Plasma matrix product attribute parameter determination method based on blood analysis data

Abstract

The invention discloses a plasma matrix product attribute parameter determination method based on blood analysis data. The method comprises the following steps: acquiring multiple groups of blood analysis sample data and plasma matrix preparation sample data; performing model training based on a mapping relation between the blood analysis sample data and the plasma matrix preparation sample data to obtain a plasma matrix product attribute parameter prediction model; and processing to-be-detected blood detection data based on the prediction model to obtain corresponding plasma matrix product attribute parameter prediction data. Correlation analysis is carried out on blood test results of different patients and plasma matrix preparation effects in advance, learning simulation is carried out on the relation between the blood test results and the plasma matrix preparation effects, the plasma matrix product attribute parameter prediction model is obtained, then model application can be carried out on whole blood analysis results of the patients in the plasma matrix preparation process, and the prediction accuracy of the plasma matrix product attribute parameters is improved. Plasma matrix product attribute parameter data most matched with the blood condition of a specific patient is obtained, and subsequent parameter adjustment is facilitated, so that the preparation effect of the plasma matrix is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of plasma matrix preparation, and more specifically, to a method for determining attribute parameters of a plasma matrix product based on blood analysis data. Background Art

[0002] As a product of autologous blood centrifugation, plasma matrix has good effects in the fields of medical treatment, beauty, repair, etc. There are many parameters for the preparation of plasma matrix, and a large number of studies have focused on the effects of different preparation parameters on the mechanical and biological properties of the final preparation product. These include: secondary centrifugation, mild centrifugation, variable speed centrifugation, etc.

[0003] However, considering that the existing parameter formulations are universal parameters determined through basic research, individual differences of patients are not involved. Therefore, regardless of the mode, a fixed centrifugation program (centrifugal force and centrifugation time) is built into the plasma matrix preparation platform. However, in actual clinical applications, there may be huge differences in the plasma matrices prepared by different patients, and the yield of their liquid plasma matrices may differ by as much as 1 / 3; in addition, the coagulation time of the final prepared solid plasma matrix may differ by more than 3 times. In this way, it is impossible to obtain dynamic plasma matrix product attribute parameter data that best matches the blood condition of a specific patient, which makes it impossible to facilitate subsequent parameter adjustment to ensure the preparation effect of the plasma matrix. Summary of the invention

[0004] In response to at least one defect or improvement need in the prior art, the present application provides a method for determining plasma matrix product attribute parameters based on blood analysis data, which is used to obtain personalized and dynamic plasma matrix product attribute parameter data that best matches the blood condition of a specific patient, thereby facilitating subsequent parameter adjustment to ensure the preparation effect of the plasma matrix.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for determining attribute parameters of a plasma matrix product based on blood analysis data, comprising:

[0006] Acquire multiple sets of blood analysis sample data and plasma matrix preparation sample data; the plasma matrix preparation sample data is sample data of plasma matrix successfully prepared by using the blood analysis sample data;

[0007] Performing model training based on the mapping relationship between the blood analysis sample data and the plasma matrix preparation sample data to obtain a plasma matrix product attribute parameter prediction model;

[0008] The blood test data to be tested are processed based on the plasma matrix product attribute parameter prediction model to obtain corresponding plasma matrix product attribute parameter prediction data.

[0009] Furthermore, the model training is performed based on the mapping relationship between the blood analysis sample data and the plasma matrix preparation sample data to obtain a plasma matrix product attribute parameter prediction model, including:

[0010] The blood analysis sample data is used as input and the plasma matrix preparation sample data is used as output to perform model training to obtain the plasma matrix product attribute parameter prediction model.

[0011] Further,

[0012] The method of processing the blood test data to be tested based on the plasma matrix product attribute parameter prediction model to obtain corresponding plasma matrix product attribute parameter prediction data includes:

[0013] Acquiring the blood test data to be tested;

[0014] The blood test data to be tested is input into the plasma matrix product attribute parameter prediction model to obtain corresponding plasma matrix product attribute parameter prediction data.

