adopt the pressure signal and the neural signal to determine a predicted value of a hemodynamic index of a rotation speed prediction model in the first closed loop, and to construct a cost function of the rotation speed prediction model based on a difference between the predicted value and a reference value of the hemodynamic index, wherein the hemodynamic index comprises an average arterial pressure index and a left ventricular end-diastolic pressure index. A rotation speed calculation submodule is configured to construct a constraint condition of the cost function, and to solve an optimal solution of the cost function based on the constraint condition of the cost function, and to determine the calculated optimal solution as a target rotation speed.

8. The apparatus of claim 7, wherein, The constraint condition comprises that the left ventricular end-diastolic pressure is greater than or equal to a preset minimum pressure threshold, the pump flow is greater than or equal to a minimum flow threshold, the pump rotation speed is within a preset safe working range, and a change in the pump rotation speed is less than or equal to a preset change range threshold.

9. The apparatus of claim 7 or 8, wherein, An expression of the cost function is as follows: ； wherein J represents a score value, represents a predicted value of the mean arterial pressure indicator, represents a reference value of the mean arterial pressure indicator, represents a predicted value of the left ventricular end diastolic pressure, represents a reference value of the left ventricular end diastolic pressure, represents a difference in rotational speed between adjacent time instants, , , are preset coefficients, respectively.

10. The apparatus of any one of claims 6-8, wherein, A sampling frequency of the first closed loop is lower than that of the second closed loop.

Images