Thromboelasticity detection system parameter identification method and system, equipment, and storage medium

Abstract

The present invention provides a method and system, device, and storage medium for identifying parameters of a thrombus elasticity detection system. The method comprises the following steps: applying an initial displacement to the thrombus elasticity detection system and acquiring a displacement response signal from the thrombus elasticity detection system; preprocessing the displacement response signal; and using the preprocessed signal as input to a deep learning model to predict parameters of the thrombus elasticity detection system. The present invention requires only a single signal acquisition for the thrombus elasticity detection system, eliminating the need for multiple acquisitions of output signals. This minimizes the amount of work required and makes it suitable for large-scale batch system parameter identification. The parameters of the thrombus elasticity detection system obtained by the present invention can be directly read, eliminating the need for post-processing calculations. The parameter acquisition method is simple, lowering the barrier to entry. The present invention eliminates the need for manual operation of key components of the thrombus elasticity detection system, eliminating the need to shut down the equipment for preventive testing, reducing time consumption and testing costs.

Description

Technical Field

[0001] The present invention relates to the technical field of coagulation detection and analysis, and in particular to a parameter identification method and system, equipment, and storage medium for a thrombus elasticity detection system. Background Art

[0002] The thromboelastogram is a curve showing the change of thrombus elasticity over time. It is used to indicate the changes in viscoelasticity of blood clots during the patient's coagulation, platelet aggregation, and fibrinolysis. It can be used for continuous and comprehensive analysis of the patient's coagulation status.

[0003] The thromboelastometry curve is obtained by drawing the data output by the thromboelastometry detection system using the corresponding software. Whether the values ​​of the parameters (elasticity coefficient and damping coefficient) of the thromboelastometry detection system are normal is crucial to ensuring the accuracy of the test results.

[0004] In the existing method, the status of the thrombus elasticity detection system requires adding a counterweight to the detection system, and the output signal of the detection system needs to be collected multiple times, and the parameters of the thrombus elasticity detection system need to be obtained through post-processing calculations. Using this method to determine whether the status of the thrombus elasticity detection system is normal requires shutting down the equipment and manually operating the key parts of the detection system. The detection platform is difficult to build, time-consuming, and the detection cost is high. Summary of the Invention

[0005] In order to achieve the above-mentioned purpose and other advantages of the present invention, the first purpose of the present invention is to provide a method for identifying parameters of a thrombus elasticity detection system, comprising the following steps:

[0006] applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system;

[0007] Preprocessing the displacement response signal;

[0008] The preprocessed signal is used as the input of the deep learning model to predict the parameters of the thrombus elasticity detection system.

[0009] Furthermore, the step of applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system includes:

[0010] According to the theory of rotational dynamics, the vibration equation of the thrombus elasticity detection system is constructed:

[0011]

[0012] Where J is the moment of inertia of the thromboelastometry system, in kg / m 2 , c is the damping coefficient, k is the elastic coefficient, θ(t) is the angular displacement, T(t) is the torque applied to the system, in N·m;

[0013] By solving the vibration equation, the displacement response of the thrombus elasticity detection system under different conditions is obtained:

[0014]

[0015] Among them, ω n is the natural frequency, ω d is the damped vibration frequency phase, is the damping ratio of the thromboelastometry system, and C1 and C2 are constants.

[0016] Furthermore, the step of applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system includes:

[0017] Based on the fact that the system damping ratio is less than 1 in this application, the displacement response of the thrombus elasticity detection system is:

[0018]

[0019] Among them, A0 is the amplitude, is the initial phase, ω n 、ω d 、 The following relationship is satisfied:

[0020]

[0021] Furthermore, the step of preprocessing the displacement response signal includes:

[0022] Perform fast Fourier transform on the displacement response signal θ(t), analyze its frequency domain components, and determine its natural frequency ω n ;

[0023] Perform bandpass filtering on the original signal.

[0024] Furthermore, the deep learning model includes an input layer, multiple long short-term memory layers, and an output layer, wherein the output of the input layer is connected to the first long short-term memory layer, multiple long short-term memory layers are connected in sequence, and the output of the last long short-term memory layer is connected to the output layer; wherein,

[0025] The input layer comprises a plurality of long short-term memory units;

[0026] Each of the long short-term memory layers includes a plurality of long short-term memory units;

[0027] The output layer is a fully connected layer containing neurons.