[0015] Furthermore, after inputting the blood test data to be tested into the plasma matrix product attribute parameter prediction model to obtain the corresponding plasma matrix product attribute parameter prediction data, the method further includes:

[0016] Perform actual preparation of plasma matrix based on the blood test data to be tested, and obtain actual data of plasma matrix product attribute parameters;

[0017] If the predicted data of the plasma matrix product attribute parameters do not match the actual data of the plasma matrix product attribute parameters, the plasma matrix product attribute parameter prediction model is adjusted and optimized based on the actual data of the plasma matrix product attribute parameters to obtain an optimized plasma matrix product attribute parameter prediction model.

[0018] Furthermore, if the predicted data of the plasma matrix product attribute parameters do not match the actual data of the plasma matrix product attribute parameters, the plasma matrix product attribute parameter prediction model is adjusted and optimized based on the actual data of the plasma matrix product attribute parameters to obtain the optimized plasma matrix product attribute parameter prediction model, including:

[0019] Comparing the predicted data of the plasma matrix product attribute parameters with the actual data of the plasma matrix product attribute parameters to obtain comparative analysis results and a fit report;

[0020] When the comparative analysis result and the fitting report indicate that the predicted data of the plasma matrix product attribute parameters do not match the actual data of the plasma matrix product attribute parameters, the plasma matrix product attribute parameter prediction model is adjusted and optimized according to the actual data of the plasma matrix product attribute parameters and the blood test data to be tested to obtain the optimized plasma matrix product attribute parameter prediction model.

[0021] Furthermore, the blood test data to be tested is obtained by performing a blood test on the patient's whole blood using a blood analysis instrument;

[0022] The blood analysis sample data is obtained by analyzing the patient's sample blood through a blood analysis instrument;

[0023] The plasma matrix preparation sample data is obtained after the plasma matrix is ​​prepared successfully on the patient's sample blood by a plasma matrix centrifuge.

[0024] Furthermore, the blood analysis sample data includes one or more of white blood cells, red blood cells, platelets, hematocrit, coefficient of variation of red blood cell distribution width, mean red blood cell volume, hemoglobin content, neutrophils, lymphocytes, monocytes, eosinophils, basophils, large platelet ratio, mean platelet volume, hematocrit, mean platelet distribution width, activated partial thromboplastin time, plasma prothrombin time, thrombin time, prothrombin time ratio, fibrinogen, prothrombin INR, prothrombin activity and glucose.

[0025] Further, the plasma matrix preparation sample data and the plasma matrix product attribute parameters respectively include plasma matrix preparation sample physical data and plasma matrix preparation sample biological data;

[0026] The physical data of the plasma matrix preparation sample includes at least one of the following: plasma matrix product volume, solid plasma matrix coagulation time, liquid plasma matrix coagulation time, solid plasma matrix mass, plasma matrix membrane mass, plasma matrix membrane maximum stress, and plasma matrix membrane maximum strain;

[0027] The biological data of the plasma matrix preparation sample includes at least one of the content and distribution of growth factors in the plasma matrix, the content and distribution of cells in the plasma matrix, the effect of the plasma matrix on promoting soft tissue regeneration, and the effect of the plasma matrix on promoting bone regeneration.

[0028] In a second aspect, the present application provides an electronic device comprising at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit is enabled to perform the steps of any of the aforementioned attribute parameter determination methods.

[0029] In a third aspect, the present application provides a storage medium storing a computer program executable by an access authentication device, which enables the access authentication device to perform the steps of any of the aforementioned attribute parameter determination methods when the computer program is run on the access authentication device.

