Method, device and equipment for predicting amplitude of platelet batroxobin activator A cup

By using a quantitative relationship model based on thromboelastography parameters, the maximum amplitude of platelet batroxobin activator A cup is predicted, solving the problems of complexity and high cost of traditional detection methods and achieving efficient and accurate detection of platelet inhibition rate.

CN120927943APending Publication Date: 2025-11-11BEIJING LEPU MEDICAL TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202511455106.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-10-13
Publication Date
2025-11-11

AI Technical Summary

Technical Problem

Traditional platelet inhibition rate testing requires induction with A-cup reagent to measure the maximum amplitude value, which results in complex operation, high cost, and limited accuracy.

Method used

By acquiring parameters such as fibrin formation time and fibrin polymerization rate of the target sample, and processing them using a pre-selected objective function, a quantitative relationship model between K value, Angle value and maximum amplitude of A cup is established, enabling high-precision prediction of the maximum amplitude of platelet batroxobin activator A cup, thus avoiding direct measurement of A cup reagent.

Benefits of technology

It has enabled automated detection of platelet inhibition rate, significantly reducing reagent costs, improving detection efficiency, and enhancing the accuracy of detection results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120927943A_ABST
    Figure CN120927943A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of medical detection, and discloses a platelet batroxobin activator A cup amplitude prediction method, device and equipment, the method comprises the following steps: obtaining a first detection parameter value of a common cup of a target detection sample, the first detection parameter value comprising fibrin formation time and / or fibrin polymerization rate; and based on the first detection parameter value of the target detection sample, predicting to obtain the maximum amplitude of the platelet batroxobin activator A cup of the target detection sample. The reagent cost for platelet inhibition rate detection can be remarkably reduced, and the detection efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of medical testing technology, specifically to a method, apparatus, and equipment for predicting the amplitude of platelet batroxobin activator A-cup. Background Technology

[0002] Platelet inhibition rate indicates the degree to which a drug inhibits platelet function. Traditional platelet inhibition rate testing requires induction with an A-cup reagent (i.e., batroxobin activator) followed by measurement of the maximum amplitude (MA), which has the following drawbacks: The procedure is complex: it requires an additional step to prepare the A-cup sample, which increases the detection time (approximately 20 minutes). High cost: The unit price of reagent A is three times that of ordinary reagent A, and the annual consumption cost increases by more than 50%; Limited accuracy of results: Current methods for measuring MA values ​​after induction with A-cup reagent are subject to interference from clinical blood samples, resulting in abnormal results such as platelet activation leading to higher test results than the true results, and insufficient activation resulting in lower values. Summary of the Invention

[0003] In view of this, the present invention provides a method, apparatus and equipment for predicting the amplitude of platelet batroxobin activator A-cup, in order to solve the problems of complex operation, low efficiency and high cost caused by the need to measure the maximum amplitude value after induction with A-cup reagent in platelet inhibition rate detection.

[0004] In a first aspect, the present invention provides a method for predicting the amplitude of platelet batroxobin activator A-cup oscillations, the method comprising: Obtain the first detection parameter value of the ordinary cup of the target detection sample, the first detection parameter value including fibrin formation time and / or fibrin polymerization rate; Based on the first detection parameter value of the target detection sample, the maximum amplitude of platelet batroxobin activator A cup of the target detection sample is predicted.

[0005] In one optional implementation, predicting the maximum amplitude of platelet batroxobin activator A cup in the target detection sample based on the first detection parameter value of the target detection sample includes: According to the pre-selected objective function, the first detection parameter value of the target detection sample is processed to obtain the maximum amplitude of the platelet batroxobin activator A cup.

[0006] In one alternative implementation, the objective function is a logarithmic function, a quadratic function, or a linear function.

[0007] In an optional implementation, before processing the first detection parameter value according to a pre-selected objective function to obtain the maximum amplitude of the platelet batroxobin activator A cup, the method further includes: Obtain the first detection parameter value of ordinary cups and the measured value of the maximum amplitude of platelet batroxobin activator A cup from multiple training samples; The selection process includes at least one of the following: selecting a second detection parameter from the first detection parameters to participate in predicting the maximum amplitude of the A-cup; selecting an objective function to process the value of the second detection parameter; selecting a parameter value of the objective function; and selecting a fusion function to fuse the processed values ​​of different second detection parameters to obtain a predicted value of the maximum amplitude of the A-cup. Based on the selection results obtained from the selection process, the predicted values ​​of the maximum amplitude of the A cup corresponding to each training sample are obtained. Based on the predicted value of the maximum amplitude of the A-cup in the multiple training samples and the corresponding measured value, it is determined whether the first preset requirement is met; the first preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup in the multiple training samples and the corresponding measured value meets the target preset requirement. If the first preset requirement is not met, the selection process is repeated until the predicted value of the maximum amplitude of the A cup of the plurality of training samples and the corresponding measured value meet the first preset requirement.

