Construction method and application of systemic lupus erythematosus activity evaluation model

Abstract

The invention relates to the technical field of medical data processing, and discloses a construction method and application of a systemic lupus erythematosus activity evaluation model. Expression level data of CD177 on the surface of neutrophil, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data and complement C4 concentration data are combined, a machine learning algorithm is utilized, and the systemic lupus erythematosus activity evaluation model is constructed. A high-precision systemic lupus erythematosus activity evaluation model is obtained through training, systemic lupus erythematosus activity can be evaluated efficiently, comprehensively and accurately, and an SLE patient is effectively assisted in seeing a doctor in time and making a correct treatment decision.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a method for constructing a systemic lupus erythematosus activity assessment model and its application. Background Art

[0002] Systemic lupus erythematosus (SLE) is a complex autoimmune disease with no cure. It mainly relies on drug therapy and disease monitoring to control the disease and delay its progression. The clinical manifestations of SLE are diverse, including fatigue, fever, joint pain, skin lesions, etc. In severe cases, it can affect important organs such as the kidneys, brain, and cardiovascular system, leading to organ failure or even death. Therefore, accurate assessment of the activity and prognosis of SLE is crucial for the treatment and management of patients.

[0003] At present, the activity assessment of SLE mainly relies on clinical manifestations, laboratory tests and disease activity scoring systems, such as the Systemic Lupus Erythematosus Disease Activity Index (SLEDAI) and the British Lupus Assessment Group Index (BILAG). However, these assessment methods have certain limitations, such as strong subjectivity, complex operation, and difficult result interpretation. According to relevant studies, almost two-thirds of cases that were judged to have clinically significant improvement or deterioration were not identified by the SLEDAI score. Anti-dsDNA antibodies and complement C3 and C4 are commonly used laboratory indicators for assessing SLE disease activity. Although anti-dsDNA antibodies are specific, the correlation between their levels and disease activity is not always consistent, and they may show a platform effect at different stages of the disease. Moreover, differences in detection methods affect the accuracy of anti-dsDNA antibody test results. In addition, the reduction of complement C3 and C4 non-specifically points to SLE, and its recovery speed is slow, and it is affected by genetic factors and varies between individuals.

[0004] Therefore, there is an urgent need for a method to construct a systemic lupus erythematosus activity assessment model to obtain a high-precision systemic lupus erythematosus activity assessment model to assist in the efficient and accurate assessment of systemic lupus erythematosus activity and provide effective and reliable data support for making treatment decisions. Summary of the invention

[0005] The present invention provides a method for constructing a systemic lupus erythematosus activity assessment model and its application, so as to solve the defect that the prior art cannot efficiently and accurately assess the activity of systemic lupus erythematosus.

[0006] The present invention provides a method for constructing a systemic lupus erythematosus activity assessment model, comprising:

[0007] Acquire the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, wherein the target population includes patient populations at different stages of SLE;

[0008] Based on the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, a systemic lupus erythematosus activity assessment model was trained through a machine learning algorithm.

[0009] According to a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, the patient population in different stages of SLE includes any one of the following or any combination thereof: remission stage, active stage.

[0010] According to a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, the systemic lupus erythematosus activity assessment model is trained by a machine learning algorithm based on the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, comprising:

[0011] According to the expression level data of CD177 on the surface of neutrophils of the target population, the titer data of anti-dsDNA antibodies, the concentration data of anti-dsDNA antibodies, the concentration data of complement C3, and the concentration data of complement C4, the expression level data of CD177 on the surface of neutrophils of the target population, the titer data of anti-dsDNA antibodies, the concentration data of anti-dsDNA antibodies, the concentration data of complement C3, and the concentration data of complement C4 of the target population are normalized into data of a unified dimension by using preset standards;

[0012] Based on the normalized target population's neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data, a systemic lupus erythematosus activity assessment model was trained using a machine learning algorithm.