[0028] Furthermore, the training of the deep learning model includes the following steps:

[0029] The displacement response signal is preprocessed and used as a training set;

[0030] Inputting data of a preset length window into the deep learning model each time;

[0031] In the process of updating the network weights according to the gradient descent of the loss function, the learnable parameters in the loss function are updated at the same time until the loss function value drops to the preset range.

[0032] Furthermore, the loss function with learnable parameters is defined as:

[0033] Loss=Loss MSE +Loss PI

[0034] Among them, Loss MSE is the mean square error between the output value and the true value, Loss PI In order to evaluate the loss of physical information, a vibration equation of the thromboelastomeric detection system is constructed, which includes two learnable parameters for estimating the elastic coefficient and damping coefficient of the system.

[0035] Furthermore, the parameters of the thrombus elasticity detection system include an elastic coefficient and a damping coefficient.

[0036] The second object of the present invention is to provide a parameter identification system for a thrombus elasticity detection system, which implements the above method and includes a displacement response signal acquisition module, a signal preprocessing module, and a parameter prediction module; wherein,

[0037] The displacement response signal acquisition module is used to apply an initial displacement to the thrombus elasticity detection system and acquire the displacement response signal of the thrombus elasticity detection system;

[0038] The signal preprocessing module is used to preprocess the displacement response signal;

[0039] The parameter prediction module is used to use the preprocessed signal as the input of the deep learning model to predict the parameters of the thrombus elasticity detection system.

[0040] A third object of the present invention is to provide a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0041] A fourth object of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention only requires one signal acquisition at most for the thrombus elasticity detection system, and does not require multiple acquisitions of output signals. The operation amount is small, and the invention is suitable for large-scale batch system parameter identification.

[0044] The parameters of the thrombus elasticity detection system obtained by the present invention can be directly read without the need for post-processing calculations. The method for obtaining the parameters is simple, which reduces the threshold for use.

[0045] The present invention does not require manual operation of key parts of the thrombus elasticity detection system, so there is no need to stop the equipment during preventive detection, which consumes less time and has lower detection costs.

[0046] The present invention constructs a learning model consisting of long short-term memory units and a loss function containing physical information items of learnable parameters. Since the model introduces prior physical information, it requires little training data and has good parameter identification effect.

[0047] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and to implement it according to the contents of the description, the following preferred embodiments of the present invention are described in detail with reference to the accompanying drawings. The specific implementation methods of the present invention are given in detail by the following embodiments and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0049] Figure 1 This is a flow chart of the parameter identification method of the thrombus elasticity detection system of Example 1;

[0050] Figure 2 This is a flow chart of displacement response signal acquisition in Example 1;

[0051] Figure 3 This is a flow chart of displacement response signal preprocessing in Example 1;

[0052] Figure 4 This is a training flow chart of the deep learning model of Example 1;

[0053] Figure 5 Schematic diagram of fast Fourier transform of displacement response signal;

[0054] Figure 6 is a schematic diagram of the filter amplitude response;

[0055] Figure 7 Schematic diagram of signal waveform before preprocessing;

[0056] Figure 8 Schematic diagram of signal waveform after preprocessing;

[0057] Figure 9 Schematic diagram of the deep learning model structure;

[0058] Figure 10 Schematic diagram of the parameter identification system of the thrombus elasticity detection system of Example 2;

[0059] Figure 11 This is a schematic diagram of the computer equipment of Example 3;

[0060] Figure 12 Schematic diagram of a computer-readable storage medium of Example 4. DETAILED DESCRIPTION

[0061] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. It should be noted that, without conflict, the embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0062] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0063] The figure numbers in this application are only used to distinguish the various steps in the scheme and are not used to limit the execution order of the various steps. The specific execution order is subject to the description in the specification.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0065] Example 1

[0066] A method for identifying parameters of a thromboelastometry system, such as Figure 1 As shown, the following steps are included:

[0067] S1. applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system;

[0068] In some embodiments, as Figure 2 As shown, the steps of applying an initial displacement to the thrombus elasticity detection system and collecting the displacement response signal of the thrombus elasticity detection system include:

[0069] S11. Based on the theory of rotational dynamics, the vibration equation of the thrombus elasticity detection system is constructed:

[0070]

[0071] Where J is the moment of inertia of the thromboelastometry system, in kg / m 2 , c is the damping coefficient, k is the elastic coefficient, θ(t) is the angular displacement, T(t) is the torque applied to the system, in N·m;

[0072] S12. Solve the vibration equation to obtain the displacement response of the thromboelasticity detection system under different conditions:

[0073]

[0074] Among them, ω n is the natural frequency, ω d is the damped vibration frequency phase, is the damping ratio of the thromboelastometry system, and C1 and C2 are constants.

