Establishment method of lupus erythematosus biomarker association model

Abstract

The invention discloses a lupus erythematosus biomarker association model establishment method, and relates to the technical field of SLE activity detection, and the method comprises the following steps: obtaining the disease activity degree score and basic physiological information of a patient, and obtaining the first marker data and the second marker data of the patient; performing patient mark grouping processing on the patients to obtain patient mark grouping information and patient marker data; sorting the markers, and establishing a marker weight processing method; a basic activity model is constructed based on the patient marker data, a personalized activity model is constructed, and systemic lupus erythematosus activity detection is carried out; the method is used for solving the problem that in the prior art, when the disease activity of systemic lupus erythematosus is detected, complex comprehensive disease activity indexes are usually used for evaluation, a rapid and accurate detection tool cannot be provided for clinicians, and the clinicians cannot be helped to diagnose and monitor the disease activity of SLE patients.

Description

Technical Field

[0001] The present invention relates to the technical field of SLE activity detection, and specifically to a method for establishing a biomarker association model for lupus erythematosus. Background Art

[0002] The SLE activity detection technology refers to a technical means for quantitatively judging the activity degree of the disease in patients with systemic lupus erythematosus through a series of laboratory examinations and clinical evaluation methods.

[0003] When the existing SLE activity detection technology detects the disease activity of systemic lupus erythematosus, it usually uses complex comprehensive disease activity indices for evaluation, such as the SLE Disease Activity Index (SLEDAI) and Systemic Lupus Activity Measure (SLAM); this increases the complexity of disease control and poses major challenges to clinicians in terms of rapid diagnosis and effective management; or it only relies on the quantitative characteristics of a certain biomarker to detect the disease activity of systemic lupus erythematosus. However, systemic lupus erythematosus is an autoimmune disease involving multiple systems. Only focusing on the quantitative characteristics of a single biomarker to judge the SLE disease activity is prone to misdiagnosis or misjudgment, and the detection results of a single biomarker may have false positives or false negatives; for example, in the patent application with the publication number CN112114126A, a diagnostic biomarker for systemic lupus erythematosus and its application are disclosed. Although this solution discovers a diagnostic biomarker for systemic lupus erythematosus, it does not mention the specific detection method for this biomarker. Therefore, when the existing SLE activity detection technology detects the disease activity of systemic lupus erythematosus, it usually uses complex comprehensive disease activity indices for evaluation, and cannot provide a rapid and accurate detection tool for clinicians to help clinicians diagnose and monitor the disease activity of SLE patients. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the existing technology to some extent. By obtaining the disease activity degree score and basic physiological information of the patient, and obtaining the first biomarker data and second biomarker data of the patient; performing patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data; and performing marker ranking processing and establishing a marker weight processing method; constructing a basic activity model based on the patient biomarker data and constructing a personalized activity model for detecting the activity of systemic lupus erythematosus; to solve the problem that when the existing SLE activity detection technology detects the disease activity of systemic lupus erythematosus, it usually uses complex comprehensive disease activity indices for evaluation, and cannot provide a rapid and accurate detection tool for clinicians to help clinicians diagnose and monitor the disease activity of SLE patients.

[0005] To achieve the above object, the present application provides a method for establishing a biomarker association model for lupus erythematosus, including the following steps: Obtain the disease activity score and basic physiological information of the patient, and obtain the first biomarker data and the second biomarker data of the patient; Perform patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data; Based on the patient marker grouping information and patient biomarker data, perform biomarker ranking processing and establish a biomarker weight processing method; Based on the patient biomarker data, construct a basic activity model, and based on the patient biomarker data of the patient, construct an individual activity model, and perform systemic lupus erythematosus activity detection.

[0006] Further, obtaining the disease activity score and basic physiological information of the patient, and obtaining the first biomarker data and the second biomarker data of the patient include the following sub-steps: For any systemic lupus erythematosus patient, denoted as the first patient, obtain the gender of the first patient, denoted as the basic physiological information of the first patient; According to the Systemic Lupus Erythematosus Disease Activity Index, obtain the systemic lupus erythematosus activity score of the first patient, denoted as the disease activity score of the first patient.

[0007] Further, obtaining the disease activity score and basic physiological information of the patient, and obtaining the first biomarker data and the second biomarker data of the patient further include the following sub-steps: The first marker includes CD4+ T cells and regulatory T cells; the second biomarker includes CD4+CD39+ T cells and CD39+ regulatory T cells; Collect the peripheral blood of the first patient, obtain the percentage and absolute count of CD4+ T cells in the peripheral blood of the first patient, and the percentage and absolute count of regulatory T cells, denoted as the first biomarker data of the first patient; And obtain the percentage of CD4+CD39+ T cells and the percentage of CD39+ regulatory T cells in the peripheral blood of the first patient, denoted as the second biomarker data of the first patient; Repeat to obtain the disease activity scores, basic physiological information, first biomarker data, and second biomarker data of multiple systemic lupus erythematosus patients.