[0013] According to a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, according to the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data are normalized into data of a unified dimension using preset standards, including:

[0014] When the expression level data of CD177 on the surface of neutrophils of an individual in the target population indicates that the expression level of CD177 on the surface of neutrophils is higher than the first preset threshold, the expression level of CD177 on the surface of neutrophils of the individual is determined to be abnormal, and the expression level data of CD177 on the surface of neutrophils is converted to the first fixed value, otherwise, it is converted to the second fixed value;

[0015] When the anti-dsDNA antibody titer data of an individual in the target population indicates that its anti-dsDNA antibody-IF is positive, the anti-dsDNA antibody-IF of the individual is determined to be abnormal, and the anti-dsDNA antibody titer data is converted to a first fixed value, otherwise it is converted to a second fixed value;

[0016] When the anti-dsDNA antibody concentration data of an individual in the target population indicates that the anti-dsDNA antibody-CLIA is positive, the anti-dsDNA antibody-CLIA of the individual is determined to be abnormal, and the anti-dsDNA antibody concentration data is converted to a first fixed value, otherwise it is converted to a second fixed value;

[0017] When the complement C3 concentration data of an individual in the target population indicates that its complement C3 concentration is lower than the second preset threshold, the complement C3 concentration of the individual is determined to be abnormal, and the complement C3 concentration data is converted to the first fixed value, otherwise, it is converted to the second fixed value;

[0018] When the complement C4 concentration data of an individual in the target population indicates that its complement C4 concentration is lower than the third preset threshold, the complement C4 concentration of the individual is determined to be abnormal, and its complement C4 concentration data is converted to the first fixed value, otherwise it is converted to the second fixed value.

[0019] According to a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, the systemic lupus erythematosus activity assessment model is trained by a machine learning algorithm based on the normalized neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, comprising:

[0020] According to the normalized neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, several systemic lupus erythematosus activity assessment models were trained through several machine learning algorithms;

[0021] The model performances of several systemic lupus erythematosus activity assessment models were compared to obtain the final systemic lupus erythematosus activity assessment model.

[0022] According to a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, the several machine learning algorithms include any one of the following or any combination thereof: a logistic regression algorithm, a random forest algorithm, a support vector machine algorithm, and a decision tree algorithm.

[0023] According to a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, the method of comparing the model performances of several systemic lupus erythematosus activity assessment models to obtain a final systemic lupus erythematosus activity assessment model comprises:

[0024] The model performance of several systemic lupus erythematosus activity assessment models was compared using evaluation indicators to obtain the final systemic lupus erythematosus activity assessment model, wherein the evaluation indicators included any one of the following or any combination thereof: accuracy, precision, recall rate, Fi score, sensitivity, specificity, and AUC value.

[0025] According to the method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention, the final systemic lupus erythematosus activity assessment model is a systemic lupus erythematosus activity assessment model obtained by training with a logistic regression algorithm, and its expression is:

[0026]

[0027] In the expression of the final systemic lupus erythematosus activity assessment model, ds DNA IF, ds DNA CLIA, C3, C4, and CCD177MFIhiNEU represent the normalized anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, complement C4 concentration data, and CD177MFI neutrophil surface CD177 expression level data, respectively.

[0028] The present invention also provides a systemic lupus erythematosus activity auxiliary assessment system, comprising:

[0029] The data receiving module is used to receive the expression level data of CD177 on the surface of neutrophils of the subject to be tested, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data sent from at least one terminal;

[0030] An auxiliary assessment module, used to obtain a systemic lupus erythematosus activity assessment result of the subject according to the systemic lupus erythematosus activity assessment model obtained by the construction method of the systemic lupus erythematosus activity assessment model described in any of the above items based on the expression level data of CD177 on the surface of neutrophils of the subject, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data of the subject;

[0031] The data output module is used to send the systemic lupus erythematosus activity assessment result of the subject to be tested to at least one terminal.