[0008] In an optional implementation, the first preset requirement further includes: the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the adenosine diphosphate inducer of the training sample; or, the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the arachidonic acid inducer of the training sample.

[0009] In an optional implementation, the method for predicting the amplitude of platelet batroxobin activator A-cup further includes: Obtain the first detection parameter value and the measured value of the maximum amplitude of platelet batroxobin activator A cup from one or more validation samples; the validation samples are different from the training samples; Based on the latest selection results, the predicted values ​​of the maximum amplitude of the A cup corresponding to each of the verification samples are obtained; Based on the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value, it is determined whether the second preset requirement is met; the second preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value meets the target preset requirement; If the second preset requirement is not met, the selection process is repeated until the predicted value of the maximum amplitude of the A cup of the verification sample and the corresponding measured value meet the second preset requirement.

[0010] In an optional implementation, after predicting the maximum amplitude of platelet batroxobin activator A cup in the target detection sample based on the first detection parameter value, the method further includes: The platelet inhibition rate is calculated based on the predicted maximum amplitude of platelet batroxobin activator A cup in the target detection sample.

[0011] In an optional implementation, after calculating the platelet inhibition rate based on the predicted value of the maximum amplitude of platelet batroxobin activator A cup in the target detection sample, the method further includes: If the platelet inhibition rate is less than 0%, then the platelet inhibition rate is set to 0%. If the platelet inhibition rate is greater than 100%, then the platelet inhibition rate is set to 100%.

[0012] Secondly, the present invention provides a device for predicting the amplitude of platelet batroxobin activator A-cup, the device comprising: The detection data acquisition module is used to acquire the first detection parameter value of the ordinary cup of the target detection sample, the first detection parameter value including fibrin formation time and / or fibrin polymerization rate; An amplitude prediction module is used to predict the maximum amplitude of platelet batroxobin activator A cup of the target detection sample based on the first detection parameter value of the target detection sample.

[0013] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for predicting the amplitude of platelet batroxobin activator A cup as described in the first aspect or any corresponding embodiment thereof.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the method for predicting the amplitude of platelet batroxobin activator A cups as described in the first aspect or any corresponding embodiment thereof.

[0015] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the method for predicting the amplitude of platelet batroxobin activator A cups as described in the first aspect or any corresponding embodiment thereof.

[0016] This invention provides a method, apparatus, and device for predicting the amplitude of platelet batroxobin activator A-cup. It is a high-precision method for predicting the maximum amplitude of platelet batroxobin activator A-cup based on thromboelastography parameters (K value, Angle value). It realizes automated detection of platelet inhibition rate without measuring the maximum amplitude value after A-cup reagent induction, solving the problems of high cost, complex operation, low efficiency, and limited result accuracy caused by traditional platelet inhibition rate detection. It significantly reduces the reagent cost of platelet inhibition rate detection and improves detection efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of the present invention, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the method for predicting the amplitude of platelet batroxobin activator A cup according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the Bland-Altman consistency analysis diagram according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a device for predicting the amplitude of platelet batroxobin activator A cup according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] According to an embodiment of the present invention, a method for predicting the amplitude of platelet batroxobin activator A cup is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of executable computer instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0021] This embodiment provides a method for predicting the amplitude of platelet batroxobin activator A-cup, which can be used with various computer devices, including thromboelastography devices and other computer devices. Figure 1 This is a flowchart of a method for predicting the amplitude of platelet batroxobin activator A-cup according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: Obtain the first detection parameter value of the ordinary cup of the target detection sample. The first detection parameter value includes fibrin formation time and / or fibrin polymerization rate.

[0022] Step S102: Based on the first detection parameter value of the target detection sample, predict the maximum amplitude of platelet batroxobin activator A cup of the target detection sample.

