Design optimization method and device for ventricular assist device using digital twin model

Abstract

The embodiment of the application provides a ventricular assist device design optimization method and device applying a digital twin model, the method comprises the following steps: obtaining target operation data representing an operation state of a ventricular assist device, and determining geometric data representing a design form of the ventricular assist device; based on the target operation data and the geometric data, a pre-constructed digital twin model is used to predict a target performance parameter of the ventricular assist device, wherein the digital twin model represents a coupling model of the ventricular assist device and a cardiovascular system; based on the target performance parameter, a target design of the ventricular assist device is determined. By using the scheme provided in the embodiment, the safety and effectiveness of the equipment can be improved.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and in particular to a design optimization method and device for ventricular assist devices using digital twin models. Background Technology

[0002] A ventricular assist device (VAD) is a medical device that uses a mechanical pump to replace or assist the heart's pumping function, maintaining blood circulation and organ perfusion, and providing transitional support or long-term treatment for patients with cardiopulmonary failure. Its core objectives are to improve hemodynamics, reduce cardiac workload, and buy time for cardiac recovery, decision-making, or organ transplantation.

[0003] The complexity of the human heart environment places extremely high demands on the performance of ventricular assist devices. To avoid affecting patients' lives, it is urgent to improve the safety and effectiveness of these devices from the source. Summary of the Invention

[0004] The purpose of this application is to provide a design optimization method and apparatus for ventricular assist devices using digital twin models, so as to improve the safety and effectiveness of the devices. The specific technical solution is as follows:

[0005] In a first aspect, embodiments of this application provide a design optimization method for ventricular assist devices using digital twin models, the method comprising:

[0006] Acquire target operating data characterizing the operating status of the ventricular assist device, and determine geometric data characterizing the design form of the ventricular assist device; wherein, the target operating data includes rotational speed, flow rate, and aortic pressure, and the geometric data includes point cloud data of the ventricular assist device;

[0007] Based on the target operating data and geometric data, a pre-constructed digital twin model is used to predict the target performance parameters of the ventricular assist device, wherein the digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system.

[0008] Based on the target performance parameters, the target design of the ventricular assist device is determined.

[0009] In one embodiment of this application, the target operating data includes first operating data under rated operating conditions and second operating data under extreme operating conditions. The target performance parameters include first performance parameters corresponding to the first operating data and second performance parameters corresponding to the second operating data. Determining the target design of the ventricular assist device based on the target performance parameters includes:

[0010] Determine the rate of change that characterizes the relationship between the first performance parameter and the second performance parameter;

[0011] Based on the first performance parameter, the second performance parameter, and the rate of change, the target design of the ventricular assist device is determined.

[0012] In one embodiment of this application, determining the target design of the ventricular assist device based on the first performance parameter, the second performance parameter, and the rate of change includes:

[0013] If the rate of change is greater than a first preset rate of change threshold and less than a second preset rate of change threshold, calculate the difference between the rate of change and the first preset rate of change threshold, convert the calculated difference into a corresponding performance parameter offset according to a preset correspondence, calculate the first sum between the performance parameter offset and the first performance parameter, and calculate the second sum between the performance parameter offset and the second performance parameter, determine the first sum and the second sum as the adjusted performance parameters, and determine the geometric design corresponding to the best performance parameter among the adjusted performance parameters as the target design of the ventricular assist device;

[0014] If the rate of change is less than a first preset rate of change threshold, the geometric design corresponding to the best performance parameter among the performance parameters is determined as the target design of the ventricular assist device.

[0015] In one embodiment of this application, the above-mentioned digital twin model includes an input layer, a feature extraction and fusion layer, and a multi-task output layer, wherein:

[0016] The input layer is used to standardize and adjust the input target running data and geometric data, and then input the adjusted target running data and geometric data into the feature extraction and fusion layer.

