Use of reagent for detecting branched-chain amino acid content in preparation of product for screening cerebral venous thrombosis

Abstract

The application discloses application of a reagent for detecting branched-chain amino acid content in preparation of a product for screening cerebral venous thrombosis, and relates to the technical field of biomedicine.The application takes branched-chain amino acids in peripheral blood as markers, judges whether a patient is suffering from cerebral venous thrombosis based on the change of branched-chain amino acid content, and has an accuracy of 0.838 or more, has a good prediction and diagnosis effect, and provides an effective way for diagnosis, treatment and research and development of cerebral venous thrombosis.

Description

Technical Field

[0001] This invention relates to the field of biomedical technology, and more specifically, to the application of reagents for detecting branched-chain amino acid content in the preparation of products for screening cerebral venous thrombosis. Background Technology

[0002] Cerebral venous thrombosis (CVT) is a type of thrombosis that occurs in the cerebral venous system, including the dural sinuses, cortical veins, and deep veins, due to various causes. It accounts for 0.5% to 1.0% of all cerebrovascular diseases. It is more common in young adults, with a predominance in women (male to female ratio of 1:3.5). Postpartum women account for approximately 5% to 20% of all CVT cases. Furthermore, with advancements in imaging equipment and technology, and the use of oral contraceptives / hormone replacement therapy, the incidence of CVT has increased significantly in recent years, placing a heavy economic burden on individual patients, their families, and society.

[0003] Although CVT is clinically assessed through imaging techniques such as cranial CT / CT venography (CTV), cranial MRI / magnetic resonance venography (MRV), and cerebral angiography (DSA), as well as auxiliary examinations including D-dimer, lumbar puncture cerebrospinal fluid analysis, factor V Leiden mutation, thrombin mutation, protein C, protein S or antithrombin III deficiency, myelodysplastic disorders, chronic inflammatory diseases, hematological diseases, nephrotic syndrome, and various autoimmune diseases or tumors, the lack of specific clinical symptoms makes it highly susceptible to missed or misdiagnosis. The missed diagnosis rate can reach 73%, and 40% of patients experience an average diagnosis time exceeding 10 days. Therefore, there is an urgent need to find a precise and rapid diagnostic indicator for CVT, enabling more CVT patients to receive a quick diagnosis.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide a reagent for detecting branched-chain amino acid content in the preparation of products for screening cerebral venous thrombosis.

[0006] This invention is implemented as follows:

[0007] In a first aspect, embodiments of the present invention provide the application of reagents for detecting the content of branched-chain amino acids in samples in the preparation of products for screening cerebral venous thrombosis.

[0008] Secondly, embodiments of the present invention provide a training method for a prediction model for screening cerebral venous thrombosis, comprising: obtaining the content of branched-chain amino acids in a training sample and the corresponding annotation results; wherein the branched-chain amino acids are those described in the foregoing embodiments; inputting the content of branched-chain amino acids in the training sample into a pre-constructed prediction model to obtain prediction results; wherein the prediction model is used to determine whether the patient has cerebral venous thrombosis based on the content of branched-chain amino acids in the peripheral blood of the sample; and updating the parameters of the prediction model based on the annotation results and the prediction results.

[0009] Thirdly, embodiments of the present invention provide a predictive device for cerebral venous thrombosis, comprising an acquisition module and a prediction module. The acquisition module is used to acquire the detection results of the content of branched-chain amino acids in a sample to be tested; the branched-chain amino acids are those described in the foregoing embodiments. The prediction module is used to input the detection results of the content of branched-chain amino acids in the sample to be tested into a prediction model trained by the training method described in the foregoing embodiments, to obtain a prediction result for the sample to be tested.

[0010] Fourthly, embodiments of the present invention provide a training device for a prediction model for screening cerebral venous thrombosis, comprising: an acquisition module, a prediction module, and a parameter update module. The acquisition module is used to acquire the branched-chain amino acid content and corresponding annotation results in the training sample; the branched-chain amino acids are those described in the foregoing embodiments. The prediction module is used to input the branched-chain amino acid content of the training sample into a pre-constructed prediction model to obtain a prediction result; the prediction model is used to determine whether the sample has cerebral venous thrombosis based on the branched-chain amino acid content. The parameter update module is used to update the parameters of the prediction model based on the annotation results and the prediction results.

[0011] Fifthly, embodiments of the present invention provide an electronic device, the electronic device including a processor and a memory; the memory is used to store a program, and when the program is executed by the processor, the processor enables the processor to implement the training method for the cerebral venous thrombosis prediction model as described in the foregoing embodiments.