[0032] The present invention also provides an electronic device, comprising a processor and a memory storing a computer program, wherein the processor implements any of the above-mentioned methods for constructing a systemic lupus erythematosus activity assessment model when executing the computer program.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for constructing any of the above-mentioned systemic lupus erythematosus activity assessment models is implemented.

[0034] The present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute any of the above-mentioned methods for constructing a systemic lupus erythematosus activity assessment model.

[0035] The present invention provides a method for constructing a systemic lupus erythematosus activity assessment model and its application, which combines the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data, and uses a machine learning algorithm to train a high-precision systemic lupus erythematosus activity assessment model, which can efficiently, comprehensively, and accurately assess the activity of systemic lupus erythematosus, and effectively assist SLE patients to seek medical treatment in a timely manner and make correct treatment decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A schematic diagram of a process for constructing a systemic lupus erythematosus activity assessment model provided by the present invention.

[0038] Figure 2 The ROC curve of the systemic lupus erythematosus activity assessment model trained by the logistic regression algorithm for assessing SLE activity is shown.

[0039] Figure 3 The importance scores of the expression level of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data in assessing SLE activity using the systemic lupus erythematosus activity assessment model trained by the logistic regression algorithm are shown.

[0040] Figure 4 The expression level of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, complement C4 concentration data, and the ROC curve of the systemic lupus erythematosus activity assessment model trained by the logistic regression algorithm when assessing SLE activity are shown.

[0041] Figure 5 The expression level of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, complement C4 concentration data, and the systemic lupus erythematosus activity assessment model trained by the logistic regression algorithm are shown, and their correlation with the systemic lupus erythematosus disease activity index (SLEDAI) when assessing SLE activity.

[0042] Figure 6 This is a schematic diagram of the structure of a systemic lupus erythematosus activity auxiliary assessment system provided by the present invention.

[0043] Figure 7 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments, and they should not be understood as limitations on the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0045] Figure 1 A flow chart of a method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention. The execution subject of the method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention can be any applicable terminal side device or network side device, such as a construction device for a systemic lupus erythematosus activity assessment model.

[0046] See also Figure 1 The method for constructing a systemic lupus erythematosus activity assessment model provided by the present invention may include:

[0047] S110. Obtain the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, wherein the target population includes patient populations at different stages of SLE. In this embodiment, the patient populations at different stages of SLE include patient populations at a remission stage and patient populations at an active stage. The SLE activity of the patient populations at different stages of SLE can be determined based on the SLEDAI score. When the SLEDAI score is less than or equal to 4, it is in the remission stage, and when it is greater than 4, it is in the active stage.

[0048] Specifically, the expression level data of CD177 on the surface of neutrophils of the target population, the titer data of anti-dsDNA antibodies, the concentration data of anti-dsDNA antibodies, the concentration data of complement C3, and the concentration data of complement C4 can be obtained by medical staff through sample collection and processing of SLE patients. For example, 1) firstly collect neutrophil samples of the target population, collect peripheral blood of the target population and the healthy control population into EDTA tubes, and use Ficoll-Paque 1) Separate peripheral blood mononuclear cells by the Plus gradient method, then precipitate the red blood cell layer with dextran to purify neutrophils, and then lyse the remaining red blood cells with lysis buffer to separate neutrophils into single cell suspensions; 2) Use flow cytometry to detect the expression level of CD177 on the surface of neutrophils, incubate with Fc receptor blocker for 15 minutes, and then use CD177, CD15, and CD14 antibodies for surface staining. After staining and washing for 30 minutes, analyze the single cell suspension by flow cytometry; 3) Detect the mean fluorescence intensity (MFI) of CD177 by flow analyzer as the C D177 expression level; at the same time, the serum of the target group was collected, and the anti-dsDNA antibody titer was detected by indirect immunofluorescence method as anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration was detected by chemiluminescence method as anti-dsDNA antibody concentration data, and the concentrations of complement C3 and C4 were detected by immunoturbidimetry as complement C3 concentration data and complement C4 concentration data, so as to obtain the expression level data of CD177 on the neutrophil surface of the target group, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data.