[0017] The feature extraction and fusion layer is used to extract the running features of the target running data and the geometric features of the geometric data, and to concatenate the running features and the geometric features to obtain the concatenated features;

[0018] The multi-task output layer is used to process the spliced ​​features using the decoder corresponding to each performance parameter index, calculate the parameter value corresponding to the performance parameter index as the performance prediction result, and output the performance prediction result.

[0019] Secondly, embodiments of this application provide a design optimization apparatus for ventricular assist devices using digital twin models, the apparatus comprising:

[0020] The data acquisition module is used to acquire target operating data characterizing the operating status of the ventricular assist device and determine geometric data characterizing the design form of the ventricular assist device; wherein, the target operating data includes rotational speed, flow rate, and aortic pressure, and the geometric data includes point cloud data of the ventricular assist device;

[0021] The parameter prediction module is used to predict the target performance parameters of the ventricular assist device based on the target operating data and geometric data, using a pre-built digital twin model, wherein the digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system.

[0022] The design optimization module is used to determine the target design of the ventricular assist device based on the target performance parameters.

[0023] In one embodiment of this application, the target operating data includes first operating data under rated operating conditions and second operating data under extreme operating conditions; the target performance parameters include first performance parameters corresponding to the first operating data and second performance parameters corresponding to the second operating data; and the design optimization module includes:

[0024] The change determination submodule is used to determine the rate of change characterizing the relationship between the first performance parameter and the second performance parameter.

[0025] The design optimization submodule is used to determine the target design of the ventricular assist device based on the first performance parameter, the second performance parameter, and the rate of change.

[0026] In one embodiment of this application, the design optimization submodule is specifically configured to: if the rate of change is greater than a first preset rate of change threshold and less than a second preset rate of change threshold, calculate the difference between the rate of change and the first preset rate of change threshold; convert the calculated difference into a corresponding performance parameter offset according to a preset correspondence; calculate a first sum between the performance parameter offset and the first performance parameter; calculate a second sum between the performance parameter offset and the second performance parameter; determine the first sum and the second sum as the adjusted performance parameters; and determine the geometric design corresponding to the best performance parameter among the adjusted performance parameters as the target design of the ventricular assist device; if the rate of change is less than the first preset rate of change threshold, determine the geometric design corresponding to the best performance parameter among the performance parameters as the target design of the ventricular assist device.

[0027] In one embodiment of this application, the above-mentioned digital twin model includes an input layer, a feature extraction and fusion layer, and a multi-task output layer, wherein:

[0028] The input layer is used to standardize and adjust the input target running data and geometric data, and then input the adjusted target running data and geometric data into the feature extraction and fusion layer.

[0029] The feature extraction and fusion layer is used to extract the running features of the target running data and the geometric features of the geometric data, and to concatenate the running features and the geometric features to obtain the concatenated features;

[0030] The multi-task output layer is used to process the spliced ​​features using the decoder corresponding to each performance parameter index, calculate the parameter value corresponding to the performance parameter index as the performance prediction result, and output the performance prediction result.

[0031] 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;

[0032] Memory, used to store computer programs;

[0033] When a processor executes a program stored in memory, it implements the steps of the method described in the first aspect above.

[0034] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect above.

[0035] As can be seen from the above, by applying the solution provided in the embodiments of this application, a precise digital twin model is used to collect two types of key data: target operating data that characterizes the working state of the pump and geometric data that characterizes the physical form of the pump. By comparing the performance prediction results corresponding to different designs through the key target performance parameters output by the digital twin model, the target design with the best overall performance is selected, thereby improving the safety and effectiveness of the equipment from the source.

[0036] 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

[0037] 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.

[0038] Figure 1This is a schematic diagram of the ventricular assist device provided in the embodiments of this application;

[0039] Figure 2a A flowchart illustrating the design optimization method for a first ventricular assist device using a digital twin model, as provided in this application embodiment;

[0040] Figure 2b A schematic diagram of the structure of a digital twin model provided in an embodiment of this application;

[0041] Figure 3 A flowchart illustrating the design optimization method for a second ventricular assist device using a digital twin model, as provided in this application embodiment;

[0042] Figure 4 A schematic diagram of the structure of a design optimization device for a first type of ventricular assist device using a digital twin model, provided in an embodiment of this application;

[0043] Figure 5 A schematic diagram of the structure of a design optimization device for a second type of ventricular assist device using a digital twin model, provided in an embodiment of this application;

[0044] Figure 6 This is a schematic diagram of the structure of an electronic medical device provided in an embodiment of this application. Detailed Implementation

[0045] 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.