[0023] Specifically, in this embodiment of the invention, cup A refers to a test cup containing batroxobin activator. Fibrin formation time, also known as the K value, refers to the time required from the start of the measurement to the amplitude of the thromboelastography reaching 20 mm, reflecting the rate of fibrin formation and clot strengthening. A shorter K value indicates a faster clotting rate. It is mainly used to assess the dynamic changes in the blood coagulation process, particularly fibrin cross-linking and clot strengthening. Fibrin polymerization rate, also known as the Angle value (α angle), is calculated on the thromboelastography by drawing a tangent line from the starting point of the thromboelastography to the maximum curve arc; the angle between this tangent line and the horizontal line is the Angle angle. The Angle angle reflects the kinetic characteristics of blood clot formation, particularly the rate of clot development under the combined action of fibrin and platelets. A larger Angle angle indicates a faster clot formation rate, usually indicating normal or high fibrinogen function. In this embodiment of the invention, the maximum amplitude (MA) refers to the maximum amplitude on the thromboelastography, representing the maximum strength of the clot.

[0024] The first detection parameter value of the ordinary cup of the target detection sample, and the first detection parameter value of the ordinary cup of the training sample mentioned below, the measured value of the maximum amplitude of the platelet batroxobin activator A cup, the first detection parameter value of the ordinary cup of the validation sample, the measured value of the maximum amplitude of the platelet batroxobin activator A cup, and the maximum amplitude (MA) of the adenosine diphosphate inducer of various samples (target detection sample, training sample, validation sample). ADP ), the maximum amplitude (MA) of the arachidonic acid inducer AA All of these can be obtained through thromboelastography (TEG). TEG can also obtain the R-value (clotting time) and maximum amplitude (MA) of samples (target detection samples, training samples, and validation samples).

[0025] The method for predicting the amplitude of platelet batroxobin activator A cup provided in this embodiment of the invention can be executed by a thromboelastography device or by a computer device other than a thromboelastography device. If it is executed by a computer device other than a thromboelastography device, then the other computer device needs to have an adapted interface to support real-time reception of detection data from mainstream thromboelastography devices.

[0026] This embodiment provides a method for predicting the amplitude of platelet batroxobin activator A-cup. It is a high-precision method for predicting the maximum amplitude of platelet batroxobin activator A-cup based on thromboelastography parameters (K value, Angle value). It realizes automated detection of platelet inhibition rate without measuring the maximum amplitude value after A-cup reagent induction. It solves the problems of high cost, complicated operation, low efficiency and limited result accuracy caused by traditional platelet inhibition rate detection, significantly reducing the reagent cost of platelet inhibition rate detection and improving detection efficiency.

[0027] In some optional embodiments, step S102, namely, predicting the maximum amplitude of platelet batroxobin activator A cup of the target detection sample based on the first detection parameter value of the target detection sample, includes: According to the pre-selected objective function, the first detection parameter value of the target detection sample is processed to obtain the maximum amplitude of the platelet batroxobin activator A cup.

[0028] The objective function is a logarithmic function, a quadratic function, or a linear function. Of course, the objective function can also be other functions, which will not be listed here. The objective function can be a function selected by the user or a function automatically selected by the system.

[0029] In this embodiment of the invention, K value and Angle value are used as key features. Combined with a function model, a quantitative relationship model between K value (fibrin formation time) and Angle value and A-cup MA value is established to achieve high-precision prediction of A-cup MA value. This allows platelet inhibition rate to be calculated without measuring the maximum amplitude value after induction with A-cup reagent, significantly reducing dependence on A-cup reagent and saving reagent costs by more than 50%.

[0030] In some optional embodiments, before processing the first detection parameter value of the target detection sample according to a pre-selected objective function to obtain the maximum amplitude of the platelet batroxobin activator A cup, the method further includes: Step 1: Obtain the first detection parameter value of the ordinary cup of multiple training samples and the measured value of the maximum amplitude of platelet batroxobin activator A cup.

[0031] Specifically, if any training sample contains abnormal data, that training sample is removed. For example, if thromboelastography (TE) parameter values ​​(R value, K value, Angle value, MA value for a standard cup, and measured MA value for an A cup) are collected from 200 clinical samples, covering the reference ranges for K values ​​(1-3) and Angle values ​​(53-72), outliers need to be removed when using these clinical samples as training samples. These outliers include samples with K values ​​<1 or >3 and Angle values ​​<53 or >72 (K < 1, Angle > 72 indicates "high fibrin formation," K > 3, Angle < 53 indicates "low fibrin formation"). The remaining 185 samples are then included in the analysis. The collected thromboelastography parameter values ​​from the 200 clinical samples can be stored in a cache. The system's cache capacity is greater than or equal to 1000 sets of thromboelastography parameter values.