[0012] In a sixth aspect, embodiments of the present invention provide a computer-readable medium storing a computer program, which, when executed by a processor, implements the training method for a cerebral venous thrombosis screening prediction model as described in the foregoing embodiments.

[0013] In a seventh aspect, embodiments of the present invention provide the application of reagents for detecting the content of branched-chain amino acids in samples in the preparation of products for detecting cerebral hemorrhage or cerebral infarction.

[0014] The present invention has the following beneficial effects:

[0015] This invention uses branched-chain amino acids in peripheral blood as markers to determine whether a patient has cerebral venous thrombosis based on changes in branched-chain amino acid content, with an accuracy of over 0.838. It has a good predictive and diagnostic effect and provides an effective approach for the diagnosis, treatment and research of cerebral venous thrombosis. Attached Figure Description

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 Peripheral blood metabolomics analysis for healthy controls and patients with acute CVT;

[0018] Figure 2 Comparison of branched-chain amino acid content in peripheral blood of healthy individuals and those with CVT; (*: p < 0.05; **: p < 0.01; ***: p < 0.001);

[0019] Figure 3 Comparison of branched-chain amino acid content in peripheral blood of healthy individuals, patients with cerebral hemorrhage, cerebral infarction, and venous sinus thrombosis (CVT);

[0020] Figure 4 ROC curve for predicting venous sinus thrombosis using leucine as a biomarker;

[0021] Figure 5 ROC curve for isoleucine as a biomarker to predict venous sinus thrombosis;

[0022] Figure 6 ROC curve for predicting venous sinus thrombosis using valine as a biomarker;

[0023] Figure 7 ROC curve analysis was performed to predict venous sinus thrombosis by randomly combining branched-chain amino acids in peripheral blood of patients with CVT. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Where specific conditions are not specified in the embodiments, conventional conditions or conditions recommended by the manufacturer shall apply. Reagents or instruments whose manufacturers are not specified are all conventional products that can be purchased commercially.

[0025] This invention provides the application of a reagent for detecting the content of branched-chain amino acids in a sample in the preparation of products for screening cerebral venous thrombosis (CVT).

[0026] Through a series of creative efforts, the inventors screened and obtained a new biomarker for diagnosing CVT – branched-chain amino acids. By detecting the content of branched-chain amino acids in the blood, it is possible to effectively predict and diagnose whether a patient has CVT, significantly improving the diagnostic rate of CVT with an accuracy of over 0.838. This provides a new detection indicator for CVT patients, and the detection time is short and the accuracy is high, enabling patients to receive timely treatment and improve survival time and survival rate.

[0027] Preferably, the branched-chain amino acid is selected from at least one of isoleucine, leucine, and valine.

[0028] Preferably, the branched-chain amino acids include isoleucine, leucine, and valine.

[0029] Preferably, the sample is any one of a blood sample, a plasma sample, a serum sample, an environmental sample containing blood, an environmental sample containing plasma, and an environmental sample containing serum. The blood sample can be a peripheral blood sample from the subject. When the sample is an environmental sample, the direct purpose of the test can be to determine the source of the sample (e.g., the patient's identity).

[0030] The present invention also provides a training method for a predictive model for screening cerebral venous thrombosis, comprising: obtaining the content of branched-chain amino acids in training samples and the corresponding annotation results; wherein the branched-chain amino acids are the branched-chain amino acids described in any of the foregoing embodiments;

[0031] The content of branched-chain amino acids in the training samples is input into a pre-built prediction model to obtain prediction results; the prediction model is used to determine whether the patient has cerebral venous thrombosis based on the content of branched-chain amino acids in the peripheral blood of the sample.

[0032] The parameters of the prediction model are updated based on the annotation results and the prediction results.

[0033] This invention also provides a device for predicting cerebral venous thrombosis, which includes an acquisition module and a prediction module.

[0034] The acquisition module is used to acquire the detection results of the content of branched-chain amino acids in the sample to be tested; the branched-chain amino acids are those described in any of the foregoing embodiments.

[0035] The prediction module is used to input the detection results of the branched-chain amino acid content in the sample to be tested into the prediction model trained by the training method described in the aforementioned embodiments, so as to obtain the prediction results of the sample to be tested.

[0036] Preferably, the prediction device further includes a storage module for storing the prediction model.

[0037] Preferably, the sample is any one of a blood sample, a plasma sample, a serum sample, an environmental sample containing blood, an environmental sample containing plasma, and an environmental sample containing serum.

[0038] This invention also provides a training device for a predictive model for screening cerebral venous thrombosis, comprising:

[0039] The acquisition module is used to acquire the branched-chain amino acid content and corresponding annotation results in the training samples; the branched-chain amino acids are those described in the foregoing embodiments; the annotation results can indicate whether the sample has cerebral venous thrombosis.