[0046] Before introducing the embodiments of this application, firstly, in conjunction with Figure 1 This application provides a description of the ventricular assist device.

[0047] The ventricular assist devices provided in this application include interventional VADs and implantable VADs. Figure 1 A schematic diagram of the interventional VAD is shown.

[0048] Figure 1 The interventional VAD shown is used across the aortic valve to pump blood from the left ventricle into the aorta to assist the heart in pumping blood.

[0049] The interventional VAD 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 left ventricle of the patient, and the bleeding port 103 is located in the aorta of the patient, thereby assisting the patient's heart in pumping blood.

[0050] The following describes the solutions provided in the embodiments of this application.

[0051] See Figure 2a , Figure 2a A flowchart illustrating the design optimization method for a ventricular assist device using a digital twin model, as provided in this application embodiment, includes the following steps 201-203:

[0052] Step S201: Obtain target operating data characterizing the operating status of the ventricular assist device, and determine geometric data characterizing the design form of the ventricular assist device.

[0053] Target operating data includes speed, flow rate, aortic pressure, etc. Target operating data can be pre-set operating data, such as the most commonly used operating parameters for ventricular assist devices.

[0054] Geometric data can include point cloud data of key points in critical components of a ventricular assist device, such as impellers and catheters.

[0055] The aforementioned geometric data represents the geometric data of candidate design forms in the database. These candidate design forms can be several design styles that meet preliminary benchmark requirements, determined comprehensively based on historical medical experience and combined with deep learning technology. This embodiment evaluates the performance of the ventricular assist device using a series of candidate design forms to determine the design scheme of the ventricular assist device that achieves the best performance.

[0056] Step S202: Based on the target operating data and geometric data, a pre-built digital twin model is used to predict the target performance parameters of the ventricular assist device.

[0057] Target performance parameter characterization: The performance of the ventricular assist device with the design form corresponding to the geometric data under the operating state corresponding to the target operating data.

[0058] The aforementioned digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system. This digital twin model is a pre-built model that learns the correspondence between operational data, geometric data, and performance parameters, thereby enabling the determination of target performance parameters based on the target operational and geometric data.

[0059] Combination Figure 2bThe model structure of the digital twin model is described below. The digital twin model includes an input layer 21, a feature extraction and fusion layer 22, and a multi-task output layer 23. Among them:

[0060] The input layer 21 is used to standardize and adjust the input target running data and geometric data, and input the adjusted target running data and geometric data into the feature extraction and fusion layer 22. The input layer includes two input channels, a first channel and a second channel. The geometric data is input into the feature extraction and fusion layer 22 through the first channel, and the target running data is input into the feature extraction and fusion layer 22 through the second channel.

[0061] The feature extraction and fusion layer 22 is used to extract the running features of the target running data and the geometric features of the geometric data, and to fuse the running features and geometric features to obtain the fused features.

[0062] Specifically, the aforementioned geometric data includes the first point cloud data and the second point cloud data.

[0063] The first point cloud data represents the surface geometry of the ventricular assist device (VAD), and the second point cloud data represents the internal geometry of the VAD. The feature extraction and fusion layer extracts local features from each point cloud data and aggregates these local features to form global geometric features. Simultaneously, it extracts operational features from the operational data, concatenates these features with the local features to obtain enhanced local features, and then fuses the global geometric features with the enhanced local features to obtain the final fused features.

[0064] The aforementioned local data features are data features that characterize the nearby context of each point cloud data, such as curvature information. Global geometric features, on the other hand, reflect the overall geometric characteristics.