[0008] Further, performing patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data includes the following sub-steps: According to the gender of the first patient, mark the first patient as a male patient or a female patient; Obtain the percentages and absolute counts of CD4+ T cells, the percentages and absolute counts of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells in all patients with systemic lupus erythematosus, and perform marker grouping processing, including: For any data of any marker, it is denoted as the first marker cell data; arrange the first marker cell data of all patients with systemic lupus erythematosus in ascending order; denote it as the first marker cell sequence, and obtain the minimum value and the maximum value in the first cell sequence, denoted as MX and MD respectively; set the number of sequence groups as k1; calculate the group interval size FD, FD = (MD - MX) / (k1 - 1); According to the group interval size FD, divide the first marker cell sequence into k1 group intervals, denoted as [MX - FD / 2, MX + FD / 2), [(MX + FD) - FD / 2, (MX + FD) + FD / 2), [(MX + 2*FD) - FD / 2, (MX + 2*FD) + FD / 2), ……, [MD - FD / 2, MD + FD / 2], and in accordance with the order of the k1 group intervals in the first marker cell sequence, successively denote them as the 1st group interval, the 2nd group interval, ……, the k1th group interval of the first marker cell data.

[0009] Furthermore, the sub-steps for performing patient marker grouping processing on patients to obtain patient marker grouping information and patient marker data also include the following: For any data of any marker in the first marker data and the second marker data of the first patient, perform marking according to the corresponding group interval; Repeat marking the first marker data and the second marker data of all patients with systemic lupus erythematosus, and after completion, obtain the first marker marking data and the second marker marking data in order, denoted as patient marker data; For all patients with systemic lupus erythematosus, divide the patients with the same gender and the same group interval for any data of any marker into one group, denoted as the 1st marker group, the 2nd marker group, …… the nth marker group respectively, and mark it as patient marker grouping information.

[0010] Furthermore, based on the patient marker grouping information and the patient marker data, perform marker sorting processing, and establish a marker weight processing method, including the following sub-steps: Set the disease activity score threshold as Q0; for any one of the marker groups denoted as any marker group, for any systemic lupus erythematosus patient within any marker group, if the corresponding disease activity score is greater than Q0, then mark the corresponding systemic lupus erythematosus patient as the active group of any marker group, otherwise mark the corresponding systemic lupus erythematosus patient as the remission group of any marker group, and repeat the marking for all systemic lupus erythematosus patients within any marker group; Obtain the percentages and absolute counts of CD4+ T cells, the percentages and absolute counts of regulatory T cells, and the percentage of CD39+ regulatory T cells of all systemic lupus erythematosus patients in the active group and remission group of any marker group; perform ROC curve analysis on any data of any one biomarker respectively, and calculate the AUC value, and sequentially obtain the AUC values corresponding to the percentage of CD4+ T cells, the absolute count of CD4+ T cells, the percentage of regulatory T cells, the absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells, and record them as CT1, CT2, TR1, TR2, DD1, and DT1 in sequence according to the data; Mark CT1, CT2, TR1, and TR2 as the first biomarker relationship parameters, and mark DD1 and DT1 as the second biomarker relationship parameters; Repeat the processing for all marker groups, and after completion, obtain the patient marker marking group information.

[0011] Furthermore, based on the patient marker grouping information and patient biomarker data, perform biomarker ranking processing, and establishing a biomarker weight processing method further includes the following sub-steps: For the first biomarker relationship parameters of any marker group, calculate MT = CT1 + CT2 + TR1 + TR2; for CT1, CT2, TR1, and TR2, calculate QC1 = CT1 / MT, QC2 = CT2 / MT, QR1 = TR1 / MT, and QR2 = TR2 / MT in sequence, and record QC1, QC2, QR1, and QR2 as the biomarker weights of CT1, CT2, TR1, and TR2 of any marker group respectively; For the second biomarker relationship parameters of any marker group, calculate MD = DD1 + DT1; for DD1 and DT1, calculate QD1 = DD1 / MD and QT1 = DT1 / MD in sequence; record QD1 and QT1 as the biomarker weights of DD1 and DT1 of any marker group respectively; Obtain the biomarker weights corresponding to all marker groups, and respectively calculate the averages of QC1, QC2, QR1, QR2, QD1, and QT1, and record them as PC1, PC2, PR1, PR2, PD1, and PT1 in sequence.

[0012] Further, a basic activity model is constructed based on patient biomarker data, and a personalized activity model is constructed based on the patient's biomarker data. The detection of systemic lupus erythematosus activity includes the following sub-steps: Based on the logistic regression model, a first original activity model and a second original activity model are constructed. The first original activity model is as follows: ; The second original activity model is as follows: ; where g1, g2, g3, g4, h1, and h2 respectively represent the percentage of CD4+ T cells, the absolute count of CD4+ T cells, the percentage of regulatory T cells, the absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells in sequence; P1 and P2 represent the systemic lupus erythematosus disease activity degree score; β0, β1, β2, β3, and β4 are the parameters of the first original activity model, and α0, α1, and α2 are the parameters of the second original activity model; The first original activity model is trained using the first biomarker data and the corresponding patient's disease activity degree score. After completion, a first basic activity model is obtained. The second original activity model is trained using the second biomarker data and the corresponding patient's disease activity degree score. After completion, a second basic activity model is obtained.

