Biomarker combination for diagnosing chronic endometritis and application thereof

Abstract

The invention discloses a biomarker composition for diagnosing chronic endometritis and application of the biomarker composition, and belongs to the technical field of biology. The biomarker combination comprises lymphocyte count, CD3 + T cell percentage, CD8 + T cell percentage, CD19 + B cell count, NK cell count, IL10, IgG and IgG4. According to the invention, eight biomarkers related to chronic endometritis are detected, and non-invasive detection and early diagnosis of CE (chronic endometritis) can be realized. A subject working characteristic curve AUC of a diagnosis model based on the marker is equal to 0.929, high specificity (88.9%) is achieved, early diagnosis accuracy of chronic endometritis (CE) is remarkably improved, a new method is provided for rapid diagnosis and early diagnosis of the CE, theoretical guidance is provided for personalized treatment of the CE, and the marker has a good application prospect. And a technical support is provided for deep research of a CE treatment mechanism.

Description

Technical Field

[0001] The present invention relates to the field of biotechnology, and particularly to a biomarker combination for diagnosing chronic endometritis and its application. Background Art

[0002] Chronic Endometritis (CE) is a chronic inflammatory disease characterized by endometrial stromal plasma cell infiltration, which is closely related to infertility, recurrent implantation failure and recurrent miscarriage. Epidemiological data shows that about 10%-30% of infertile women have CE, and its missed diagnosis rate is as high as 30%. The pathogenesis of CE is complex, involving bacterial infection, intrauterine microecological imbalance, immune microenvironment disorder and abnormal immune cell infiltration. Since CE lacks typical clinical symptoms, its early diagnosis is crucial for improving pregnancy outcomes.

[0003] Currently, the clinical diagnosis of chronic endometritis (CE) mainly relies on the following two techniques: histopathological examination and hysteroscopy. Histopathological examination is the gold standard, and the infiltration status of plasma cells is confirmed by detecting CD138-positive plasma cells through endometrial biopsy. Hysteroscopy can directly observe the changes in the endometrium, such as "strawberry sign" (large-area congestion in the mucosal area, with a white center point), focal congestion and endometrial micro-polyps (small masses with a diameter < 1 mm, having an obvious connective vascular axis), etc.

[0004] At present, the following key defects and deficiencies exist in the diagnostic methods for CE: 1. Risk of invasive operations: Existing diagnostic methods mainly rely on hysteroscopy and histopathology examinations. These operations not only pose a risk of damaging the endometrium but may also cause bleeding or infection. For infertile patients, invasive examination methods may also have an adverse impact on subsequent reproductive treatments. 2. Insufficient sensitivity and specificity: Although endometrial biopsy for detecting CD138 is regarded as the gold standard for diagnosing CE, since a small number of CD138+ plasma cells may also appear in the endometrium of healthy women of childbearing age, a false positive rate of 20%-30% is caused. Moreover, hysteroscopy examination depends to a certain extent on the subjective experience of the operator and there is a certain degree of uncertainty. 3. Lack of standardized threshold: Currently, the diagnosis of CE relies on the counting of CD138+ plasma cells, but the thresholds in different studies are not exactly the same. Some studies use a threshold of 1-5 cells / HPF, while some studies use a standard of 1 cell / 10HPF. In addition, inflammation may be focally distributed, and there is a risk of missed diagnosis in a single biopsy; the influence of the menstrual cycle and sampling volume also has a certain impact on the diagnostic results. In summary, a unified and standardized diagnostic standard has not been formed. 4. Absence of non-invasive detection means: Existing technologies have not been able to achieve non-invasive screening of CE through peripheral blood biomarkers, resulting in difficulty in early effective intervention for high-risk populations (such as patients undergoing in vitro fertilization embryo transfer). At the same time, the sensitivity and specificity of routine single blood tests are not sufficient to replace pathological biopsy, thus limiting the application of CE in early detection and monitoring. Summary of the Invention

[0005] The object of the present invention is to provide a biomarker combination for diagnosing chronic endometritis and its application to solve the problems existing in the above-mentioned prior art. The present invention detects 8 biomarkers related to chronic endometritis, which can achieve non-invasive detection and rapid diagnosis of CE, and avoid the damage caused by invasive surgical operations and the long diagnosis time. The area under the receiver operating characteristic curve (AUC) of the diagnostic model based on the above biomarkers is 0.929, with a relatively high specificity (88.9%), significantly improving the early diagnosis accuracy rate of CE, providing a new method for the rapid diagnosis and early diagnosis of CE, providing theoretical guidance for the personalized treatment of CE, and also providing technical support for the in-depth study of the treatment mechanism of CE.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] The present invention provides a biomarker combination for diagnosing chronic endometritis, including lymphocyte count, percentage of CD3+ T cells, percentage of CD8+ T cells, CD19+ B cell count, NK cell count, IL10, IgG, and IgG4.