[0065] The multi-task output layer 23 is used to process the concatenated features using the decoder corresponding to each performance parameter index, calculate the parameter values ​​corresponding to the performance parameter index as the performance prediction result, and output the performance prediction result. For example... Figure 2b As shown, the multi-task output layer 23 includes multiple output layers, such as output layer 1, output layer 2, ..., output layer n. Each output layer outputs the performance prediction result corresponding to each performance parameter index.

[0066] The aforementioned performance parameters may include hemolysis index, shear stress, etc.

[0067] The multi-task output layer enables the simultaneous prediction of multiple performance parameters without having to run the model separately for each parameter, significantly improving the efficiency of performance prediction and ensuring consistency among the various performance prediction metrics, thereby supporting faster and more reliable design iterations.

[0068] Step S203: Determine the target design of the ventricular assist device based on the target performance parameters.

[0069] The target performance parameters obtained so far reflect the performance corresponding to several geometric data. Based on this, the design form corresponding to the optimal target performance parameters is determined as the target design of the ventricular assist device.

[0070] Other implementation methods for determining the target design can be found in the following sections. Figure 3 The corresponding implementation examples will not be described in detail here.

[0071] As can be seen from the above, by applying the solution provided in this embodiment, a precise digital twin model is used to collect two types of key data: target operating data that characterizes the working state of the pump and geometric data that characterizes the physical form of the pump. By comparing the performance prediction results of different designs through the key target performance parameters output by the digital twin model, the target design with the best overall performance is selected, thereby improving the safety and effectiveness of the equipment from the source.

[0072] The foregoing Figure 2a In the corresponding embodiment, when determining the target design in step S203, in addition to the methods mentioned above, it can also be achieved using the following steps S303-S304. Based on this, see... Figure 3 , Figure 3 This is a flowchart illustrating a second design optimization method for a ventricular assist device using a digital twin model, provided in an embodiment of this application. The method includes the following steps S301-S304.

[0073] Step S301: Obtain target operating data characterizing the operating status of the ventricular assist device, and determine geometric data characterizing the design form of the ventricular assist device.

[0074] The target operating data includes the first operating data under the rated operating state and the second operating data under the extreme operating state.

[0075] The first operating data for the rated operating state and the second operating data for the extreme operating state are both preset. The rated operating state represents the operating state in which the ventricular assist device is used at the highest frequency, while the extreme operating state represents the operating state of the ventricular assist device under extreme conditions. For example, the first operating data for the rated operating state may include the average speed setting, average flow rate, etc., while the extreme operating state may include the maximum speed setting, maximum flow rate, etc.

[0076] Step S302: Based on the target operating data and geometric data, predict the target performance parameters of the ventricular assist device.

[0077] The target performance parameters include the first performance parameters corresponding to the first running data and the second performance parameters corresponding to the second running data.

[0078] Step S303: Determine the rate of change characterizing the relationship between the first performance parameter and the second performance parameter.

[0079] Specifically, the rate of change between the first performance parameter and the second performance parameter corresponding to the same indicator can be calculated.

[0080] Step S304: Based on the first performance parameter, the second performance parameter, and the rate of change, determine the target design of the ventricular assist device.

[0081] The rate of change quantifies the severity of changes in operating status.

[0082] The first implementation method for determining the target design is as follows: normalize the first performance parameter, the second performance parameter, and the rate of change, calculate the average value after processing, and determine the geometric data corresponding to the design with the highest average value as the target design of the ventricular assist device.

[0083] The second implementation method for determining the target design is as follows: if the rate of change is greater than the first preset rate of change threshold and less than the second preset rate of change threshold, calculate the difference between the rate of change and the first preset rate of change threshold, adjust the first performance parameter and the second performance parameter based on the difference, and determine the target design of the ventricular assist device based on the adjusted first performance parameter and the second performance parameter.