[0049] S120. Based on the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, a systemic lupus erythematosus activity assessment model was trained through a machine learning algorithm.

[0050] In one embodiment, S120 may include:

[0051] S1201. According to the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data are normalized into data of a unified dimension using preset standards, wherein the pre-examination standard may be, for example (see Table 1):

[0052] When the expression level data of CD177 on the surface of neutrophils of an individual in the target population indicates that the expression level of CD177 on the surface of neutrophils is higher than the first preset threshold (15659 in this embodiment, i.e., when MFI>15659), the expression level of CD177 on the surface of neutrophils of the individual is determined to be abnormal, and the expression level data of CD177 on the surface of neutrophils is converted to a first fixed value (0 in this embodiment), otherwise it is converted to a second fixed value (1 in this embodiment);

[0053] When the anti-dsDNA antibody titer data of an individual in the target population indicates that the anti-dsDNA antibody-IF is positive (in this embodiment, the anti-dsDNA antibody titer is greater than 1:10, which is positive), the anti-dsDNA antibody-IF of the individual is determined to be abnormal, and the anti-dsDNA antibody titer data is converted to the first fixed value, otherwise it is converted to the second fixed value;

[0054] When the anti-dsDNA antibody concentration data of an individual in the target population indicates that the anti-dsDNA antibody-CLIA is positive (in this embodiment, the anti-dsDNA antibody concentration>24IU / ml is positive), the anti-dsDNA antibody-CLIA of the individual is determined to be abnormal, and the anti-dsDNA antibody concentration data is converted to the first fixed value, otherwise it is converted to the second fixed value;

[0055] When the complement C3 concentration data of an individual in the target population indicates that the complement C3 concentration is lower than the second preset threshold value (in this embodiment, the complement C3 concentration is <0.73 g / L), the complement C3 concentration of the individual is determined to be abnormal, and the complement C3 concentration data is converted to the first fixed value, otherwise, it is converted to the second fixed value;

[0056] When the complement C4 concentration data of an individual in the target population indicates that the complement C4 concentration is lower than the third preset threshold value (in this embodiment, the complement C4 concentration is <0.1 g / L), the complement C4 concentration of the individual is determined to be abnormal, and the complement C4 concentration data is converted to the first fixed value, otherwise, it is converted to the second fixed value;

[0057] Table 1

[0058]

[0059] S1202. According to the normalized neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, several systemic lupus erythematosus activity assessment models are trained by several machine learning algorithms, wherein the several machine learning algorithms include any one of the following or any combination thereof: logistic regression algorithm, random forest algorithm, support vector machine algorithm, and decision tree algorithm;

[0060] S1203. Using evaluation indicators, compare the model performance of several systemic lupus erythematosus activity assessment models to obtain a final systemic lupus erythematosus activity assessment model, wherein the evaluation indicators include any one of the following or any combination thereof: accuracy, precision, recall rate, Fi score, sensitivity, specificity, and AUC value.

[0061] In this embodiment, the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of 105 SLE patients (including 65 cases in the active stage and 40 cases in the remission stage) were collected as the training data of the model (70% as the training set and 30% as the test set), and four systemic lupus erythematosus activity assessment models were obtained by training using the logistic regression algorithm, random forest algorithm, support vector machine algorithm, and decision tree algorithm, respectively. The comparison results of their accuracy are shown in Table 2.

[0062] Table 2

[0063] Model Accuracy Logistic Regression 63.33％ Random Forest 53.33％ Support Vector Machine (SVM) 60.00％ Decision Tree 56.67％