[0030] In general, the above technical solutions conceived by the present application can achieve the following beneficial effects compared with the prior art:

[0031] This application has previously conducted a correlation analysis on the blood test results of different patients and the effect of their plasma matrix preparation, and has simulated the relationship between the two, and obtained a plasma matrix product attribute parameter prediction model, so that the model can be applied to the patient's whole blood analysis results during the preparation of the plasma matrix, and the dynamic plasma matrix product attribute parameter data that best matches the blood condition of a specific patient is obtained, which is convenient for subsequent parameter adjustment to ensure the preparation effect of the plasma matrix. That is, after obtaining these plasma matrix product attribute parameter prediction data, it can also be used to preliminarily understand the product characteristics of the plasma matrix prepared by individual patients, so as to adjust the relevant parameters according to clinical needs, and finally achieve the effect required by clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A core flow chart of a method for determining plasma matrix product attribute parameters based on blood analysis data provided in an embodiment of the present application;

[0034] Figure 2 A schematic diagram comparing the strength of an expected prepared plasma matrix and the strength of an actually prepared plasma matrix provided in an embodiment of the present application;

[0035] Figure 3 A schematic diagram of correlation analysis between a blood analysis result and a final plasma matrix yield provided in an embodiment of the present application;

[0036] Figure 4 A block diagram of an electronic device provided in an embodiment of the present application and suitable for implementing the attribute parameter determination method described above. DETAILED DESCRIPTION

[0037] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0038] The terms "including" or "having" and any variations thereof in the specification, claims or drawings of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0039] Plasma matrix, as a product of autologous blood centrifugation, is mainly composed of growth factors, platelets, leukocytes and fiber scaffolds. It has the function of regeneration and repair. It has been widely used in the fields of oral and maxillofacial soft and hard tissue regeneration and repair, skin beauty, and injection treatment of osteoarthritis, and has achieved good results.

[0040] There are many factors that affect the final plasma matrix preparation effect, among which blood-related indicators are particularly important. At present, medical centrifuges are usually used for the preparation of clinical plasma matrices, which have fixed preparation procedures. However, in actual clinical applications, there may be huge differences in the plasma matrices prepared by different patients, and the output of their liquid plasma matrices may differ by up to 1 / 3; in addition, the coagulation time of the solid plasma matrix finally prepared may differ by more than 3 times. In this way, it is impossible to obtain the dynamic plasma matrix product attribute parameter data that best matches the blood condition of a specific patient, and thus the preparation effect of the plasma matrix cannot be guaranteed. In view of this, the present application proposes a parameter determination method, device and medium based on plasma matrix preparation, which is used to obtain personalized dynamic plasma matrix product attribute parameter data that best matches the blood condition of a specific patient, so as to facilitate subsequent parameter adjustment to ensure the preparation effect of the plasma matrix.

[0041] refer to Figure 1 An embodiment of the present application proposes a method for determining attribute parameters of a plasma matrix product based on blood analysis data. The attribute parameter determination method may mainly include the following steps.

[0042] Step 1: Acquire multiple groups of blood plasma sample data. Each group of blood plasma sample data may specifically include: blood analysis sample data and plasma matrix preparation sample data (i.e., plasma matrix product attribute parameter type data), wherein the plasma matrix preparation sample data is sample data of plasma matrix successfully prepared through blood analysis sample data.

[0043] It should be noted that the plasma matrix is ​​prepared from blood. Blood with different parameters will produce different plasma matrices. In order to be able to prepare patient-specific plasma matrices in the subsequent clinical setting, this can be achieved in advance through model learning and training.

[0044] The blood analysis sample data may be data obtained after analyzing the patient's sample blood using a blood analysis instrument.

[0045] Blood analyzers, also known as blood cell analyzers, blood cell meters or blood cell counters, are precision medical devices used to detect the number, morphology and distribution of various cell components in the blood (such as red blood cells, white blood cells and platelets, etc.). The principles of blood analyzers can be summarized into photoelectric, capacitive, resistive, centrifugal and laser scattering. Among them, photoelectric, capacitive and resistive types measure the size, number and electrical properties of cells by physical methods; centrifugal uses centrifugal force to separate cells of different weights; and laser scattering uses laser beams to illuminate cells and infer the morphology and structure of cells by measuring the intensity and direction of scattered light.