[0013] Further, a basic activity model is constructed based on patient biomarker data, and a personalized activity model is constructed based on the patient's biomarker data. The detection of systemic lupus erythematosus activity further includes the following sub-steps: For the patient to be detected, the basic physiological information, the first biomarker data, and the second biomarker data of the patient to be detected are obtained, and the marker group corresponding to the basic physiological information, the first biomarker data, and the second biomarker data of the patient to be detected is obtained, denoted as the first similarity group. The first biomarker data and the disease activity degree score of the patients corresponding to the first similarity group are obtained, denoted as the first similarity data; and the second biomarker data and the disease activity degree score of the patients corresponding to the first similarity group are obtained, denoted as the second similarity data; and QC1, QC2, QR1, QR2, QD1, and QT1 corresponding to the first similarity group are obtained.

[0014] Further, a basic activity model is constructed based on patient biomarker data, and a personalized activity model is constructed based on the patient's biomarker data. The detection of systemic lupus erythematosus activity further includes the following sub-steps: Change PC1, PC2, PR1, and PR2 in the first basic activity model to QC1, QC2, QR1, and QR2 corresponding to the first similarity grouping in sequence; and use the first similarity data to train the first basic activity model. After completion, obtain the first personalized activity model. Change PD1 and PT1 in the second basic activity model to QD1 and QT1 corresponding to the first similarity grouping in sequence; and use the second similarity data to train the second basic activity model. After completion, obtain the second personalized activity model. Input the first biomarker data and the second biomarker data of the patient to be detected into the first personalized activity model and the second personalized activity model in sequence, and obtain the first activity degree A1 and the first activity degree A2 in sequence; calculate A0 = q1 * A1 + q2 * A2 to obtain the systemic lupus erythematosus activity degree score A0 of the patient to be detected, where q1 and q2 are set weight coefficients.

[0015] Advantages of the present invention: By obtaining the disease activity degree score and basic physiological information of the patient, and obtaining the first biomarker data and the second biomarker data of the patient; performing patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data; performing biomarker ranking processing based on the patient marker grouping information and patient biomarker data, and establishing a biomarker weight processing method; constructing a basic activity model based on the patient biomarker data, and constructing a personalized activity model based on the patient biomarker data of the patient, and performing systemic lupus erythematosus activity detection; it can provide a rapid and accurate detection tool for clinicians, help clinicians diagnose and monitor the disease activity of SLE patients, and improve the accuracy of disease activity detection. By establishing a biomarker weight processing method, obtaining different weights of different biomarkers, and enabling the model to consider the importance of the input data, the advantage is that the model can pay more attention to important biomarker data, thereby more accurately capturing the rules in the data and improving the accuracy of the model's prediction of disease activity; by constructing two activity models through different biomarker data, the advantage is that more appropriate parameter settings can be selected according to the characteristics of the biomarker data they contain, and it can more flexibly adapt to the characteristics of different parameter biomarker data combinations, improve the overall performance of the detection model, and further improve the accuracy of detection. Description of the Drawings

[0016] Figure 1 It is a flowchart of the steps of the method of the present invention; Figure 2 It is a flowchart for dividing the first marker cell sequence of the present invention; Figure 3 It is a schematic diagram of the ROC curve analysis of the present invention; Figure 4 This is the pulse width scatter plot of the present invention. Specific embodiments