[0084] In this embodiment, the calculated difference is converted into a corresponding performance parameter offset according to a preset correspondence. The performance parameter offset is then used to adjust the first performance parameter and the second performance parameter. For example, a first sum between the first performance parameter and the performance parameter offset is calculated, and a second sum between the second performance parameter and the performance parameter offset is calculated. The first sum and the second sum are then determined as the adjusted performance parameters.

[0085] The implementation method for determining the target design is as follows: the geometric data corresponding to the optimally adjusted performance parameters are determined as the target design;

[0086] If the rate of change is less than the first preset rate of change threshold, the target design is determined based on the first performance parameter and the second performance parameter. For example, the geometric data corresponding to the optimal first performance parameter and the second performance parameter are determined as the target design.

[0087] If the rate of change is greater than the second preset rate of change threshold, the geometric data will not be considered as the target design.

[0088] In this embodiment, by setting a threshold for the rate of change and making a judgment, designs with smoother performance degradation and more stable operation can be actively screened out. When the rate of change is within a reasonable range, the performance parameters are dynamically adjusted based on the difference and then evaluated, which increases the flexibility and intelligence of decision-making.

[0089] As can be seen from the above, by applying the solution provided in this embodiment, the performance of the design is evaluated under both rated and extreme conditions. This results in the final selected target design not only performing well under normal conditions, but also taking into account the comprehensive performance under both common and extreme conditions. This helps to prevent the equipment from experiencing a sharp decline in performance when encountering fluctuations in flow or pressure, thereby improving the overall reliability and adaptability of the equipment in practical applications.

[0090] Corresponding to the aforementioned design optimization method for a ventricular assist device using a digital twin model, this application also provides a design optimization device for a ventricular assist device using a digital twin model.

[0091] See Figure 4 , Figure 4 A schematic diagram of the structure of the first design optimization device for a ventricular assist device using a digital twin model provided in this application embodiment.

[0092] The first data acquisition module 401 is used to acquire target operating data characterizing the operating status of the ventricular assist device and determine geometric data characterizing the design form of the ventricular assist device; wherein, the target operating data includes rotational speed, flow rate, and aortic pressure, and the geometric data includes point cloud data of the ventricular assist device;

[0093] The first parameter prediction module 402 is used to predict the target performance parameters of the ventricular assist device based on the target operating data and geometric data, using a pre-built digital twin model, wherein the digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system.

[0094] Design optimization module 403 is used to determine the target design of the ventricular assist device based on the target performance parameters.

[0095] As can be seen from the above, by applying the solution provided in this embodiment, a precise digital twin model is used to collect two types of key data: target operating data that characterizes the working state of the pump and geometric data that characterizes the physical form of the pump. By comparing the performance prediction results of different designs through the key target performance parameters output by the digital twin model, the target design with the best overall performance is selected, thereby improving the safety and effectiveness of the equipment from the source.

[0096] See Figure 5 , Figure 5 A schematic diagram of the design optimization device for a second type of ventricular assist device using a digital twin model, provided in an embodiment of this application.

[0097] The second data acquisition module 501 is used to acquire target operating data characterizing the operating status of the ventricular assist device and determine geometric data characterizing the design form of the ventricular assist device.

[0098] The aforementioned target operating data includes the first operating data under rated operating conditions and the second operating data under extreme operating conditions.

[0099] The second parameter prediction module 502 is used to predict the target performance parameters of the ventricular assist device based on the target operating data and geometric data, using a pre-built digital twin model, wherein the digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system.

[0100] The target performance parameters include the first performance parameters corresponding to the first running data and the second performance parameters corresponding to the second running data.

[0101] The change determination submodule 503 is used to determine the rate of change characterizing the relationship between the first performance parameter and the second performance parameter.

[0102] Design optimization submodule 504 is used to determine the target design of the ventricular assist device based on the first performance parameter, the second performance parameter, and the rate of change.

[0103] As can be seen from the above, by applying the solution provided in this embodiment, the performance of the design is evaluated under both rated and extreme conditions. This results in the final selected target design not only performing well under normal conditions, but also taking into account the comprehensive performance under both common and extreme conditions. This helps to prevent the equipment from experiencing a sharp decline in performance when encountering fluctuations in flow or pressure, thereby improving the overall reliability and adaptability of the equipment in practical applications.