[0008] The present invention also provides an application of the above biomarker combination in the preparation of a product for the early diagnosis of chronic endometritis.

[0009] Optionally, the product includes a reagent or a kit.

[0010] Furthermore, the product diagnoses chronic endometritis by detecting the content of the biomarker combination in peripheral blood.

[0011] The present invention also provides a kit for the early diagnosis of chronic endometritis, and the kit contains reagents for detecting the lymphocyte count, the percentage of CD3+ T cells, the percentage of CD8+ T cells, the CD19+ B cell count, the NK cell count, the IL10 content, the IgG content, and the IgG4 content in peripheral blood.

[0012] The present invention also provides an application of the above biomarker combination in constructing a diagnostic model for chronic endometritis.

[0013] The present invention also provides a method for constructing a diagnostic model for chronic endometritis, and the diagnostic model for chronic endometritis is constructed by using the XGBoost algorithm.

[0014] Furthermore, it includes the following steps:

[0015] Obtain the data of the lymphocyte count, the percentage of CD3+ T cells, the percentage of CD8+ T cells, the CD19+ B cell count, the NK cell count, the IL10 content, the IgG content, and the IgG4 content in the peripheral blood of patients as a data set;

[0016] Randomly divide the data set into a training set, a validation set, and a test set;

[0017] Use the training set to construct a diagnostic model based on the XGBoost algorithm; use the validation set to perform cross-validation on the diagnostic model; use the test set to evaluate the clinical applicability and diagnostic performance of the diagnostic model.

[0018] The present invention also provides a diagnostic model for chronic endometritis constructed by the above construction method.

[0019] The present invention discloses the following technical effects:

[0020] The present invention uses LASSO regression analysis to screen out 8 biomarkers related to chronic endometritis (CE). By detecting 8 biomarkers in peripheral blood (lymphocyte count, IL10, CD3+ percentage, CD8+ percentage, CD19+ B cell count, NK cell count, IgG, IgG4), non-invasive detection of CE can be achieved, avoiding the risks of endometrial injury, bleeding and infection caused by hysteroscopy or endometrial biopsy, and reducing the discomfort of patients. The detection of 8 biomarkers in the present invention can achieve early detection and diagnosis of CE, is applicable to the routine screening of asymptomatic high-risk populations (such as IVF patients), the AUC of the receiver operating characteristic curve is 0.929, with high specificity (88.9%), and can significantly improve the accuracy of early diagnosis of CE.

[0021] The present invention combines multi-dimensional immune indexes (cell subsets + inflammatory factors), uses the XGBoost machine learning algorithm to integrate data, optimizes the classification performance, outputs the CE probability based on biomarker data, and uses the SHAP interpretation model to predict the logic, which can standardize and visualize the diagnostic results, make them interpretable, provide a new method for the rapid diagnosis and early diagnosis of CE, provide theoretical guidance for the personalized treatment of CE, and also provide technical support for the in-depth study of the CE treatment mechanism. Brief Description of the Drawings

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 It is a LASSO coefficient path diagram;

[0024] Figure 2 It is a cross-validation curve of LASSO regression analysis;

[0025] Figure 3 It is the variance inflation factor (VIF) of the screened biomarkers;

[0026] Figure 4 It is the ROC curve of the training set of multiple machine learning classification models;

[0027] Figure 5 It is the calibration curve of the training set of multiple machine learning classification models;

[0028] Figure 6 It is the precision-recall curve of the training set of multiple machine learning classification models;

[0029] Figure 7 ROC curve of the validation set for the diagnostic model; where the lines of different colors represent 10-fold cross-validation;

[0030] Figure 8 ROC curve of the test set for the diagnostic model;

[0031] Figure 9 DCA curve of the test set for the diagnostic model;

[0032] Figure 10 Calibration curve of the test set for the diagnostic model;

[0033] Figure 11 SHAP ranking plot of biomarker importance;

[0034] Figure 12 SHAP dependence plot;

[0035] Figure 13 SHAP waterfall plot for personalized interpretation of the diagnostic result of patient A. Detailed implementation manners

[0036] Now, various exemplary implementation manners of the present invention will be described in detail. This detailed description should not be considered as a limitation of the present invention, but should be understood as a more detailed description of certain aspects, characteristics, and implementation schemes of the present invention.