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Example 1, please refer to Figure 1 As shown, in the first aspect, the present application provides a method for establishing a biomarker association model for lupus erythematosus, including the following steps: Step S1, obtain the disease activity score and basic physiological information of the patient, and obtain the first biomarker data and the second biomarker data of the patient; Step S1 includes the following sub-steps: Step S101, for any patient with systemic lupus erythematosus, denoted as the first patient, obtain the gender of the first patient, denoted as the basic physiological information of the first patient; Systemic lupus erythematosus is abbreviated as SLE; Step S102, obtain the systemic lupus erythematosus activity score of the first patient according to the Systemic Lupus Erythematosus Disease Activity Index, denoted as the disease activity score of the first patient; The Systemic Lupus Erythematosus Disease Activity Index, i.e., Systemic Lupus Erythematosus Disease Activity Index (SLEDAI), is a commonly used tool in clinical practice to evaluate the disease activity of patients with systemic lupus erythematosus, including 11 aspects, and is scored according to the specific symptoms and examination results of the patient, with a total score of 105 points; The first marker includes CD4+ T cells and regulatory T cells; The second markers include CD4+CD39+ T cells and CD39+ regulatory T cells; Step S104, collect the peripheral blood of the first patient, obtain the percentage and absolute count of CD4+ T cells in the peripheral blood of the first patient, and the percentage and absolute count of regulatory T cells, denoted as the first biomarker data of the first patient; Peripheral blood refers to the blood outside the bone marrow in the circulatory system, containing various cell components, having important physiological functions, and being widely used in clinical diagnosis and other aspects; Step S105, and obtain the percentage of CD4+CD39+ T cells and the percentage of CD39+ regulatory T cells in the peripheral blood of the first patient, denoted as the second biomarker data of the first patient; Step S106, repeatedly obtain the disease activity scores, basic physiological information, first biomarker data, and second biomarker data of multiple patients with systemic lupus erythematosus; In the specific implementation process, CD4+ T cells are an important type of immune cell in the human immune system and can participate in the pathogenesis of various autoimmune diseases, such as rheumatoid arthritis, systemic lupus erythematosus, etc. Regulatory T cells, abbreviated as Tregs, are a subset of T cells that control the autoimmune reactivity in the body; CD39 is an enzyme that plays an important role in the immune system and other physiological processes; CD39, as an immunosuppressive molecule, plays an important role in regulating the immune response of SLE; Incorporating CD39 expression into the diagnostic assessment significantly improves the accuracy of determining the disease activity of SLE; Including CD39+ Treg cells and CD4+CD39+ T cells as biomarkers can provide clinicians with a more precise tool to diagnose and monitor the disease activity of SLE patients, and may improve disease management and treatment outcomes.

[0019] Step S2, perform patient marker grouping processing on the patients to obtain patient marker grouping information and patient biomarker data; Step S2 includes the following sub-steps: Step S201, according to the gender of the first patient, label the first patient as a male patient or a female patient; There are significant differences in the clinical manifestations, disease severity, and complications of systemic lupus erythematosus between male and female patients, which are mainly related to gender differences in hormones, genetics, and immune regulation. Therefore, differentiating between male and female patients facilitates subsequent targeted training of the model and improves the accuracy of subsequent activity detection; Step S202, obtain the percentages and absolute counts of CD4+ T cells, the percentages and absolute counts of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells of all patients with systemic lupus erythematosus, and perform marker grouping processing. Step S202 includes the following sub-steps: Step S2021, please refer to Figure 2 As shown, for any data of any biomarker, it is denoted as the first marker cell data; that is, the six biomarker data of the percentage and absolute count of CD4+ T cells, the percentage and absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells; Arrange the first marker cell data of all patients with systemic lupus erythematosus in ascending order; denote it as the first marker cell sequence, and obtain the minimum value and the maximum value in the first cell sequence, denoted as MX and MD respectively; Set the number of sequence groups as k1; Calculate the group interval size FD, FD = (MD - MX) / (k1 - 1); In this embodiment, k1 = 3, and k1 is generally 2 - 5; Step S2022: According to the size FD of the grouping interval, divide the first marker cell sequence into k1 grouping intervals, denoted as [MX - FD / 2, MX + FD / 2), [(MX + FD) - FD / 2, (MX + FD) + FD / 2), [(MX + 2*FD) - FD / 2, (MX + 2*FD) + FD / 2), ……, [MD - FD / 2, MD + FD / 2], and successively denote them as the 1st grouping interval, the 2nd grouping interval, ……, the k1th grouping interval of the first marker cell data in the order corresponding to the k1 grouping intervals in the first marker cell sequence; Step S2023: For any data of any one of the first marker data and the second marker data of the first patient, make a mark according to the corresponding grouping interval; Step S2024: Repeat marking the first marker data and the second marker data of all patients with systemic lupus erythematosus. After completion, obtain the first marker marked data and the second marker marked data in order, denoted as patient marker data; Step S203: For all patients with systemic lupus erythematosus, group the patients with the same gender and the same grouping interval where any data of any one of the markers is located into one group, and denote them as the 1st marker group, the 2nd marker group, ……, the nth marker group respectively, marked as patient marker group information; In the specific implementation process, k1 should not be too large. If it is too large, there will be fewer patients in the same grouping, that is, less data in the same grouping, which will lead to insufficient data for subsequent model training. The theoretical number of groupings is 2*k1^6, but due to the certain variation relationship among the six markers of the percentage and absolute count of CD4+T cells, the percentage and absolute count of regulatory T cells, the percentage of CD4+CD39+T cells, and the percentage of CD39+regulatory T cells, the actual number of groupings will be much less than 2*k1^6, so as to ensure the data quantity in the same grouping.