[0075] Based on the fact that the system damping ratio is less than 1 in this application, the displacement response of the thrombus elasticity detection system is:

[0076]

[0077] Among them, A0 is the amplitude, is the initial phase, ω n 、ω d 、 The following relationship is satisfied:

[0078]

[0079] S2. preprocessing the displacement response signal;

[0080] In some embodiments, as Figure 3 As shown, the step of preprocessing the displacement response signal includes:

[0081] S21, perform fast Fourier transform on the displacement response signal θ(t), refer to Figure 5 , analyze its frequency domain components and determine its natural frequency ω n , for example, to determine its natural frequency ω n About 5.4Hz.

[0082] S22, bandpass filtering the original signal; for example, the filter passband is set to 4.4 to 6.4 Hz, and the filter amplitude response in this embodiment is referenced Figure 6 , signal waveforms before and after preprocessing refer to Figure 7 、 Figure 8.

[0083] S3. Use the preprocessed signal as the input of the deep learning model to predict the parameters of the thrombus elasticity detection system.

[0084] In some embodiments, the deep learning model includes an input layer, multiple long short-term memory layers, and an output layer, wherein the output of the input layer is connected to the first long short-term memory layer, multiple long short-term memory layers are connected in sequence, and the output of the last long short-term memory layer is connected to the output layer; wherein,

[0085] The input layer comprises a plurality of long short-term memory units;

[0086] Each of the long short-term memory layers includes a plurality of long short-term memory units;

[0087] The output layer is a fully connected layer containing neurons.

[0088] like Figure 9 As shown, the constructed deep learning model has a total of five layers, and the structure includes an input layer, three long short-term memory layers, and an output layer. In this embodiment, the parameters of each layer are set as follows: the input layer contains 50 long short-term memory units, the input step size is 50, the input data is 1-dimensional data, and the output length is 50. One-dimensional sequence, connected to the next long short-term memory layer; three long short-term memory layers each contain 100 long short-term memory units, the first two layers each output a one-dimensional sequence of length 50 and connect to the next layer, and the output length of the last long short-term memory layer is 1 and connected to the output layer; the output layer is a fully connected layer containing one neuron, and the activation function is the PReLU function.

[0089] Specifically, if Figure 4 As shown, the training of the deep learning model includes the following steps:

[0090] S300, pre-processing the displacement response signal as a training set;

[0091] S310. Input data of a preset length window into the deep learning model each time; for example, input data with a window length of 50 into the deep learning model each time.

[0092] S320. In the process of updating the network weights according to the gradient descent of the loss function, the learnable parameters in the loss function are simultaneously updated until the loss function value drops to a preset range, for example, until the loss function Loss value drops below 0.01.

[0093] In this embodiment, the loss function containing learnable parameters is defined as:

[0094] Loss=Loss MSE +Loss PI

[0095] Among them, Loss MSE is the mean square error between the output value and the true value, Loss PI In order to evaluate the loss of physical information, a vibration equation of the thromboelastomeric detection system is constructed, which includes two learnable parameters for estimating the elastic coefficient and damping coefficient of the system.

[0096] After the training is completed, the parameter estimates of the elastic coefficient and damping coefficient of the thrombus elastography detection system can be obtained by reading the latest updated parameters to be learned in the deep learning model.

[0097] The parameter estimates for the elasticity coefficient and damping coefficient obtained in this example are 56.19718 and 0.03020, respectively. Given that the normal range for the elasticity coefficient of a thromboelastometry system is 52-62, and the normal range for the damping coefficient is 0-0.05, the elasticity coefficient and damping coefficient measured in this example are both within the normal range. Therefore, the system parameter identification is correct.

[0098] This embodiment provides a thrombus elasticity detection system parameter identification method for parameter identification of the elastic coefficient and damping coefficient of the thrombus elasticity detection system, which is conducive to determining the status of the thrombus elasticity detection system and thereby ensuring the accuracy and consistency of the detection results between thrombus elasticity detection systems.

[0099] Example 2

[0100] A thrombus elasticity detection system parameter identification system implements the above method. For a detailed description of the method, please refer to the corresponding description in the above method embodiment, which will not be repeated here. Figure 10 As shown, the system includes a displacement response signal acquisition module 41, a signal preprocessing module 42, and a parameter prediction module 43; wherein,

[0101] The displacement response signal acquisition module is used to apply an initial displacement to the thrombus elasticity detection system and acquire the displacement response signal of the thrombus elasticity detection system;

[0102] The signal preprocessing module is used to preprocess the displacement response signal;

[0103] The parameter prediction module is used to use the preprocessed signal as the input of the deep learning model to predict the parameters of the thrombus elasticity detection system.