[0037] It should be understood that the terms described in the present invention are only for describing particular implementation manners and are not used to limit the present invention. Additionally, for the numerical ranges in the present invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Any intermediate value within any stated value or stated range, as well as each smaller range between any other stated value or intermediate value within the stated range, is also included in the present invention. The upper and lower limits of these smaller ranges can be independently included or excluded from the range.

[0038] Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present invention pertains. Although the present invention only describes preferred methods and materials, any methods and materials similar or equivalent to those described herein can also be used in the implementation or testing of the present invention. All documents mentioned in this specification are incorporated by reference to disclose and describe the methods and / or materials related to the documents. In case of conflict with any incorporated document, the content of this specification shall prevail.

[0039] Without departing from the scope or spirit of the present invention, various improvements and changes can be made to the specific embodiments of the specification of the present invention, which are obvious to those skilled in the art. Other embodiments obtained from the specification of the present invention are obvious to those skilled in the art. The specification and examples of the present invention are merely exemplary.

[0040] Regarding the use of "comprising", "including", "having", "containing", etc. herein, they are all open-ended terms, meaning including but not limited to.

[0041] The technical idea of the present invention is as follows:

[0042] ①Collect the clinical diagnosis results and laboratory test data of the patients; the diagnosis result is whether chronic endometritis has occurred.

[0043] The laboratory test data includes 77 test parameters, specifically including:

[0044] Complete blood count (20 items): white blood cell count (WBC), red blood cell count (RBC), hemoglobin (Hb), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), platelet count (PLT), red blood cell distribution width coefficient of variation (RDW-CV), mean platelet volume (MPV), platelet distribution width (PDW), percentage and absolute count of white blood cell classification (lymphocytes, neutrophils, eosinophils, basophils, monocytes);

[0045] Serum infection markers and biochemical analysis (27 items): troponin T, ferritin, procalcitonin, C-reactive protein, alanine aminotransferase, total protein, albumin, total bilirubin, alkaline phosphatase, aspartate aminotransferase, γ-glutamyl transferase, cholinesterase, lipase, amylase, glucose, uric acid, creatine kinase isoenzyme MB, creatine kinase, lactate dehydrogenase, urea, creatinine, potassium, sodium, chloride, calcium, magnesium, total carbon dioxide;

[0046] Immunological analysis (17 items): immunoglobulins IgG, IgA, IgM and their 4 IgG subclasses, lymphocyte subsets: percentage and absolute count of CD3+ T cells, CD4+ T helper cells, CD8+ T cells, CD19+ B cells, natural killer (NK) cells;

[0047] Cytokine profile (12 items) interleukin (IL-1β, IL-2, IL-4, IL-5, IL-6, IL-8, IL-10, IL-12P70, IL-17), interferon (IFN-α, IFN-γ) and tumor necrosis factor-α (TNF-α);

[0048] Coagulation index D-dimer.

[0049] ② Adopt a standardized data processing method to normalize the test results.

[0050] ③ Through LASSO regression, from blood routine indexes, blood biochemical indexes, coagulation indexes, lymphocyte subset indexes, cytokine indexes and other indexes, screen out key biomarkers including lymphocyte count, percentage of CD3+ T cells, percentage of CD8+ T cells, count of CD19+ B cells, count of NK cells, IL-10, IgG and IgG4.

[0051] ④ Use the XGBoost algorithm to construct a prediction model. According to the model score, judge the probability that the patient has CE.

[0052] Example 1

[0053] 1. Collection of clinical patient samples

[0054] The patients participating in the enrollment screening were infertile patients who received the first in vitro fertilization (IVF) treatment at Peking University Third Hospital from 2018 to 2022. All patients were screened through strict inclusion and exclusion criteria.