[0032] Step 2: Perform selection processing, which includes at least one of the following: selecting a second detection parameter from the first detection parameters to participate in predicting the maximum amplitude of the A-cup; selecting the objective function to process the value of the second detection parameter; selecting the parameter value of the objective function; selecting a fusion function, which is used to fuse the processed values ​​of different second detection parameters to obtain the predicted value of the maximum amplitude of the A-cup.

[0033] In this embodiment of the invention, it is possible that not all first detection parameter values ​​participate in the prediction of the maximum amplitude of the A-cup. Here, the first detection parameter values ​​will be filtered, and only the filtered first detection parameters (i.e., the second detection parameters) will participate in the prediction of the maximum amplitude of the A-cup.

[0034] The candidate functions that can be selected as the objective function include: logarithmic functions, quadratic functions, and linear functions. Of course, other functions may also be included, but they are not listed here.

[0035] Regarding the selection of parameter values ​​for the objective function, for example, if the objective function is a linear function: y = a × x + b (x can be the first detection parameter value), then it is necessary to select the specific values ​​of the two parameters a and b.

[0036] The fusion function can be an averaging function or a weighted summation function. Of course, if there is only one first detection parameter after filtering, which is also the second detection parameter, then a fusion function is not needed.

[0037] Step 3: Based on the selection results obtained from the selection process, obtain the predicted values ​​of the maximum amplitude of the A cup corresponding to each training sample.

[0038] Specifically, for the selected first detection parameter (i.e., the second detection parameter), the chosen objective function is used to process it, obtaining the corresponding processed value. If there are multiple second detection parameters (i.e., including fibrin formation time and fibrin polymerization rate simultaneously), then the chosen fusion function is used to fuse the multiple processed values ​​to obtain the predicted value of the maximum amplitude of the A-cup. If there is only one second detection parameter, no fusion is needed, and the obtained processed value is directly used as the predicted value of the maximum amplitude of the A-cup. For each training sample, the corresponding predicted value of the maximum amplitude of the A-cup is obtained using this method.

[0039] For example, if fibrin formation time (K value) and fibrin polymerization rate (Angle value) are both selected to predict the maximum amplitude of A-cup, and the objective function is a linear function, then the K value and Angle value are processed using linear functions respectively, resulting in processed values ​​of a1×K+b1 and a2×Angle+b2. Then, if the selected fusion function is an averaging function, the average of the two processed values ​​is calculated, i.e., (a1×K+b1 + a2×Angle+b2) / 2.

[0040] Step 4: Based on the predicted value of the maximum amplitude of the A-cup of the multiple training samples and the corresponding measured value, determine whether the first preset requirement is met; the first preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup of the multiple training samples and the corresponding measured value meets the target preset requirement, which may specifically include at least one of the following: the absolute error is less than a set threshold, the mean absolute error is less than a set threshold, the relative error is less than a set threshold, the root mean square error is less than a set threshold, and the percentage range of the error distribution is within an acceptable range, etc.

[0041] Step 5: If it is determined that the first preset requirement is not met, the selection process is re-executed until the predicted value of the maximum amplitude of the A cup of the multiple training samples and the corresponding measured value meet the first preset requirement.

[0042] In some optional embodiments, the first preset requirement further includes: for the same training sample, the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the adenosine diphosphate inducer of the training sample; or, the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the arachidonic acid inducer of the training sample.

[0043] In other optional implementations, step 3, namely, obtaining the predicted value of the maximum amplitude of the A-cup corresponding to each training sample based on the selection result obtained from the selection process, includes: Step 31: Based on the selection result obtained from the selection process, obtain the input features corresponding to the training sample.

[0044] Specifically, for the selected first detection parameter (i.e., the second detection parameter), the chosen objective function is used to process it to obtain the corresponding processed value. If there are multiple second detection parameters (i.e., including fibrin formation time and fibrin polymerization rate simultaneously), then the chosen fusion function is used to fuse the multiple processed values ​​to obtain the input feature; if there is only one second detection parameter, then no fusion is needed, and the obtained processed value is directly used as the input feature. For each training sample, the corresponding input feature is obtained using this method.

[0045] Step 32: Input the input features into the Gradient Boosting Decision Tree (GBDT) model and output the predicted value of the maximum amplitude of the A cup of the training sample.