[0046] In some embodiments, the blood analysis sample data may specifically include: white blood cells, red blood cells, platelets, hematocrit, red blood cell distribution width variation coefficient, mean red blood cell volume, hemoglobin content, neutrophils, lymphocytes, monocytes, eosinophils, basophils, large platelet ratio, mean platelet volume, platelet hematocrit, mean platelet distribution width, activated partial prothromboplastin time, plasma prothrombin time, thrombin time, prothrombin time ratio, fibrinogen, prothrombin INR, prothrombin activity, glucose and other parameters.

[0047] The plasma matrix preparation sample data may be data obtained after the plasma matrix is ​​successfully prepared on the patient's sample blood using a plasma matrix centrifuge.

[0048] The plasma matrix centrifuge instrument, which is commonly referred to as a plasma centrifuge, is a device widely used in medicine, biology and laboratories. A plasma centrifuge is a special instrument that uses centrifugal force to separate blood into plasma and other components (such as gel, cells, etc.). It is often used as an instrument for separating serum, plasma, precipitating protein or urine sediment examination in medical examinations. The working principle of a plasma centrifuge is based on centrifugal force, which is the force generated when an object moves in a circle around a certain orbit. In a plasma centrifuge, the magnitude of the centrifugal force can be controlled by adjusting the speed of the centrifuge. When the centrifuge starts to rotate, due to the different densities of the various components in the blood, the centrifugal forces they are subjected to are also different, so stratification will occur, thereby achieving the separation of plasma and other components.

[0049] In some embodiments, the plasma matrix preparation sample data (plasma matrix product attribute parameter data) may specifically include: plasma matrix preparation sample physical data and plasma matrix preparation sample biological data.

[0050] The physical data of the plasma matrix preparation sample may specifically include: at least one of the following: plasma matrix product volume, solid plasma matrix coagulation time, liquid plasma matrix coagulation time, solid plasma matrix mass, plasma matrix membrane mass, plasma matrix membrane maximum stress and plasma matrix membrane maximum strain.

[0051] The biological data of the plasma matrix preparation sample may specifically include at least one of the content and distribution of growth factors in the plasma matrix, the content and distribution of cells in the plasma matrix, the effect of the plasma matrix on promoting soft tissue regeneration, and the effect of the plasma matrix on promoting bone regeneration.

[0052] Step 2: Perform model training based on multiple groups of blood plasma sample data, that is, perform model training based on the mapping relationship between blood analysis sample data and plasma matrix preparation sample data to obtain a plasma matrix product attribute parameter prediction model.

[0053] In some embodiments, after obtaining multiple groups of blood plasma sample data, model training can be performed on the multiple groups of blood plasma sample data, that is, the mapping relationship between the blood analysis sample data and the plasma matrix preparation sample data can be learned through the model, so as to obtain a plasma matrix product attribute parameter prediction model, wherein the input item of the plasma matrix product attribute parameter prediction model is the blood analysis sample data, and the output item is the plasma matrix preparation sample data.

[0054] The input blood analysis sample data can be directly obtained through testing, and the output plasma matrix preparation sample data can be directly obtained through clinical measurement. Both data do not require additional data preprocessing before training as in the prior art.

[0055] During model training, the model will also be optimized based on the actual output and plasma matrix preparation sample data. That is, after inputting the blood analysis sample data, the loss function is obtained by comparing the obtained output items with the plasma matrix preparation sample data. The model is then fine-tuned and optimized using the loss function to ultimately obtain a plasma matrix product attribute parameter prediction model that can obtain the most suitable data for plasma matrix preparation corresponding to the blood data.