[0104] In one embodiment of this application, the design optimization submodule is specifically configured to: if the rate of change is greater than a first preset rate of change threshold and less than a second preset rate of change threshold, calculate the difference between the rate of change and the first preset rate of change threshold; convert the calculated difference into a corresponding performance parameter offset according to a preset correspondence; calculate a first sum between the performance parameter offset and the first performance parameter; calculate a second sum between the performance parameter offset and the second performance parameter; determine the first sum and the second sum as the adjusted performance parameters; and determine the geometric design corresponding to the best performance parameter among the adjusted performance parameters as the target design of the ventricular assist device; if the rate of change is less than the first preset rate of change threshold, determine the geometric design corresponding to the best performance parameter among the performance parameters as the target design of the ventricular assist device.

[0105] In this embodiment, by setting a threshold for the rate of change and making a judgment, designs with smoother performance degradation and more stable operation can be actively screened out. When the rate of change is within a reasonable range, the performance parameters are dynamically adjusted based on the difference and then evaluated, which increases the flexibility and intelligence of decision-making.

[0106] In one embodiment of this application, the above-mentioned digital twin model includes an input layer, a feature extraction and fusion layer, and a multi-task output layer, wherein:

[0107] The input layer is used to standardize and adjust the input target running data and geometric data, and then input the adjusted target running data and geometric data into the feature extraction and fusion layer.

[0108] The feature extraction and fusion layer is used to extract the running features of the target running data and the geometric features of the geometric data, and to concatenate the running features and the geometric features to obtain the concatenated features;

[0109] The multi-task output layer is used to process the spliced ​​features using the decoder corresponding to each performance parameter index, calculate the parameter value corresponding to the performance parameter index as the performance prediction result, and output the performance prediction result.

[0110] The multi-task output layer enables the simultaneous prediction of multiple performance parameters without having to run the model separately for each parameter, significantly improving the efficiency of performance prediction and ensuring consistency among the various performance prediction metrics, thereby supporting faster and more reliable design iterations.

[0111] Corresponding to the design optimization method for ventricular assist devices using digital twin models described above, embodiments of this application provide an electronic medical device, see [link to relevant documentation]. 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.

[0112] Memory 603 is used to store computer programs;

[0113] When the processor 601 executes the program stored in the memory 603, it implements the above-mentioned design optimization method steps for a ventricular assist device using a digital twin model.

[0114] 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.

[0115] The communication interface is used for communication between the aforementioned controller and other devices.

[0116] 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.

[0117] 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.

[0118] 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 above-described design optimization method and steps for a ventricular assist device using a digital twin model.

[0119] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, enables the computer to implement the design optimization method and steps for a ventricular assist device using a digital twin model as described above.

[0120] As can be seen from the above, by applying the solution provided in this embodiment, a precise digital twin model is used to collect two types of key data: target operating data that characterizes the working state of the pump and geometric data that characterizes the physical form of the pump. By comparing the performance prediction results of different designs through the key target performance parameters output by the digital twin model, the target design with the best overall performance is selected, thereby improving the safety and effectiveness of the equipment from the source.

[0121] 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)).

[0122] 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.

[0123] 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.