[0064] According to the accuracy of four systemic lupus erythematosus activity assessment models, this embodiment uses a systemic lupus erythematosus activity assessment model trained by a logistic regression algorithm (hereinafter referred to as the logistic regression model) as the final systemic lupus erythematosus activity assessment model. The accuracy of the logistic regression model is 63.33%, the precision is 62.07%, the recall rate is 100%, and the F1 score is 76.60%. Its sensitivity in assessing SLE activity is 88.89% and its specificity is 75.00%, which is far superior to any single indicator of the expression level of CD177 on the surface of neutrophils, anti-dsDNA antibody-IF, anti-dsDNA antibody-CLIA, complement C3, and complement C4. The area under the curve (AUC) is an important indicator for measuring the performance of a classification model. The closer the AUC value is to 1, the better the performance of the model. The AUC of the logistic regression model is 0.826, indicating that the logistic regression model performs well in the SLE activity classification task (see Figure 2 ). The logistic regression model has good performance in distinguishing SLE activity. The importance scores of individual indicators in the logistic regression model, including the expression level of CD177 on the surface of neutrophils, anti-dsDNA antibody-IF, anti-dsDNA antibody-CLIA, complement C3, and complement C4, are shown in Figure 3 and Table 3.

[0065] Table 3

[0066] feature importance(%) <![CDATA[CD177 MFIhi OR]]> 73.13 C4 52.71 dsDNA-IF 48.47 dsDNA-CLIA 12.58 C3 12.49

[0067] The final systemic lupus erythematosus activity assessment model in this embodiment is a systemic lupus erythematosus activity assessment model obtained by training with a logistic regression algorithm, and its expression is:

[0068]

[0069] In the expression of the final systemic lupus erythematosus activity assessment model, ds DNA IF, ds DNA CLIA, C3, C4, and CD177MFIhiNEU represent the normalized anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, complement C4 concentration data, and CD177MFI neutrophil surface CD177 expression level data, respectively.

[0070] Also, see Figure 4 As shown in Table 4, the ROC curve of the logistic regression model constructed by combining the five indicators of neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data for evaluating SLE activity showed superior performance compared with a single indicator, with improved sensitivity and specificity.

[0071] Table 4

[0072]

[0073] See also Figure 5 ,Comparing the correlation between the logistic regression model and the 5 indices and the SLEDAI score, ,it can be seen that the logistic regression model showed a better correlation.

[0074] The model optimal threshold of the final systemic lupus erythematosus activity assessment model in this embodiment is 0.667. When the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the subject are input into the final systemic lupus erythematosus activity assessment model, and the obtained P value is greater than 0.667, it is determined that the subject is in the active stage of SLE.

[0075] The present invention provides a method for constructing a systemic lupus erythematosus activity assessment model and its application, which combines the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data, and uses a machine learning algorithm to train a high-precision systemic lupus erythematosus activity assessment model, which can efficiently, comprehensively, and accurately assess the activity of systemic lupus erythematosus, and effectively assist SLE patients to seek medical treatment in a timely manner and make correct treatment decisions.

[0076] The system for auxiliary assessment of activity of systemic lupus erythematosus provided by the present invention is described below. The system for auxiliary assessment of activity of systemic lupus erythematosus described below and the method for constructing the systemic lupus erythematosus activity assessment model described above can be referenced to each other.

[0077] like Figure 6 As shown, the present invention provides a systemic lupus erythematosus activity auxiliary assessment system, which may include:

[0078] The data receiving module is used to receive the expression level data of CD177 on the surface of neutrophils of the subject to be tested, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data sent from at least one terminal;

[0079] An auxiliary assessment module, used to obtain a systemic lupus erythematosus activity assessment result of the subject according to the systemic lupus erythematosus activity assessment model obtained by the construction method of the systemic lupus erythematosus activity assessment model described in any of the above items based on the expression level data of CD177 on the surface of neutrophils of the subject, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data of the subject;

[0080] The data output module is used to send the systemic lupus erythematosus activity assessment result of the subject to be tested to at least one terminal.