[0046] Gradient boosting decision tree is an ensemble learning algorithm based on decision trees. It iteratively trains multiple weak learners (usually shallow decision trees) and combines gradient descent to optimize the loss function, ultimately forming a strong prediction model.

[0047] Accordingly, the step of processing the first detection parameter value of the target detection sample according to a pre-selected objective function to obtain the maximum amplitude of the platelet batroxobin activator A cup specifically includes: Based on the selection result obtained from the selection process, the input features corresponding to the target detection sample are obtained; The input features corresponding to the target detection sample are input into the gradient boosting decision tree model, and the maximum amplitude of the A-cup of the target detection sample is output.

[0048] In this embodiment of the invention, a quantitative relationship is established between the K value and Angle value of the ordinary cup and the maximum amplitude (MA) of the batroxobin activator A cup through a machine learning model, thereby realizing the automated detection of platelet inhibition rate without the need for A cup reagent.

[0049] In some alternative embodiments, predicting the maximum amplitude of platelet batroxobin activator A cup in the target detection sample based on the first detection parameter value of the target detection sample includes: One or more processing functions are used to process the first detection parameter value to obtain one or more predicted features; The predicted features are input into the gradient boosting decision tree model, which outputs the maximum amplitude of the A-cup of the target detection sample.

[0050] Specifically, the processing function may include one or more of logarithmic functions, quadratic functions, and linear functions. The processing function may also include a function that fuses the eigenvalues ​​obtained from the aforementioned functions (one or more of logarithmic functions, quadratic functions, and linear functions) to obtain fused eigenvalues.

[0051] For example, the processing function may include logarithmic, quadratic, and linear functions, as well as an averaging function to obtain the fused feature values. The first detection parameter values ​​include the standard cup size K and the Angle value. Therefore, the final predicted features include: log(K), log(Angle), and Angle. 2 K 2 a×K+b, a×Angle+b, (K 2 +Angle 2 ) / 2 average, (log(K)+log(Angle) ) / 2, (a×K+b+a×Angle+b) / 2.

[0052] The gradient boosting decision tree model described above needs to be trained and validated beforehand. The model validation results need to meet the following error metric requirements: mean absolute error (MAE) ≤ 1.5% (or 1.2%), coefficient of determination (R²) ≤ 1.2%. 2 The value should be ≥0.95 (or 0.96) to ensure high-precision prediction of the maximum amplitude of the A-cup of the target detection sample. Specifically, K-fold cross-validation (K can be, for example, 10) can be used.

[0053] The gradient boosting decision tree model described above can be embedded in a computer's field-programmable gate array (FPGA) chip to achieve millisecond-level response. For example, given a set of elasticity map detection data (K=2.1, Angle=65), it can output MA within 10ms. A杯预测值 =35.2±1.5. Then, the inhibition rate of 82.4% can be automatically generated according to the formula, and the confidence interval (80.1%-84.7%) can be marked.

[0054] In the above embodiments, the prediction of the maximum amplitude of platelet batroxobin activator A cup in the target detection sample (or training sample) also includes a 95% confidence interval, such as 22.5 ± 1.8.

[0055] In some optional embodiments, the method for predicting the maximum amplitude of platelet batroxobin activator A cup also includes: Step 1: Obtain the first detection parameter value of the ordinary cup of one or more verification samples, and the measured value of the maximum amplitude of platelet batroxobin activator A cup; the verification samples are different from the training samples.

[0056] Step 2: Based on the latest selection results, obtain the predicted value of the maximum amplitude of the A cup corresponding to each verification sample.

[0057] Similarly, the process of obtaining the predicted value of the maximum amplitude of the A-cup corresponding to a verification sample specifically includes: processing the selected first detection parameter (i.e., the second detection parameter) using a selected objective function to obtain the corresponding processed value. If there are multiple second detection parameters (i.e., simultaneously including fibrin formation time and fibrin polymerization rate), then the selected fusion function is used to fuse the multiple processed values ​​to obtain the predicted value of the maximum amplitude of the A-cup; if there is only one second detection parameter, then no fusion is required, and the obtained processed value is directly used as the predicted value of the maximum amplitude of the A-cup.

[0058] Step 3: Based on the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value, determine whether the second preset requirement is met; the second preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value meets the target preset requirement.