[0104] Based on the technical solution of the above embodiment, optionally, the step of applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system includes:

[0105] According to the theory of rotational dynamics, the vibration equation of the thrombus elasticity detection system is constructed:

[0106]

[0107] Where J is the moment of inertia of the thromboelastometry system, in kg / m 2 , c is the damping coefficient, k is the elastic coefficient, θ(t) is the angular displacement, T(t) is the torque applied to the system, in N·m;

[0108] By solving the vibration equation, the displacement response of the thrombus elasticity detection system under different conditions is obtained:

[0109]

[0110] Among them, ω n is the natural frequency, ω d is the damped vibration frequency phase, is the damping ratio of the thromboelastometry system, and C1 and C2 are constants.

[0111] Based on the technical solution of the above embodiment, optionally, the step of applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system includes:

[0112] Based on the fact that the system damping ratio is less than 1 in this application, the displacement response of the thrombus elasticity detection system is:

[0113]

[0114] Among them, A0 is the amplitude, is the initial phase, ω n 、ω d 、 The following relationship is satisfied:

[0115]

[0116] Based on the technical solution of the above embodiment, optionally, the step of pre-processing the displacement response signal includes:

[0117] Perform fast Fourier transform on the displacement response signal θ(t), analyze its frequency domain components, and determine its natural frequency ω n ;

[0118] Perform bandpass filtering on the original signal.

[0119] Based on the technical solution of the above embodiment, optionally, the deep learning model includes an input layer, multiple long short-term memory layers, and an output layer, the output of the input layer is connected to the first long short-term memory layer, the multiple long short-term memory layers are connected in sequence, and the output of the last long short-term memory layer is connected to the output layer; wherein,

[0120] The input layer comprises a plurality of long short-term memory units;

[0121] Each of the long short-term memory layers includes a plurality of long short-term memory units;

[0122] The output layer is a fully connected layer containing neurons.

[0123] Based on the technical solution of the above embodiment, optionally, the training of the deep learning model includes the following steps:

[0124] The displacement response signal is preprocessed and used as a training set;

[0125] Inputting data of a preset length window into the deep learning model each time;

[0126] In the process of updating the network weights according to the gradient descent of the loss function, the learnable parameters in the loss function are updated at the same time until the loss function value drops to the preset range.

[0127] Based on the technical solution of the above embodiment, optionally, the loss function containing learnable parameters is defined as:

[0128] Loss=Loss MSE +Loss PI

[0129] Among them, Loss MSE is the mean square error between the output value and the true value, Loss PI In order to evaluate the loss of physical information, a vibration equation of the thromboelastomeric detection system is constructed, which includes two learnable parameters for estimating the elastic coefficient and damping coefficient of the system.

[0130] Based on the technical solutions of the above embodiments, optionally, the parameters of the thrombus elasticity detection system include an elastic coefficient and a damping coefficient.

[0131] This embodiment provides a thrombus elasticity detection system parameter identification system for parameter identification of the elastic coefficient and damping coefficient of the thrombus elasticity detection system, which is conducive to determining the status of the thrombus elasticity detection system and thereby ensuring the accuracy and consistency of the detection results between thrombus elasticity detection systems.

[0132] Example 3

[0133] A computer device 500, such as Figure 11 As shown, the system includes a memory 510, a processor 520, and a computer program 530 stored in the memory and executable by the processor. When the processor executes the computer program, the steps of a method for identifying parameters of a thromboelastometry system are implemented. For a detailed description of the method, please refer to the corresponding description in the above method embodiment and will not be repeated here.

[0134] Example 4

[0135] A computer-readable storage medium such as Figure 12 As shown, a computer program is stored thereon, and when the computer program is executed by the processor, the steps of a method for identifying parameters of a thrombus elasticity detection system are implemented. For a detailed description of the method, reference can be made to the corresponding description in the above method embodiment, which will not be repeated here.

[0136] Example 5

[0137] A computer program product includes a computer program that, when executed by a processor, implements the steps of a method for identifying parameters of a thromboelastometry system. For a detailed description of the method, reference may be made to the corresponding description in the above method embodiment and will not be repeated here.

[0138] The number of devices and processing scales described herein are intended to simplify the description of the present invention. Applications, modifications, and variations of the present invention will be readily apparent to those skilled in the art.