[0020] Step S3: Based on the patient marker group information and the patient marker data, perform marker sorting processing and establish a marker weight processing method; Step S3 includes the following sub-steps: Step S301, set the disease activity degree score threshold as Q0; for any one of the marker groups denoted as any marker group, for any systemic lupus erythematosus patient within any marker group, if the corresponding disease activity degree score is greater than Q0, then mark the corresponding systemic lupus erythematosus patient as the active group of any marker group, otherwise mark the corresponding systemic lupus erythematosus patient as the remission group of any marker group, and repeat marking all systemic lupus erythematosus patients within any marker group; in this embodiment, Q0 = 9, that is, those with a disease activity degree score greater than 9 are marked as the active group, and those with a disease activity degree score of 9 or below are marked as the remission group; Step S302, please refer to Figure 3 as shown in Figure 3 A, B, and C in are respectively the percentage graph of CD39+ regulatory T cells, the percentage graph of regulatory T cells, and the ROC curve analysis graph of the absolute count of regulatory T cells in order, and D is the combined graph of the curves of A, B, and C; Figure 3 E, F, and G in are respectively the percentage graph of CD4+CD39+ T cells, the percentage graph of CD4+ T cells, and the ROC curve analysis graph of the absolute count of CD4+ T cells; H is the combined graph of the curves of E, F, and G; obtain the percentage and absolute count of CD4+ T cells, the percentage and absolute count of regulatory T cells, and the percentage of CD39+ regulatory T cells of all systemic lupus erythematosus patients in the active group and remission group of any marker group; conduct ROC curve analysis on any data of any one biomarker respectively, and calculate the AUC value, and successively obtain the AUC values corresponding to the percentage of CD4+ T cells, the absolute count of CD4+ T cells, the percentage of regulatory T cells, the absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells, and record them as CT1, CT2, TR1, TR2, DD1, and DT1 in order according to the data; ROC curve analysis is a statistical method used to evaluate the performance of binary classification models. The ROC curve takes the false positive rate as the abscissa and the true positive rate as the ordinate; in binary classification problems, the model will make predictions for each sample and give a probability value of predicting the positive class; by setting different probability thresholds, the samples can be divided into positive and negative classes; the AUC value refers to the area under the ROC curve and is an important indicator to measure the performance of the ROC curve; the range of the AUC value is between 0.5 and 1; Step S303, mark CT1, CT2, TR1, and TR2 as the first biomarker relationship parameters, and mark DD1 and DT1 as the second biomarker relationship parameters; Step S304, repeat the processing for all marker groups, and after completion, obtain the patient marker marking group information; Step S305: For the first marker relationship parameter of any marker group, calculate MT = CT1 + CT2 + TR1 + TR2; for CT1, CT2, TR1, and TR2 in sequence, calculate QC1 = CT1 / MT, QC2 = CT2 / MT, QR1 = TR1 / MT, and QR2 = TR2 / MT, and record QC1, QC2, QR1, and QR2 as the marker weights of CT1, CT2, TR1, and TR2 of any marker group respectively; for example, if CT1 = 0.56, CT2 = 0.53, TR1 = 0.64, TR2 = 0.52, then MT = 2.25, QC1 = 0.56 / 2.25 = 0.25, QC2 = 0.53 / 2.25 = 0.24, QR1 = 0.64 / 2.25 = 0.28, QR2 = 0.52 / 2.25 = 0.23; Step S306: For the second marker relationship parameter of any marker group, calculate MD = DD1 + DT1; for DD1 and DT1 in sequence, calculate QD1 = DD1 / MD and QT1 = DT1 / MD; record QD1 and QT1 as the marker weights of DD1 and DT1 of any marker group respectively; for example, if DD1 = 0.71, DT1 = 0.75, then MD = 1.46, QC1 = 0.71 / 1.46 = 0.49, QC2 = 0.75 / 1.46 = 0.51; Step S307: Obtain the marker weights corresponding to all marker groups, and calculate the average values of QC1, QC2, QR1, QR2, QD1, and QT1 respectively, and record them as PC1, PC2, PR1, PR2, PD1, and PT1 in sequence; In the specific implementation process, the AUC value provides a quantitative index that can accurately reflect the ability of each marker data to distinguish different patient groups; the range of the AUC value is between 0.5 and 1. The closer the value is to 1, the stronger the prediction ability of the marker data for grouping, the higher the importance, that is, the greater the weight; the closer the value is to 0.5, the worse the prediction ability of the parameter, the relatively lower the importance, that is, the lower the weight; through this quantitative method, the importance differences between different marker data can be clearly compared.