[0059] The second preset requirement can be the same as the first preset requirement, that is, the preset requirement for the training sample and the preset requirement for the validation sample are the same. The second preset requirement may also include: the predicted value of the maximum amplitude of the A-cup of the validation sample is less than or equal to the maximum amplitude of the adenosine diphosphate inducer of the validation sample; or, the predicted value of the maximum amplitude of the A-cup of the validation sample is less than or equal to the maximum amplitude of the arachidonic acid inducer of the validation sample. In other embodiments, the second preset requirement may be different from the first preset requirement. For example, both the second and first preset requirements may include a requirement for the difference between the predicted value of the maximum amplitude of the A-cup and the corresponding measured value, but the specific difference requirement may differ.

[0060] Step 4: If it is determined that the second preset requirement is not met, the selection process is re-executed until the predicted value of the maximum amplitude of the A cup of the verification sample and the corresponding measured value meet the second preset requirement.

[0061] In some specific implementations, the selection process may be re-executed only when all verification samples are determined to fail to meet the second preset requirement, that is, when the predicted value and the corresponding measured value of the maximum amplitude of the A cup of each verification sample are both determined to fail to meet the second preset requirement, for example, when the predicted value and the measured value of the maximum amplitude of the A cup of 3 verification samples deviate by more than 5%. When the predicted value of the maximum amplitude of the A cup of the verification sample and the corresponding measured value are used to determine that the second preset requirement is not met, and it is determined to re-execute the selection process, the first detection parameter value and the measured value of the maximum amplitude of the platelet batroxobin activator A cup of some new samples can be obtained. These values, together with the first detection parameter value and the measured value of the maximum amplitude of the platelet batroxobin activator A cup of the verification sample, can be used as the judgment condition for the selection process. Alternatively, the first detection parameter value and the measured value of the maximum amplitude of the platelet batroxobin activator A cup of some or all of the original training samples can be used together with the detection data of the verification sample as the judgment condition for the selection process.

[0062] The process of calibrating the model using validation samples can be performed periodically or after multiple test samples are found to have abnormal inhibition rates. After calibration, for test samples with abnormal inhibition rates, their A-cup maximum amplitude can be re-predicted and the inhibition rate recalculated.

[0063] Thromboelastography data from clinical samples can be shared among multiple hospitals, for example, through a cloud platform. This allows for the acquisition of more clinical samples as training and / or validation samples, enabling iterative optimization of the prediction algorithm and improving the accuracy of predicting the maximum amplitude of platelet batroxobin activator A-cup. In the event of a network outage, data is stored locally for at least 24 hours and automatically synchronized upon network recovery. To ensure data security, multi-level user access control can be implemented, including operator, administrator, and engineer permissions.

[0064] For training samples, validation samples, and other samples where the maximum amplitude of the A-cup was measured, a line graph comparing the predicted and measured values ​​can be updated and displayed in real time. To facilitate error analysis, a Bland-Altman consistency analysis graph can also be generated (e.g., ...). Figure 2 (as shown in the figure) and error distribution heatmap.

[0065] Additionally, if the K value or Angle value of the ordinary cup of the sample (target detection sample or verification sample) is outside the range (K value range is 1-3, Angle value range is 53-72), for example, K=0.8, an abnormal prompt will be output, such as "Sample abnormal, retesting is recommended".

[0066] In some optional embodiments, step S102, that is, after predicting the maximum amplitude of platelet batroxobin activator A cup of the target detection sample based on the first detection parameter value, further includes: The platelet inhibition rate is calculated based on the predicted maximum amplitude of platelet batroxobin activator A cup in the target detection sample.

[0067] Specifically, the formula for calculating the platelet inhibition rate is: ,or,

[0068] in, This represents the maximum amplitude of the adenosine diphosphate inducer. This represents the maximum amplitude of the arachidonic acid inducer. This is the predicted value for the maximum amplitude of platelet batroxobin activator A-cup. This represents the maximum amplitude of a standard cup. The calculated suppression rate can be rounded to two decimal places.

[0069] In some optional embodiments, after calculating the platelet inhibition rate based on the predicted value of the maximum amplitude of platelet batroxobin activator A cup in the target detection sample, the method further includes: If the platelet inhibition rate is less than 0%, then the platelet inhibition rate is set to 0%. If the platelet inhibition rate is greater than 100%, then the platelet inhibition rate is set to 100%.

[0070] The method provided in this invention requires no manual intervention throughout the entire process, from data acquisition to inhibition rate calculation. Finally, this invention can also output a PDF format test report, including model version, calibration records, and quality control indicators.