[0139] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the description and implementation methods. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

[0140] The apparatus, computer device, non-volatile computer storage medium, and method provided in the embodiments of this specification correspond to each other. Therefore, the apparatus, computer device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, computer device, and non-volatile computer storage medium will not be repeated here.

[0141] Those skilled in the art will also appreciate that, in addition to implementing the controller in pure computer-readable program code, it is entirely possible to implement the same functionality by programming the method steps logically, such as through logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices included therein for implementing various functions can also be considered structures within the hardware component. Alternatively, the devices for implementing various functions can be considered both software units implementing the method and structures within the hardware component.

[0142] The systems, devices, or units described in the above embodiments can be implemented by computer chips or physical devices, or by products with certain functions. For ease of description, the above devices are described separately by function, with each unit described separately. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware components.

[0143] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0147] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0148] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program units. Generally, program units include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program units may be located in local and remote computer storage media, including storage devices.

[0149] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0150] The foregoing is merely an example of the present invention and is not intended to limit the present invention to one or more embodiments. It will be apparent to those skilled in the art that various modifications and variations may be made to the present invention to one or more embodiments. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention to one or more embodiments shall be included within the scope of the claims of the present invention to one or more embodiments.

Claims

1. A method for identifying parameters of a thromboelastometry system, characterized in that: The following steps are involved: applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system; Preprocessing the displacement response signal; The preprocessed signal is used as the input of the deep learning model to predict the parameters of the thromboelastometry system; The step of applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system includes: Based on the fact that the system damping ratio is less than 1 in this application, the displacement response of the thrombus elasticity detection system is: ， in, is the amplitude, is the initial phase, is the natural frequency, is the damped vibration frequency phase, is the damping ratio of the thromboelastometry system, 、 、 Satisfies the following relationship: ， , ； Where, k is the elastic coefficient and c is the damping coefficient; The training of the deep learning model includes the following steps: The displacement response signal is preprocessed and used as a training set; Inputting data of a preset length window into the deep learning model each time; In the process of updating the network weights according to the gradient descent of the loss function, the learnable parameters in the loss function are updated at the same time until the loss function value drops to the preset range; The loss function with learnable parameters is defined as: ， in, is the mean square error between the output value and the true value, In order to evaluate the loss of physical information, a vibration equation of the thromboelastomeric detection system is constructed, which includes two learnable parameters for estimating the elastic coefficient and damping coefficient of the system.

2. The method for identifying parameters of a thrombus elasticity detection system according to claim 1, wherein: The step of applying an initial displacement to the thrombus elasticity detection system and collecting a displacement response signal of the thrombus elasticity detection system includes: According to the theory of rotational dynamics, the vibration equation of the thrombus elasticity detection system is constructed: ， in, is the moment of inertia of the thromboelastometry system, in units of , is the angular displacement, is the torque on the system, in units of ; By solving the vibration equation, the displacement response of the thrombus elasticity detection system under different conditions is obtained: ， in, , is a constant.

3. The method for identifying parameters of a thrombus elasticity detection system according to claim 1, wherein: The step of pre-processing the displacement response signal comprises: The displacement response signal Perform fast Fourier transform to analyze its frequency domain components and determine its natural frequency ; Perform bandpass filtering on the original signal.

4. The method for identifying parameters of a thromboelastometry system according to claim 2, wherein: The deep learning model includes an input layer, multiple long short-term memory layers, and an output layer. The output of the input layer is connected to the first long short-term memory layer. The multiple long short-term memory layers are connected in sequence, and the output of the last long short-term memory layer is connected to the output layer. The input layer comprises a plurality of long short-term memory units; Each of the long short-term memory layers includes a plurality of long short-term memory units; The output layer is a fully connected layer containing neurons.

5. The method for identifying parameters of a thromboelastometry system according to claim 1, wherein: The parameters of the thrombus elasticity detection system include elasticity coefficient and damping coefficient.

6. A thromboelastometry system parameter identification system, implementing the method according to any one of claims 1 to 5, characterized in that: It includes displacement response signal acquisition module, signal preprocessing module and parameter prediction module; among them, The displacement response signal acquisition module is used to apply an initial displacement to the thrombus elasticity detection system and acquire the displacement response signal of the thrombus elasticity detection system; The signal preprocessing module is used to preprocess the displacement response signal; The parameter prediction module is used to use the preprocessed signal as the input of the deep learning model to predict the parameters of the thrombus elasticity detection system.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images