[0056] In some embodiments, plasma matrix separation is currently achieved by horizontal centrifugation, and parameters include centrifugal force, centrifugal radius, and centrifugal time. Through the results of blood tests, the patient's coagulation function state, as well as the differences in the types and numbers of internal cells can be anticipated, and this part is patient-specific. However, the final standards or goals for preparing plasma matrices are consistent, including: better solid plasma matrix coagulation effect, higher mechanical strength, longest liquid plasma matrix coagulation time, best plasma matrix effect in promoting tissue regeneration, as many cells and growth factors as possible, and as evenly distributed as possible. In order to achieve this fixed goal or standard, it is necessary to analyze the patient's individual blood test results and adjust the parameters of the preparation process, that is, a model is needed to realize the process of personalized parameter adjustment.

[0057] The plasma matrix product attribute parameter prediction model requires a large amount of data for analysis, but the plasma matrix is ​​different from conventional AI training data, and it is difficult to obtain a large amount of learning data. The scheme of this application is to jointly carry out multiple centers, and quickly generate the first generation of learning models at the same time to build the foundation. The evolution of the model will be completed by multiple centers in the later stage. But in fact, the data obtained by the blood test equipment used in different centers are different, and the final results lack comparability and consistency, so the data needs to be preprocessed and corrected, which is also one of the reasons why no one is currently doing this direction.

[0058] The trained plasma matrix product attribute parameter prediction model will eventually feed back the output item as a result. This result can quickly guide the clinical parameter selection. Although this parameter is not a parameter used by machine learning, by adjusting this parameter, some data of the plasma matrix sample can be corrected. For example, extending the centrifugation time and reducing the centrifugal force can promote the coagulation of the plasma matrix and reduce the coagulation time. At the same time, the adjustment of parameters can also adjust the distribution of internal biological components and affect the yield of the plasma matrix product finally obtained.

[0059] Step 3: Process the blood test data to be tested based on the plasma matrix product attribute parameter prediction model to predict the corresponding plasma matrix product attribute parameter prediction data.

[0060] After the training of the plasma matrix product attribute parameter prediction model is completed, it can be applied in clinical trials, that is, the whole blood of the patient is collected in the clinic, and then the whole blood of the patient is tested by a blood analysis instrument to obtain the blood test data to be tested of the patient. At this time, the blood test data to be tested can be input into the plasma matrix product attribute parameter prediction model, so as to predict the plasma matrix product attribute parameter prediction data corresponding to the blood test data to be tested. After obtaining these plasma matrix product attribute parameter prediction data, it can be used to preliminarily understand the product characteristics of the plasma matrix prepared by the individual patient, so as to adjust the relevant parameters according to clinical needs, and finally achieve the effect required by the clinic.

[0061] It should be noted that, since the plasma matrix product attribute parameter prediction model is trained based on the blood analysis sample data and the plasma matrix preparation sample data, the plasma matrix product attribute parameter prediction model has learned how to process the blood analysis data to obtain the plasma matrix product attribute parameter prediction data after training. At this time, after the blood test data to be tested is input into the plasma matrix product attribute parameter prediction model, the target parameter prediction model can process and predict the blood test data to be tested to obtain the plasma matrix product attribute parameter prediction data.

[0062] The above are the core steps of a method for determining the attribute parameters of plasma matrix products based on blood analysis data.

[0063] In some embodiments, after the predicted data of the plasma matrix product attribute parameters are obtained, the plasma matrix is ​​actually prepared by a plasma matrix preparation device to obtain the actual data of the plasma matrix product attribute parameters.

[0064] The criteria for successful preparation of plasma matrix may include: obtaining solid plasma matrix and liquid plasma matrix at the same time, separation of solid plasma matrix and red blood cells after centrifugation, solid plasma matrix being in a clampable gel state after preparation, generally in the upper layer of the test tube, and red blood cells generally in the lower layer of the test tube, and liquid plasma matrix being able to maintain a liquid state for more than 60 minutes after preparation.

[0065] The trained plasma matrix product attribute parameter prediction model may also produce prediction deviations during clinical application due to insufficient model training. Therefore, it is also necessary to continuously optimize the model to make the target parameter prediction model more accurate.