[0071] This embodiment also provides a device for predicting the amplitude of platelet batroxobin activator A-cup, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0072] This embodiment provides a device for predicting the amplitude of platelet batroxobin activator A-cup, such as... Figure 3 As shown, it includes: The detection data acquisition module 301 is used to acquire the first detection parameter value of the ordinary cup of the target detection sample, the first detection parameter value including fibrin formation time and / or fibrin polymerization rate. The amplitude prediction module 302 is used to predict the maximum amplitude of platelet batroxobin activator A cup of the target detection sample based on the first detection parameter value of the target detection sample.

[0073] In some optional implementations, the amplitude prediction module 302 is specifically used to process the first detection parameter value of the target detection sample according to a pre-selected objective function to obtain the maximum amplitude of the platelet batroxobin activator A cup.

[0074] In some alternative implementations, the objective function is a logarithmic function, a quadratic function, or a linear function.

[0075] In some optional embodiments, the platelet batroxobin activator A-cup amplitude prediction device further includes: The training sample detection data acquisition module is used to acquire the first detection parameter value of the ordinary cup of multiple training samples and the measured value of the maximum amplitude of the platelet batroxobin activator A cup. A selection processing module is configured to perform selection processing, which includes at least one of the following: selecting a second detection parameter from the first detection parameters to participate in predicting the maximum amplitude of the A-cup; selecting an objective function to process the value of the second detection parameter; selecting a parameter value of the objective function; and selecting a fusion function to fuse the processed values ​​of different second detection parameters to obtain a predicted value of the maximum amplitude of the A-cup. The first prediction module is used to obtain the predicted value of the maximum amplitude of the A cup corresponding to each training sample based on the selection result obtained by the selection process. The first judgment module is used to determine whether a first preset requirement is met based on the predicted value of the maximum amplitude of the A-cup of the multiple training samples and the corresponding measured value; the first preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup of the multiple training samples and the corresponding measured value meets the target preset requirement. The first control module is configured to control the selection processing module, the first prediction module, and the first judgment module to run repeatedly if the determination is not satisfied with the first preset requirement, until the predicted value of the maximum amplitude of the A cup of the plurality of training samples and the corresponding measured value satisfy the first preset requirement.

[0076] In some optional implementations, the first preset requirement further includes: the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the adenosine diphosphate inducer of the training sample; or, the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the arachidonic acid inducer of the training sample.

[0077] In some alternative embodiments, the device for predicting the amplitude of platelet batroxobin activator A cups further includes: The verification sample detection data acquisition module is used to acquire the first detection parameter value of the ordinary cup of one or more verification samples and the measured value of the maximum amplitude of the platelet batroxobin activator A cup; the verification sample is different from the training sample; The second prediction module is used to obtain the predicted value of the maximum amplitude of the A cup corresponding to each of the verification samples based on the latest selection result. The second judgment module is used to determine whether a second preset requirement is met based on the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value; the second preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value meets the target preset requirement; The second control module is used to control the selection processing module, the second prediction module and the second judgment module to run repeatedly if the determination does not meet the second preset requirement, until the predicted value of the maximum amplitude of the A cup of the verification sample and the corresponding measured value meet the second preset requirement.

[0078] In some optional embodiments, the platelet batroxobin activator A-cup amplitude prediction device further includes: The inhibition rate calculation module is used to calculate the platelet inhibition rate based on the predicted value of the maximum amplitude of platelet batroxobin activator A cup in the target detection sample.

[0079] In some optional embodiments, the platelet batroxobin activator A-cup amplitude prediction device further includes: An abnormal calibration module is used to set the platelet inhibition rate to 0% if the platelet inhibition rate is less than 0%, and to set the platelet inhibition rate to 100% if the platelet inhibition rate is greater than 100%.

[0080] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0081] In this embodiment, the platelet batroxobin activator A-cup amplitude prediction device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0082] This invention also provides a computer device having the above-described features. Figure 3 The device shown is for predicting the amplitude of platelet batroxobin activator A-cup.

[0083] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0084] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0085] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0086] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0087] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0088] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0089] If the computer device is a thromboelastography device, then it also includes some other structures necessary for thromboelastography devices, which will not be elaborated here.

[0090] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0091] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0092] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for predicting the amplitude of platelet batroxobin activator A-cup, characterized in that, The method includes: Obtain the first detection parameter value of the ordinary cup of the target detection sample, the first detection parameter value including fibrin formation time and / or fibrin polymerization rate; Based on the first detection parameter value of the target detection sample, the maximum amplitude of platelet batroxobin activator A cup of the target detection sample is predicted.