[0081] After obtaining the expression level data of CD177 on the surface of neutrophils of the subject, the titer data of anti-dsDNA antibodies, the concentration data of anti-dsDNA antibodies, the concentration data of complement C3, and the concentration data of complement C4, the medical staff can input them into the auxiliary assessment system for systemic lupus erythematosus activity, which is received by the data receiving module of the auxiliary assessment system for systemic lupus erythematosus activity, and then the auxiliary assessment module obtains the systemic lupus erythematosus activity assessment result of the subject according to the systemic lupus erythematosus activity assessment model, and then the data output module outputs the systemic lupus erythematosus activity assessment result of the subject. The subject can decide whether to seek medical treatment based on the systemic lupus erythematosus activity assessment result, and the medical staff can formulate appropriate treatment strategies for patients in the active stage of SLE based on the systemic lupus erythematosus activity assessment result.

[0082] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to perform the following steps:

[0083] Receiving the expression level data of CD177 on the surface of neutrophils of the subject to be tested, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data sent from at least one terminal;

[0084] According to the neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the subject, a systemic lupus erythematosus activity assessment model is obtained by the method for constructing a systemic lupus erythematosus activity assessment model described in any of the above items to obtain a systemic lupus erythematosus activity assessment result of the subject;

[0085] The systemic lupus erythematosus activity assessment result of the subject is sent to at least one terminal.

[0086] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0087] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can perform the following steps:

[0088] Receiving the expression level data of CD177 on the surface of neutrophils of the subject to be tested, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data sent from at least one terminal;

[0089] According to the neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the subject, a systemic lupus erythematosus activity assessment model is obtained by the method for constructing a systemic lupus erythematosus activity assessment model described in any of the above items to obtain a systemic lupus erythematosus activity assessment result of the subject;

[0090] The systemic lupus erythematosus activity assessment result of the subject is sent to at least one terminal.

[0091] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented to perform the following steps when executed by a processor:

[0092] Receiving the expression level data of CD177 on the surface of neutrophils of the subject to be tested, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data sent from at least one terminal;

[0093] According to the neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the subject, a systemic lupus erythematosus activity assessment model is obtained by the method for constructing a systemic lupus erythematosus activity assessment model described in any of the above items to obtain a systemic lupus erythematosus activity assessment result of the subject;

[0094] The systemic lupus erythematosus activity assessment result of the subject is sent to at least one terminal.

[0095] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0096] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0097] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a systemic lupus erythematosus activity assessment model, characterized in that: include: Acquire the expression level data of CD177 on the surface of neutrophils, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, wherein the target population includes patient populations at different stages of SLE; Based on the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, a systemic lupus erythematosus activity assessment model was trained through a machine learning algorithm.

2. The method for constructing a systemic lupus erythematosus activity assessment model according to claim 1, characterized in that: Patient groups at different stages of SLE include a remission patient group and / or an active patient group.

3. The method for constructing a systemic lupus erythematosus activity assessment model according to claim 1, characterized in that: The systemic lupus erythematosus activity assessment model is trained by a machine learning algorithm based on the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, including: According to the expression level data of CD177 on the surface of neutrophils of the target population, the titer data of anti-dsDNA antibodies, the concentration data of anti-dsDNA antibodies, the concentration data of complement C3, and the concentration data of complement C4, the expression level data of CD177 on the surface of neutrophils of the target population, the titer data of anti-dsDNA antibodies, the concentration data of anti-dsDNA antibodies, the concentration data of complement C3, and the concentration data of complement C4 of the target population are normalized into data of a unified dimension by using preset standards; Based on the normalized target population's neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data, a systemic lupus erythematosus activity assessment model was trained using a machine learning algorithm.