[0124] 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 design optimization method for ventricular assist devices using digital twin models, characterized in that, The method includes: Acquire target operating data characterizing the operating status of the ventricular assist device, and determine geometric data characterizing the design form of the ventricular assist device; wherein, the target operating data includes rotational speed, flow rate, and aortic pressure, and the geometric data includes point cloud data of the ventricular assist device; Based on the target operating data and geometric data, a pre-constructed digital twin model is used to predict the target performance parameters of the ventricular assist device, wherein the digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system. The target operating data includes first operating data under rated operating conditions and second operating data under extreme operating conditions. The target performance parameters include first performance parameters corresponding to the first operating data and second performance parameters corresponding to the second operating data. Based on the target performance parameters, the target design of the ventricular assist device is determined, including: Determine the rate of change that characterizes the relationship between the first performance parameter and the second performance parameter; Based on the first performance parameter, the second performance parameter, and the rate of change, the target design of the ventricular assist device is determined, including: If the rate of change is greater than a first preset rate of change threshold and less than a second preset rate of change threshold, calculate the difference between the rate of change and the first preset rate of change threshold, convert the calculated difference into a corresponding performance parameter offset according to a preset correspondence, calculate the first sum between the performance parameter offset and the first performance parameter, and calculate the second sum between the performance parameter offset and the second performance parameter, determine the first sum and the second sum as the adjusted performance parameters, and determine the geometric design corresponding to the best performance parameter among the adjusted performance parameters as the target design of the ventricular assist device; If the rate of change is less than a first preset rate of change threshold, the geometric design corresponding to the best performance parameter among the performance parameters is determined as the target design of the ventricular assist device.

2. The method according to claim 1, characterized in that, The digital twin model includes an input layer, a feature extraction and fusion layer, and a multi-task output layer, wherein: The input layer is used to standardize and adjust the input target running data and geometric data, and then input the adjusted target running data and geometric data into the feature extraction and fusion layer. The feature extraction and fusion layer is used to extract the running features of the target running data and the geometric features of the geometric data, and to concatenate the running features and the geometric features to obtain the concatenated features; The multi-task output layer is used to process the spliced ​​features using the decoder corresponding to each performance parameter index, calculate the parameter value corresponding to the performance parameter index as the performance prediction result, and output the performance prediction result.

3. A design optimization device for ventricular assist devices using digital twin models, characterized in that, The device includes: The data acquisition module is used to acquire target operating data characterizing the operating status of the ventricular assist device and determine geometric data characterizing the design form of the ventricular assist device; wherein, the target operating data includes rotational speed, flow rate, and aortic pressure, and the geometric data includes point cloud data of the ventricular assist device; The parameter prediction module is used to predict the target performance parameters of the ventricular assist device based on the target operating data and geometric data, using a pre-built digital twin model, wherein the digital twin model represents the coupling model of the ventricular assist device and the cardiovascular system. The target operating data includes first operating data under rated operating conditions and second operating data under extreme operating conditions. The target performance parameters include first performance parameters corresponding to the first operating data and second performance parameters corresponding to the second operating data. The design optimization module includes: The change determination submodule is used to determine the rate of change characterizing the relationship between the first performance parameter and the second performance parameter. The design optimization submodule is specifically used to: if the rate of change is greater than a first preset rate of change threshold and less than a second preset rate of change threshold, calculate the difference between the rate of change and the first preset rate of change threshold; convert the calculated difference into a corresponding performance parameter offset according to a preset correspondence; calculate a first sum between the performance parameter offset and the first performance parameter; calculate a second sum between the performance parameter offset and the second performance parameter; determine the first sum and the second sum as the adjusted performance parameters; and determine the geometric design corresponding to the best performance parameter among the adjusted performance parameters as the target design of the ventricular assist device; if the rate of change is less than the first preset rate of change threshold, determine the geometric design corresponding to the best performance parameter among the performance parameters as the target design of the ventricular assist device.

4. The apparatus according to claim 3, characterized in that, The digital twin model includes an input layer, a feature extraction and fusion layer, and a multi-task output layer, wherein: The input layer is used to standardize and adjust the input target running data and geometric data, and then input the adjusted target running data and geometric data into the feature extraction and fusion layer. The feature extraction and fusion layer is used to extract the running features of the target running data and the geometric features of the geometric data, and to concatenate the running features and the geometric features to obtain the concatenated features; The multi-task output layer is used to process the spliced ​​features using the decoder corresponding to each performance parameter index, calculate the parameter value corresponding to the performance parameter index as the performance prediction result, and output the performance prediction result.

5. An electronic medical device, characterized in that, It includes 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; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method steps of any one of claims 1-2.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method steps of any one of claims 1-2.

Images