2. The method according to claim 1, characterized in that, The prediction of the maximum amplitude of platelet batroxobin activator A cup in the target detection sample based on the first detection parameter value includes: According to the pre-selected objective function, the first detection parameter value of the target detection sample is processed to obtain the maximum amplitude of the platelet batroxobin activator A cup.

3. The method according to claim 2, characterized in that, The objective function is a logarithmic function, a quadratic function, or a linear function.

4. The method according to claim 2 or 3, characterized in that, Before processing the first detection parameter value of the target detection sample according to a pre-selected objective function to obtain the maximum amplitude of the platelet batroxobin activator A cup, the method further includes: Obtain the first detection parameter value of ordinary cups and the measured value of the maximum amplitude of platelet batroxobin activator A cup from multiple training samples; The selection process includes at least one of the following: selecting a second detection parameter from the first detection parameters to participate in predicting the maximum amplitude of the A-cup; selecting an objective function to process the value of the second detection parameter; selecting a parameter value of the objective function; and selecting a fusion function to fuse the processed values ​​of different second detection parameters to obtain a predicted value of the maximum amplitude of the A-cup. Based on the selection results obtained from the selection process, the predicted values ​​of the maximum amplitude of the A cup corresponding to each training sample are obtained. Based on the predicted value of the maximum amplitude of the A-cup in the multiple training samples and the corresponding measured value, it is determined whether the first preset requirement is met; the first preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup in the multiple training samples and the corresponding measured value meets the target preset requirement. If the first preset requirement is not met, the selection process is repeated until the predicted value of the maximum amplitude of the A cup of the plurality of training samples and the corresponding measured value meet the first preset requirement.

5. The method according to claim 4, characterized in that, The first preset requirement further includes: the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the adenosine diphosphate inducer of the training sample; or, the predicted value of the maximum amplitude of the A-cup of the training sample is less than or equal to the maximum amplitude of the arachidonic acid inducer of the training sample.

6. The method according to claim 4, characterized in that, Also includes: Obtain the first detection parameter value of the ordinary cup of one or more verification samples, and the measured value of the maximum amplitude of platelet batroxobin activator A cup; The verification sample is different from the training sample; Based on the latest selection results, the predicted values ​​of the maximum amplitude of the A cup corresponding to each of the verification samples are obtained; Based on the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value, it is determined whether the second preset requirement is met; the second preset requirement includes that the difference between the predicted value of the maximum amplitude of the A-cup of the verification sample and the corresponding measured value meets the target preset requirement; If the second preset requirement is not met, the selection process is repeated until the predicted value of the maximum amplitude of the A cup of the verification sample and the corresponding measured value meet the second preset requirement.

7. The method according to claim 1, characterized in that, After predicting the maximum amplitude of platelet batroxobin activator A cup in the target detection sample based on the first detection parameter value, the method further includes: The platelet inhibition rate is calculated based on the predicted maximum amplitude of platelet batroxobin activator A cup in the target detection sample.

8. The method according to claim 7, characterized in that, After calculating the platelet inhibition rate based on the predicted value of the maximum amplitude of platelet batroxobin activator A cup in the target detection sample, the method further includes: If the platelet inhibition rate is less than 0%, then the platelet inhibition rate is set to 0%. If the platelet inhibition rate is greater than 100%, then the platelet inhibition rate is set to 100%.

9. A device for predicting the amplitude of platelet batroxobin activator A-cup, characterized in that, The device includes: The detection data acquisition module is used to acquire the first detection parameter value of the ordinary cup of the target detection sample, the first detection parameter value including fibrin formation time and / or fibrin polymerization rate; An amplitude prediction module is used to predict the maximum amplitude of platelet batroxobin activator A cup of the target detection sample based on the first detection parameter value of the target detection sample.

10. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the method for predicting the amplitude of platelet batroxobin activator A cup as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Platelet detection method

    CN104914254A

  • Platelet inhibition rate calculation method based on thromboelastography

    CN110619938A

  • 2-level thromboelastography quality control product, preparation method and application thereof

    CN112697557A

  • Batroxobin cup detection reagent with platelet aggregation function and preparation method of batroxobin cup detection reagent

    CN112924701A

  • Method for determination of functional fibrinogen

    RU2669796C1