[0021] Step S4: Construct a basic activity model based on the patient marker data, and construct a personalized activity model based on the patient's marker data, and perform systemic lupus erythematosus activity detection; Step S4 includes the following sub-steps: Step S401: Construct a first original activity model and a second original activity model based on the logistic regression model. The first original activity model is as follows: ; The second original activity model is as follows: ; where g1, g2, g3, g4, h1, and h2 respectively represent, in sequence, the percentage of CD4+ T cells, the absolute count of CD4+ T cells, the percentage of regulatory T cells, the absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells; P1 and P2 represent the systemic lupus erythematosus disease activity score; β0, β1, β2, β3, and β4 are the parameters of the first original activity model, and α0, α1, and α2 are the parameters of the second original activity model; before model training, β0, β1, β2, β3, β4, α0, α1, and α2 need to be initialized, and generally, β0, β1, β2, β3, β4, α0, α1, and α2 are initialized to relatively small random values, for example, 0.004; Step S402: Use the first biomarker data and the corresponding patient's disease activity score to train the first basic activity model. After completion, obtain the first original activity model. Then, use the second biomarker data and the corresponding patient's disease activity score to train the second basic activity model. After completion, obtain the second original activity model; all the corresponding biomarker data should be used in this training, which can allow the model to be exposed to as many samples and features as possible, so as to learn the patterns and rules widely existing in the data; in this way, the model can possess more comprehensive knowledge, have a more general understanding and adaptability to various situations, and avoid the model making one-sided judgments by only focusing on local data features; Step S403: For the patient to be tested, obtain the basic physiological information, the first biomarker data, and the second biomarker data of the patient to be tested, and obtain the marker grouping corresponding to the basic physiological information, the first biomarker data, and the second biomarker data of the patient to be tested, denoted as the first similar grouping. Obtain the first biomarker data and the disease activity score of the patients corresponding to the first similar grouping, denoted as the first similar data; and obtain the second biomarker data and the disease activity score of the patients corresponding to the first similar grouping, denoted as the second similar data; and obtain the QC1, QC2, QR1, QR2, QD1, and QT1 corresponding to the first similar grouping; for example, if the patient to be tested is male, and his gender plus the first biomarker data and the second biomarker data are in the second marker grouping, then the second marker grouping is denoted as the first similar grouping; Step S404: Sequentially change PC1, PC2, PR1, and PR2 in the first basic activity model to QC1, QC2, QR1, and QR2 corresponding to the first similar grouping; and use the first similar data to train the first basic activity model. After completion, obtain the first personalized activity model; Step S405: Change PD1 and PT1 in the second basic activity model to QD1 and QT1 corresponding to the first similarity group in sequence; and use the second similarity data to train the second basic activity model. After completion, obtain the second personalized activity model. The data used in this training is from patients similar to the patient to be tested, which can further optimize the model according to the characteristics of a specific patient group. Since similar patients may have similar disease characteristics, physiological conditions, or other relevant factors, by focusing on this part of the data, the model can learn more deeply about the specific patterns and characteristics related to this patient group, thereby improving the prediction accuracy and pertinence for patients in this group. Step S406: Input the first biomarker data and the second biomarker data of the patient to be tested into the first personalized activity model and the second personalized activity model in sequence, and obtain the first activity A1 and the first activity A2 in sequence; calculate A0 = q1 * A1 + q2 * A2 to obtain the systemic lupus erythematosus activity degree score A0 of the patient to be tested, where q1 and q2 are set weight coefficients. In this embodiment, q1 is 0.4 and q2 is 0.6, which can be set according to the actual application scenario. In the specific implementation process, obtain different weights for different biomarkers and enable the model to consider the importance of the input data. The weights can be assigned according to the actual contribution degree of each biomarker to the disease activity. For example, if in the actual situation, the percentage of CD39+ regulatory T cells has a greater impact on the activity, then giving it a higher weight can make the model pay more attention to this parameter, thereby more accurately capturing the rules in the data and improving the accuracy of the model's prediction of the disease activity. And it can avoid the model relying too much on some less important data or being affected by noise data. When the weight of a certain data is correctly set, even if there are some small fluctuations in the data of this parameter, it will not have too much impact on the output result of the model, thereby making the model more stable and reducing the uncertainty of the model output.

[0022] Embodiment 2, Second aspect, please refer to Figure 4 as shown Figure 4The structure diagram of an electronic device is exemplified. The electronic device may include: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus. The memory stores computer-readable instructions. The processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a method for establishing a lupus biomarker association model are run to achieve the following functions: obtaining the disease activity degree score and basic physiological information of a patient, and obtaining the first biomarker data and the second biomarker data of the patient; performing patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data; performing biomarker ranking processing based on the patient marker grouping information and the patient biomarker data, and establishing a biomarker weight processing method; constructing a basic activity degree model based on the patient biomarker data, and constructing a personalized activity degree model based on the patient biomarker data of the patient, and performing systemic lupus erythematosus activity detection.

[0023] In addition, when the logical instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0024] Embodiment 3, Third aspect, the present application also provides a computer-readable storage medium. The present application provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method for establishing a lupus biomarker association model are run to achieve the following functions: obtaining the disease activity degree score and basic physiological information of a patient, and obtaining the first biomarker data and the second biomarker data of the patient; performing patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data; performing biomarker ranking processing based on the patient marker grouping information and the patient biomarker data, and establishing a biomarker weight processing method; constructing a basic activity degree model based on the patient biomarker data, and constructing a personalized activity degree model based on the patient biomarker data of the patient, and performing systemic lupus erythematosus activity detection.

[0025] With the description of the above embodiments, the embodiments of the present invention can be provided as a method, a system or a computer program product. Based on such an understanding, the above technical solution, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each of the embodiments or some parts of the embodiments.