[0066] In some embodiments, after obtaining the predicted data of the plasma matrix product attribute parameters, it can be compared with the actual data of the plasma matrix product attribute parameters (obtained by the actual preparation of the plasma matrix based on the blood test data to be tested). If the predicted data of the plasma matrix product attribute parameters match the actual data of the plasma matrix product attribute parameters, it means that the current prediction model is very accurate and very consistent with the actual situation; if it does not match, it means that the current prediction model needs to be optimized. Therefore, the existing prediction model can be adjusted and optimized by the actual data of the plasma matrix product attribute parameters and the blood test data to be tested, so as to obtain the optimized plasma matrix product attribute parameter prediction model.

[0067] The predicted data of plasma matrix product attribute parameters are compared with the actual data of plasma matrix product attribute parameters to obtain comparative analysis results and a fitting report; when the comparative analysis results and the fitting report indicate that the predicted data of plasma matrix product attribute parameters do not match the actual data of plasma matrix product attribute parameters, the prediction model is adjusted according to the actual data of plasma matrix product attribute parameters and the blood test data to be tested to obtain an optimized plasma matrix product attribute parameter prediction model.

[0068] The comparative analysis results and fitting report can be used to indicate whether the existing learning experience of the plasma matrix product attribute parameter prediction model is complete. If the comparative analysis results are consistent and the fitting effect is good, it means that the model has sufficient learning experience and can accurately predict the relevant attribute parameters of the plasma matrix product during plasma matrix preparation.

[0069] After obtaining the blood test data obtained by analyzing and testing whole blood with a blood analyzer, relevant centrifugation parameters and plasma matrix product attribute parameter prediction data can be generated. By statistically analyzing and comparing the actual data of the plasma matrix product attribute parameters with the predicted data of the plasma matrix product attribute parameters during clinical use, comparative analysis results and fitting reports can be obtained.

[0070] In some embodiments, Figure 2 The figure shows a comparison of the strength of the expected plasma matrix and the strength of the actually prepared plasma matrix. It can be seen that Figure 2 Use box plots to calculate statistics. The middle line represents the median of the data, the box represents the concentrated range of the data, and the upper and lower lines represent the upper and lower limits of the data. Figure 2 It can be seen that the breaking strength of the plasma matrix actually prepared is slightly higher than the expected breaking strength, but the difference is not large and there is no significant difference.

[0071] In some embodiments, Figure 3The figure shows the correlation analysis between the blood analysis results and the final plasma matrix yield, where the horizontal axis represents the hemoglobin content and the vertical axis represents the length of the liquid plasma matrix. Since the cross-sectional area of ​​the blood collection tube is constant, the length of the liquid plasma matrix represented by the vertical axis can also indirectly reflect the volume change of the liquid plasma matrix.

[0072] One embodiment of the present application provides a parameter determination method based on plasma matrix preparation, which preliminarily performs correlation analysis on the blood test results of different patients and the effect of their plasma matrix preparation, performs learning simulation on the relationship between the two, and obtains a plasma matrix product attribute parameter prediction model, thereby enabling the model to be applied to the patient's whole blood analysis results during the preparation of the plasma matrix, and obtains dynamic plasma matrix product attribute parameter data that best matches the blood condition of a specific patient, which is convenient for subsequent parameter adjustment and thus ensures the preparation effect of the plasma matrix. That is, after obtaining these plasma matrix product attribute parameter prediction data, it can be used to preliminarily understand the product characteristics of the plasma matrix prepared by the individual patient, so as to adjust the relevant parameters according to clinical needs, and finally achieve the effect required by the clinical situation.

[0073] Figure 4 A block diagram of an electronic device suitable for implementing the above-described attribute parameter determination method according to an embodiment of the present application is schematically shown. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0074] like Figure 4 As shown, the electronic device 1000 described in this embodiment includes: a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage part 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (for example, an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include an onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the attribute parameter determination method flow according to an embodiment of the present application.