4. The method for constructing a systemic lupus erythematosus activity assessment model according to claim 3, characterized in that: According to the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data, the expression level data of CD177 on the surface of neutrophils of the target population, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data are normalized into data of a unified dimension using preset standards, including: When the expression level data of CD177 on the surface of neutrophils of an individual in the target population indicates that the expression level of CD177 on the surface of neutrophils is higher than the first preset threshold, the expression level of CD177 on the surface of neutrophils of the individual is determined to be abnormal, and the expression level data of CD177 on the surface of neutrophils is converted to the first fixed value, otherwise, it is converted to the second fixed value; When the anti-dsDNA antibody titer data of an individual in the target population indicates that its anti-dsDNA antibody-IF is positive, the anti-dsDNA antibody-IF of the individual is determined to be abnormal, and the anti-dsDNA antibody titer data is converted to a first fixed value, otherwise it is converted to a second fixed value; When the anti-dsDNA antibody concentration data of an individual in the target population indicates that the anti-dsDNA antibody-CLIA is positive, the anti-dsDNA antibody-CLIA of the individual is determined to be abnormal, and the anti-dsDNA antibody concentration data is converted to a first fixed value, otherwise it is converted to a second fixed value; When the complement C3 concentration data of an individual in the target population indicates that its complement C3 concentration is lower than the second preset threshold, the complement C3 concentration of the individual is determined to be abnormal, and the complement C3 concentration data is converted to the first fixed value, otherwise, it is converted to the second fixed value; When the complement C4 concentration data of an individual in the target population indicates that its complement C4 concentration is lower than the third preset threshold, the complement C4 concentration of the individual is determined to be abnormal, and its complement C4 concentration data is converted to the first fixed value, otherwise it is converted to the second fixed value.

5. The method for constructing a systemic lupus erythematosus activity assessment model according to claim 4, characterized in that: The systemic lupus erythematosus activity assessment model is trained by a machine learning algorithm based on the normalized neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, including: According to the normalized neutrophil surface CD177 expression level data, anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, and complement C4 concentration data of the target population, several systemic lupus erythematosus activity assessment models were trained through several machine learning algorithms; The model performances of several systemic lupus erythematosus activity assessment models were compared to obtain the final systemic lupus erythematosus activity assessment model.

6. The method for constructing a systemic lupus erythematosus activity assessment model according to claim 5, characterized in that: Several machine learning algorithms include any one or any combination of the following: logistic regression algorithm, random forest algorithm, support vector machine algorithm, decision tree algorithm; Wherein, the comparison of the model performances of several systemic lupus erythematosus activity assessment models to obtain the final systemic lupus erythematosus activity assessment model includes: The model performance of several systemic lupus erythematosus activity assessment models was compared using evaluation indicators to obtain the final systemic lupus erythematosus activity assessment model, wherein the evaluation indicators included any one of the following or any combination thereof: accuracy, precision, recall rate, Fi score, sensitivity, specificity, and AUC value.

7. The method for constructing a systemic lupus erythematosus activity assessment model according to claim 6, characterized in that: The final systemic lupus erythematosus activity assessment model is the systemic lupus erythematosus activity assessment model trained by the logistic regression algorithm, and its expression is: In the expression of the final systemic lupus erythematosus activity assessment model, dsDNAIF, dsDNACLIA, C3, C4, and CD177MFIhiNEU represent the normalized anti-dsDNA antibody titer data, anti-dsDNA antibody concentration data, complement C3 concentration data, complement C4 concentration data, and CD177MFI neutrophil surface CD177 expression level data, respectively.

8. A system for assisting in assessing the activity of systemic lupus erythematosus, characterized in that: include: The data receiving module is used to receive the expression level data of CD177 on the surface of neutrophils of the subject to be tested, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data sent from at least one terminal; An auxiliary evaluation module, used to obtain a systemic lupus erythematosus activity evaluation result of the subject according to the systemic lupus erythematosus activity evaluation model obtained by the method for constructing a systemic lupus erythematosus activity evaluation model according to any one of claims 1 to 7, based on the expression level data of CD177 on the surface of neutrophils of the subject, the anti-dsDNA antibody titer data, the anti-dsDNA antibody concentration data, the complement C3 concentration data, and the complement C4 concentration data of the subject; The data output module is used to send the systemic lupus erythematosus activity assessment result of the subject to be tested to at least one terminal.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for constructing a systemic lupus erythematosus activity assessment model according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a systemic lupus erythematosus activity assessment model as described in any one of claims 1 to 7 is implemented.

Images