[0026] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The above-described embodiments are merely illustrative. For example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For another example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some communication interfaces. The indirect coupling or communication connection of systems, modules and units can be in an electrical, mechanical or other form.

[0027] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for establishing a biomarker association model for lupus erythematosus, characterized in that, It includes the following steps: Obtain the disease activity degree score and basic physiological information of the patient, and obtain the first biomarker data and the second biomarker data of the patient; Perform patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data; Perform biomarker ranking processing based on the patient marker grouping information and patient biomarker data, and establish a biomarker weight processing method; Construct a basic activity model based on the patient biomarker data, and construct a personalized activity model based on the patient biomarker data of the patient, and perform systemic lupus erythematosus activity detection.

2. The method for establishing a biomarker association model for lupus erythematosus according to claim 1, wherein Obtaining the disease activity degree score and basic physiological information of the patient, and obtaining the first biomarker data and the second biomarker data of the patient includes the following sub-steps: For any systemic lupus erythematosus patient, denoted as the first patient, obtain the gender of the first patient, denoted as the basic physiological information of the first patient; Obtain the systemic lupus erythematosus activity degree score of the first patient according to the systemic lupus erythematosus disease activity index, denoted as the disease activity degree score of the first patient.

3. The method for establishing a biomarker association model for lupus erythematosus according to claim 2, wherein Obtaining the disease activity degree score and basic physiological information of the patient, and obtaining the first biomarker data and the second biomarker data of the patient further includes the following sub-steps: The first biomarker includes CD4+ T cells and regulatory T cells; the second biomarker includes CD4+CD39+ T cells and CD39+ regulatory T cells; Collect the peripheral blood of the first patient, obtain the percentage and absolute count of CD4+ T cells in the peripheral blood of the first patient, and the percentage and absolute count of regulatory T cells, denoted as the first biomarker data of the first patient; And obtain the percentage of CD4+CD39+ T cells and the percentage of CD39+ regulatory T cells in the peripheral blood of the first patient, denoted as the second biomarker data of the first patient; Repeat to obtain the disease activity degree scores, basic physiological information, first biomarker data and second biomarker data of multiple systemic lupus erythematosus patients.

4. A method for establishing a biomarker association model for lupus erythematosus according to claim 3, characterized in that, Performing patient marker grouping processing on the patient to obtain patient marker grouping information and patient biomarker data includes the following sub-steps: According to the gender of the first patient, mark the first patient as a male patient or a female patient; Obtain the percentage and absolute count of CD4+ T cells, the percentage and absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells of all systemic lupus erythematosus patients, and perform marker grouping processing, including: For any data of any biomarker, denoted as the first marker cell data; arrange the first marker cell data of all systemic lupus erythematosus patients in ascending order; denoted as the first marker cell sequence, obtain the minimum value and the maximum value in the first cell sequence, denoted as MX and MD respectively; set the number of sequence groups as k1; calculate the grouping interval size FD, FD = (MD - MX) / (k1 - 1); According to the size FD of the grouping interval, the first marker cell sequence is divided into k1 grouping intervals, denoted as [MX - FD / 2, MX + FD / 2), [(MX + FD) - FD / 2, (MX + FD) + FD / 2), [(MX + 2*FD) - FD / 2, (MX + 2*FD) + FD / 2), ……, [MD - FD / 2, MD + FD / 2], and according to the order corresponding to the k1 grouping intervals in the first marker cell sequence, they are successively denoted as the 1st grouping interval, the 2nd grouping interval, ……, the k1th grouping interval of the first marker cell data.

5. The method for establishing a biomarker association model for lupus erythematosus according to claim 4, characterized in that, The patient marking grouping process for patients to obtain patient marker grouping information and patient marker data further includes the following sub-steps: For any data of any one of the first marker data and the second marker data of the first patient, mark according to the corresponding grouping interval. Repeat marking the first marker data and the second marker data of all patients with systemic lupus erythematosus. After completion, obtain the first marker marked data and the second marker marked data in order, denoted as patient marker data. For all patients with systemic lupus erythematosus, group the patients with the same gender and the same grouping interval where any data of any one of the markers is located into one group, denoted as the 1st marker grouping, the 2nd marker grouping, …… the nth marker grouping respectively, and mark it as patient marker grouping information.

6. The method for establishing a biomarker association model for lupus erythematosus according to claim 5, wherein Based on the patient marker grouping information and the patient marker data, perform marker sorting processing and establish a marker weight processing method, including the following sub-steps: Set the disease activity degree score threshold as Q0; for any one marker grouping denoted as any marker grouping, for any patient with systemic lupus erythematosus in any marker grouping, if the corresponding disease activity degree score is greater than Q0, then mark the corresponding patient with systemic lupus erythematosus as the active group of any marker grouping, otherwise mark the corresponding patient with systemic lupus erythematosus as the remission group of any marker grouping, and repeat marking all patients with systemic lupus erythematosus in any marker grouping. Obtain the percentages and absolute counts of CD4+ T cells, the percentages and absolute counts of regulatory T cells, and the percentage of CD39+ regulatory T cells of all patients with systemic lupus erythematosus in the active group and the remission group of any marker grouping; perform ROC curve analysis on any data of any one of the markers respectively, and calculate the AUC value, and successively obtain the AUC values corresponding to the percentage of CD4+ T cells, the absolute count of CD4+ T cells, the percentage of regulatory T cells, the absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells, and denote them as CT1, CT2, TR1, TR2, DD1, and DT1 in order according to the data. Mark CT1, CT2, TR1, and TR2 as the first marker relationship parameters, and mark DD1 and DT1 as the second marker relationship parameters. Repeat the processing for all marker groupings. After completion, obtain the patient marker marked grouping information.