[0075] In RAM 1003, various programs and data required for the operation of electronic device 1000 are stored. Processor 1001, ROM 1002 and RAM 1003 are connected to each other via bus 1004. Processor 1001 performs various operations of the attribute parameter determination method flow according to the embodiment of the present application by executing the program in ROM 1002 and / or RAM 1003. It should be noted that the program can also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 can also perform various operations of the attribute parameter determination method flow according to the embodiment of the present application by executing the program stored in the one or more memories.

[0076] According to an embodiment of the present application, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to the bus 1004. The electronic device 1000 may further include one or more of the following components connected to the I / O interface 1005: an input portion 1006 including a keyboard, a mouse, etc.; an output portion 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 1008 including a hard disk, etc.; and a communication portion 1009 including a network interface card such as a LAN card, a modem, etc. The communication portion 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage portion 1008 as needed.

[0077] According to the attribute parameter determination method flow of the embodiment of the present application, it can be implemented as a computer software program. For example, the embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program contains a program code for executing the attribute parameter determination method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 1009, and / or installed from the removable medium 1011. When the computer program is executed by the processor 1001, the above-mentioned functions defined in the system of the embodiment of the present application are executed. According to the embodiment of the present application, the system, equipment, device, module and / or unit described above can be implemented by a computer program module.

[0078] The embodiments of the present application also provide a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the steps of the attribute parameter determination method according to the embodiments of the present application can be implemented.

[0079] According to an embodiment of the present application, the computer-readable storage medium may be a non-volatile computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In an embodiment of the present application, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an apparatus, or a device. For example, according to an embodiment of the present application, the computer-readable storage medium may include one or more memories other than the ROM 1002 and / or RAM 1003 described above.

[0080] It should be noted that the functional modules in the various embodiments of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product.

[0081] The flowchart and / or block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flowchart and / or block diagram can represent a part of a module, program segment or code, and a part of the above-mentioned module, program segment or code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0082] Those skilled in the art will appreciate that the features described in the various embodiments and / or claims of the present application may be combined and / or combined in a variety of ways, even if such combinations and / or combinations are not explicitly described in the present application. In particular, without departing from the spirit and teachings of the present application, the technical features described in the various embodiments and / or claims of the present application may be combined and / or combined in a variety of ways, and all of these combinations and / or combinations fall within the scope of the present application.

[0083] Although the present application has been shown and described with reference to specific exemplary embodiments of the present application, it should be understood by those skilled in the art that various changes in form and details may be made to the present application without departing from the spirit and scope of the present application as defined by the appended claims and their equivalents. Therefore, the scope of the present application should not be limited to the above-mentioned embodiments, but should be determined not only by the appended claims, but also by the equivalents of the appended claims.

Claims

1. A method for determining plasma matrix product attribute parameters based on blood analysis data, characterized in that: include: Acquire multiple sets of blood analysis sample data and plasma matrix preparation sample data; the plasma matrix preparation sample data is sample data of plasma matrix successfully prepared by using the blood analysis sample data; Performing model training based on the mapping relationship between the blood analysis sample data and the plasma matrix preparation sample data to obtain a plasma matrix product attribute parameter prediction model; The blood test data to be tested are processed based on the plasma matrix product attribute parameter prediction model to obtain corresponding plasma matrix product attribute parameter prediction data.

2. The method for determining the property parameters of a plasma matrix product according to claim 1, wherein: The model training is performed based on the mapping relationship between the blood analysis sample data and the plasma matrix preparation sample data to obtain the plasma matrix product attribute parameter prediction model, which includes: The blood analysis sample data is used as input and the plasma matrix preparation sample data is used as output to perform model training to obtain the plasma matrix product attribute parameter prediction model.

3. The method for determining the attribute parameters of a plasma matrix product according to claim 1, wherein: The method of processing the blood test data to be tested based on the plasma matrix product attribute parameter prediction model to obtain corresponding plasma matrix product attribute parameter prediction data includes: Acquiring the blood test data to be tested; The blood test data to be tested is input into the plasma matrix product attribute parameter prediction model to obtain corresponding plasma matrix product attribute parameter prediction data.