[0040] The prediction module is used to input the branched-chain amino acid content of the training sample into a pre-built prediction model to obtain the prediction result; the prediction model is used to determine whether the sample has cerebral venous thrombosis based on the branched-chain amino acid content in the sample.

[0041] The parameter update module is used to update the parameters of the prediction model based on the annotation results and the prediction results.

[0042] Preferably, the training device further includes a storage module for storing the prediction model.

[0043] It should be noted that the modules described in any of the above embodiments can be stored in memory or embedded in the operating system (OS) of the electronic device provided in this application in the form of software or firmware, and can be executed by the processor in the electronic device. Meanwhile, the data, program code, etc., required to execute the above modules can be stored in memory.

[0044] This invention also provides an electronic device, which includes a processor and a memory; the memory is used to store a program, and when the program is executed by the processor, the processor enables the processor to implement the training method for the cerebral venous thrombosis prediction model as described in the foregoing embodiments.

[0045] The electronic device may also include a bus and a communication interface. The memory, processor, and communication interface are electrically connected directly or indirectly to each other to enable data transmission or interaction. For example, these components can be electrically connected to each other through one or more buses or signal lines.

[0046] The memory can be, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), etc.

[0047] A processor can be an integrated circuit chip with signal processing capabilities. This processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0048] In practical applications, the electronic device can be a server, cloud platform, mobile phone, tablet computer, laptop computer, ultra-mobile personal computer (UMPC), handheld computer, netbook, personal digital assistant (PDA), wearable electronic device, virtual reality device, etc. Therefore, the embodiments of this application do not limit the types of electronic devices.

[0049] This invention also provides a computer-readable medium storing a computer program, which, when executed by a processor, implements the training method for a cerebral venous thrombosis screening prediction model as described in the foregoing embodiments.

[0050] Computer-readable media can be general-purpose storage media, such as removable disks and hard drives.

[0051] Furthermore, embodiments of the present invention provide the application of reagents for detecting the content of branched-chain amino acids in samples in the preparation of products for detecting cerebral hemorrhage or cerebral infarction.

[0052] The embodiments of the present invention also provide a training method for a prediction model of cerebral hemorrhage or cerebral infarction, a prediction device for cerebral hemorrhage or cerebral infarction, an electronic device, and a computing and readable medium. The specific solutions are the same as the aforementioned CVT technical solutions, except that CVT is replaced by cerebral hemorrhage or cerebral infarction.

[0053] The features and performance of the present invention will be further described in detail below with reference to embodiments.

[0054] Example 1

[0055] Serum samples were collected from healthy controls (n=13) and acute CVT patients (n=40) and metabolomics were performed. Sequencing results showed that, compared with the healthy control group, CVT patients had significantly different metabolites in their peripheral blood. Figure 1 Principal component analysis showed that the differentially expressed genes could significantly distinguish between healthy individuals and CVT patients. Figure 1 (B)

[0056] The sequencing results were analyzed, and branched-chain amino acids (isoleucine, leucine, and valine) were extracted as detection markers and their analysis and validation were performed. The results are as follows: Figure 2 As shown, compared with healthy individuals (HC), patients with venous sinus thrombosis (CVT) had significantly lower peak concentrations of branched-chain amino acids in their peripheral blood (*: p < 0.05; **: p < 0.01; ***: p < 0.001).

[0057] Example 2

[0058] Comparison of branched-chain amino acid content in peripheral blood of healthy individuals, patients with cerebral hemorrhage, cerebral infarction, and venous sinus thrombosis (CVT).

[0059] ELISA testing revealed that, compared to healthy individuals, patients with cerebral hemorrhage and cerebral infarction had significantly elevated levels of branched-chain amino acids in their peripheral blood, while patients with venous sinus thrombosis had significantly decreased levels of branched-chain amino acids in their peripheral blood. Figure 3 In the middle A, branched-chain amino acid levels can be used to identify venous sinus thrombosis. Figure 3 (B) formation, cerebral infarction ( Figure 3 Cerebral hemorrhage (C) Figure 3 Diagnosis of D in patients with SARS (***: p < 0.0001).

[0060] Example 3

[0061] To verify the predictive efficacy of isoleucine, leucine, and valine individually for patients with venous sinus thrombosis (CVT), ROC (receiver operating characteristic curve) analysis was performed. The results showed that leucine AUC = 0.717 (95% CI: 0.583-0.835), isoleucine AUC = 0.777 (95% CI: 0.625-0.881), and valine AUC = 0.938 (95% CI: 0.866-0.99), indicating that these three branched-chain amino acids can identify CVT patients. (See [link to relevant documentation]). Figures 4-6 .