7. The method for establishing a biomarker association model for lupus erythematosus according to claim 6, characterized in that, Perform marker ranking processing based on patient flag grouping information and patient marker data, and establish a marker weight processing method, which further includes the following sub-steps: For the first marker relationship parameter of any flag grouping, calculate MT = CT1 + CT2 + TR1 + TR2; for CT1, CT2, TR1, and TR2, calculate QC1 = CT1 / MT, QC2 = CT2 / MT, QR1 = TR1 / MT, and QR2 = TR2 / MT in sequence, and record QC1, QC2, QR1, and QR2 as the marker weights of CT1, CT2, TR1, and TR2 of any flag grouping respectively; For the second marker relationship parameter of any flag grouping, calculate MD = DD1 + DT1; for DD1 and DT1, calculate QD1 = DD1 / MD and QT1 = DT1 / MD in sequence; record QD1 and QT1 as the marker weights of DD1 and DT1 of any flag grouping respectively; Obtain the marker weights corresponding to all flag groupings, and calculate the average values of QC1, QC2, QR1, QR2, QD1, and QT1 respectively, and record them as PC1, PC2, PR1, PR2, PD1, and PT1 in sequence.

8. A method for establishing a biomarker association model for lupus erythematosus according to claim 7, characterized in that Construct a basic activity model based on patient marker data, and construct a personalized activity model based on the patient's marker data, and perform systemic lupus erythematosus activity detection, which includes the following sub-steps: Construct the first original activity model and the second original activity model based on the logistic regression model. The first original activity model is as follows: ; The second original activity model is as follows: ; where g1, g2, g3, g4, h1, and h2 respectively represent the percentage of CD4+ T cells, the absolute count of CD4+ T cells, the percentage of regulatory T cells, the absolute count of regulatory T cells, the percentage of CD4+CD39+ T cells, and the percentage of CD39+ regulatory T cells in sequence; P1 and P2 represent the systemic lupus erythematosus disease activity degree score; β0, β1, β2, β3, and β4 are the parameters of the first original activity model, and α0, α1, and α2 are the parameters of the second original activity model; Use the first marker data and the disease activity degree score of the corresponding patient to train the first original activity model, and after completion, obtain the first basic activity model. Use the second marker data and the disease activity degree score of the corresponding patient to train the second original activity model, and after completion, obtain the second basic activity model.

9. The method for establishing a biomarker association model for lupus erythematosus according to claim 8, wherein, Construct a basic activity model based on patient marker data, and construct a personalized activity model based on the patient's marker data, and perform systemic lupus erythematosus activity detection, which further includes the following sub-steps: For the patient to be detected, obtain the basic physiological information, the first marker data, and the second marker data of the patient to be detected, and obtain the flag grouping corresponding to the basic physiological information, the first marker data, and the second marker data of the patient to be detected, which is recorded as the first similar grouping. Obtain the first marker data and the disease activity degree score of the patient corresponding to the first similar grouping, which are recorded as the first similar data; And obtain the second marker data and the disease activity degree score of the patient corresponding to the first similar grouping, which are recorded as the second similar data; and obtain QC1, QC2, QR1, QR2, QD1, and QT1 corresponding to the first similar grouping.

10. The method for establishing a biomarker association model for lupus erythematosus according to claim 9, characterized in that, Construct a basic activity model based on patient marker data, and construct a personalized activity model based on the patient's marker data, and perform systemic lupus erythematosus activity detection, which further includes the following sub-steps: Change PC1, PC2, PR1, and PR2 in the first basic activity model to QC1, QC2, QR1, and QR2 corresponding to the first similarity group in sequence; and use the first similarity data to train the first basic activity model. After completion, obtain the first personalized activity model; Change PD1 and PT1 in the second basic activity model to QD1 and QT1 corresponding to the first similarity group in sequence; And use the second similarity data to train the second basic activity model. After completion, obtain the second personalized activity model; Input the first biomarker data and the second biomarker data of the patient to be detected into the first personalized activity model and the second personalized activity model in sequence, and obtain the first activity degree A1 and the first activity degree A2 in sequence; calculate A0 = q1 * A1 + q2 * A2 to obtain the systemic lupus erythematosus activity degree score A0 of the patient to be detected, where q1 and q2 are set weight coefficients.

Images