4. The method for determining the attribute parameters of a plasma matrix product according to claim 3, characterized in that: After inputting the blood test data to be tested into the plasma matrix product attribute parameter prediction model to obtain the corresponding plasma matrix product attribute parameter prediction data, the method further includes: Perform actual preparation of plasma matrix based on the blood test data to be tested, and obtain actual data of plasma matrix product attribute parameters; If the predicted data of the plasma matrix product attribute parameters do not match the actual data of the plasma matrix product attribute parameters, the plasma matrix product attribute parameter prediction model is adjusted and optimized based on the actual data of the plasma matrix product attribute parameters to obtain an optimized plasma matrix product attribute parameter prediction model.

5. The method for determining the attribute parameters of a plasma matrix product according to claim 4, characterized in that: If the predicted data of the plasma matrix product attribute parameters do not match the actual data of the plasma matrix product attribute parameters, the plasma matrix product attribute parameter prediction model is adjusted and optimized based on the actual data of the plasma matrix product attribute parameters to obtain the optimized plasma matrix product attribute parameter prediction model, including: Comparing the predicted data of the plasma matrix product attribute parameters with the actual data of the plasma matrix product attribute parameters to obtain comparative analysis results and a fit report; When the comparative analysis result and the fitting report indicate that the predicted data of the plasma matrix product attribute parameters do not match the actual data of the plasma matrix product attribute parameters, the plasma matrix product attribute parameter prediction model is adjusted and optimized according to the actual data of the plasma matrix product attribute parameters and the blood test data to be tested to obtain the optimized plasma matrix product attribute parameter prediction model.

6. The method for determining the attribute parameters of a plasma matrix product according to any one of claims 1 to 5, characterized in that: The blood test data to be tested is obtained by performing a blood test on the patient's whole blood using a blood analysis instrument; The blood analysis sample data is obtained by analyzing the patient's sample blood through a blood analysis instrument; The plasma matrix preparation sample data is obtained after the plasma matrix is ​​prepared successfully on the patient's sample blood by a plasma matrix centrifuge.

7. The method for determining the attribute parameters of a plasma matrix product according to any one of claims 1 to 5, characterized in that: The blood analysis sample data includes one or more of white blood cells, red blood cells, platelets, hematocrit, coefficient of variation of red blood cell distribution width, mean red blood cell volume, hemoglobin content, neutrophils, lymphocytes, monocytes, eosinophils, basophils, large platelet ratio, mean platelet volume, hematocrit, mean platelet distribution width, activated partial prothromboplastin time, plasma prothrombin time, thrombin time, prothrombin time ratio, fibrinogen, prothrombin INR, prothrombin activity and glucose.

8. The method for determining the attribute parameters of a plasma matrix product according to any one of claims 1 to 5, characterized in that: The plasma matrix preparation sample data and the plasma matrix product attribute parameters respectively include plasma matrix preparation sample physical data and plasma matrix preparation sample biological data; The physical data of the plasma matrix preparation sample includes at least one of the following: plasma matrix product volume, solid plasma matrix coagulation time, liquid plasma matrix coagulation time, solid plasma matrix mass, plasma matrix membrane mass, plasma matrix membrane maximum stress, and plasma matrix membrane maximum strain; The biological data of the plasma matrix preparation sample includes at least one of the content and distribution of growth factors in the plasma matrix, the content and distribution of cells in the plasma matrix, the effect of the plasma matrix on promoting soft tissue regeneration, and the effect of the plasma matrix on promoting bone regeneration.

9. An electronic device, characterized in that: It comprises at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program, and when the computer program is executed by the processing unit, the processing unit is enabled to perform the steps of the attribute parameter determination method according to any one of claims 1 to 8.

10. A storage medium, characterized in that: It stores a computer program executable by an access authentication device. When the computer program runs on the access authentication device, the access authentication device can execute the steps of the attribute parameter determination method according to any one of claims 1 to 8.

Images