[0062] Example 4

[0063] The predictive efficacy of any pairwise or three-way combinations of isoleucine, leucine, and valine for patients with venous sinus thrombosis was verified using ROC receiver operating characteristic curve analysis.

[0064] When using leucine, isoleucine, and valine as three amino acids to predict and diagnose CVT, the AUC was 0.93 (95% CI: 0.834-0.996). Figure 7 (A)

[0065] When the combination of leucine and valine was analyzed using ROC curves, the AUC was 0.92 (95% CI: 0.826–0.98). Figure 7 (B)

[0066] When ROC curve analysis was performed on the combination of isoleucine and valine, the AUC was 0.914 (95% CI: 0.794–0.988). Figure 7 (C)

[0067] When the combination of leucine and isoleucine was analyzed using ROC curves, the AUC was 0.737 (95% CI: 0.391–0.851). Figure 7 D);

[0068] Example 5

[0069] To verify the accuracy of predicting CVT using any combination of isoleucine, leucine, and valine, or any combination of all three.

[0070] Univariate ROC curve analysis (Examples 2 and 3) showed that Valine AUC = 0.938 (95% CI: 0.866-0.99). Multivariate analysis and application of the combination of three amino acids, Leucine, Isoleucine, and Valine, to predict and diagnose CVT showed that AUC = 0.93 (95% CI: 0.834-0.996).

[0071] The average accuracy of Valine alone, calculated by accuracy (representing the proportion of samples with correct predictions), is 0.8, while the average accuracy of the combination of the three amino acids Leucine, Isoleucine, and Valine is 0.838.

[0072] It should be noted that the sample information used in Examples 3-5 is as follows: 61 healthy individuals, 67 cases of venous sinus thrombosis, 65 cases of cerebral infarction, and 66 cases of cerebral hemorrhage. There were no differences in age, gender, and indicators that may affect metabolic status, such as blood glucose and blood lipids, among the groups. See Table 1 for details.

[0073] Table 1 Sample Information

[0074]

[0075] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. The application of a reagent for detecting the content of branched-chain amino acids in a sample in the preparation of products for screening cerebral venous thrombosis, characterized in that, The branched-chain amino acids are selected from any combination of the following: A combination of valine and isoleucine; A combination of isoleucine, leucine, and valine.

2. The application according to claim 1, characterized in that, The sample is a blood sample.

3. The application according to claim 1, characterized in that, The sample can be either a plasma sample or a serum sample.

4. A training method for a predictive model for screening cerebral venous thrombosis, characterized in that, It includes: Obtain the branched-chain amino acid content and corresponding annotation results in the training samples; The branched-chain amino acid is the branched-chain amino acid described in claim 1; The content of branched-chain amino acids in the training samples is input into a pre-built prediction model to obtain prediction results; the prediction model is used to determine whether the patient has cerebral venous thrombosis based on the content of branched-chain amino acids in the peripheral blood of the sample. The parameters of the prediction model are updated based on the annotation results and the prediction results.

5. A device for predicting cerebral venous thrombosis, characterized in that, It includes: The acquisition module is used to acquire the detection results of the content of branched-chain amino acids in the sample to be tested; the branched-chain amino acids are those described in claim 1. The prediction module is used to input the detection results of the branched-chain amino acid content in the sample to be tested into the prediction model trained by the training method as described in claim 4, so as to obtain the prediction results of the sample to be tested.

6. The predictive device for cerebral venous thrombosis according to claim 5, characterized in that, A storage module is used to store the prediction model.

7. The predictive device for cerebral venous thrombosis according to claim 5, characterized in that, The sample is a blood sample.

8. The predictive device for cerebral venous thrombosis according to claim 5, characterized in that, The sample can be either a plasma sample or a serum sample.

9. A training device for a predictive model for screening cerebral venous thrombosis, characterized in that, It includes: The acquisition module is used to acquire the content of branched-chain amino acids in training samples and the corresponding annotation results; The branched-chain amino acid is the branched-chain amino acid described in claim 1; The prediction module is used to input the branched-chain amino acid content of the training sample into a pre-built prediction model to obtain the prediction result; the prediction model is used to determine whether the sample has cerebral venous thrombosis based on the branched-chain amino acid content in the sample. The parameter update module is used to update the parameters of the prediction model based on the annotation results and the prediction results.

10. An electronic device, characterized in that, The electronic device includes a processor and a memory; the memory is used to store a program, which, when executed by the processor, causes the processor to implement the training method for the cerebral venous thrombosis screening prediction model as described in claim 4.

11. A computer-readable medium, characterized in that, The computer-readable medium stores a computer program that, when executed by a processor, implements the training method for the cerebral venous thrombosis screening prediction model as described in claim 4.

Images