[0055] The inclusion criteria included: (1) infertile patients who underwent hysteroscopy and endometrial biopsy; (2) endometrial biopsy specimens were subjected to standard histopathological examinations of CD138 and CD38 by immunohistochemistry (IHC) staining; (3) complete laboratory records, including complete blood count, biochemical parameters, coagulation function, immunoglobulins and IgG subclasses, lymphocyte subsets and cytokine profiles.

[0056] The exclusion criteria included: (1) a history of recurrent miscarriage or severe endocrine diseases (such as thyroid dysfunction); (2) endometriosis; (3) uterine malformations, intrauterine adhesions, submucous myomas; (4) chromosomal abnormalities; (5) abnormal preoperative vaginal secretion examinations; (6) polycystic ovary syndrome (PCOS); (7) abnormal uterine bleeding (AUB); (8) patients lacking any of the above information or key laboratory index data.

[0057] After screening, a total of 542 participants were finally included. The recruited patients were diagnosed with chronic endometritis (CE). The diagnostic criteria were: (1) histopathological examination: clear plasma cell infiltration; (2) clinical symptoms: including infertility and recurrent miscarriage; (3) microbial detection: used as an auxiliary tool, including PCR and culture methods. Finally, it was determined that there were 290 patients with chronic endometritis (CE) and 252 non-CE patients among the patients.

[0058] 2. Laboratory test data

[0059] Complete blood count (20 items): white blood cell count (WBC), red blood cell count (RBC), hemoglobin (Hb), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), mean corpuscular hemoglobin concentration (MCHC), platelet count (PLT), red blood cell distribution width coefficient of variation (RDW-CV), mean platelet volume (MPV), platelet distribution width (PDW), percentage and absolute count of white blood cell differential (lymphocytes, neutrophils, eosinophils, basophils, monocytes);

[0060] Serum infection markers and biochemical analysis (27 items): troponin T, ferritin, procalcitonin, C-reactive protein, alanine aminotransferase, total protein, albumin, total bilirubin, alkaline phosphatase, aspartate aminotransferase, γ-glutamyl transferase, cholinesterase, lipase, amylase, glucose, uric acid, creatine kinase isoenzyme MB, creatine kinase, lactate dehydrogenase, urea, creatinine, potassium, sodium, chloride, calcium, magnesium, total carbon dioxide;

[0061] Immunological analysis (17 items): immunoglobulins IgG, IgA, IgM and their 4 IgG subclasses, lymphocyte subsets: percentage and absolute count of CD3+ T cells, CD4+ T helper cells, CD8+ T cells, CD19+ B cells, natural killer (NK) cells;

[0062] Cytokine profile (12 items): interleukins (IL-1β, IL-2, IL-4, IL-5, IL-6, IL-8, IL-10, IL-12P70, IL-17), interferons (IFN-α, IFN-γ) and tumor necrosis factor-α (TNF-α);

[0063] Coagulation index D-dimer.

[0064] 3. LASSO regression feature selection:

[0065] Parameter setting: Variable selection uses LASSO regression analysis (λ = 0.03042).

[0066] Screening results: As Figure 1 and Figure 2 shown, 8 key markers are screened out from the candidate variables (laboratory test data), including immune cell parameters: lymphocyte count, percentage of CD3+ T cells, percentage of CD8+ T cells, CD19+ B cell count, NK cell count; cytokines: IL10, IgG, IgG4.

[0067] The detection results of 8 markers in clinical CE patients and non-CE patients are shown in Table 1. Each marker is higher in CE patients than in non-CE patients.

[0068] Table 1 Detection results of 8 markers in CE patients and non-CE patients

[0069]

[0070] 4. Multicollinearity of key markers

[0071] To evaluate the potential multicollinearity among the selected parameters, the variance inflation factor (VIF) was calculated for the 8 key markers screened out. The results are as Figure 3 shown. All VIF values are less than 5, indicating a low degree of multicollinearity, which means the variables are not highly correlated and can be used separately for further analysis.

[0072] 5. Machine learning model construction

[0073] 5.1 Screening the best model from multiple models

[0074] 5.1.1 Data division: The data of 542 patients were randomly divided into a training set (n = 325), a validation set (n = 108), and a test set (n = 109) at a ratio of 6:2:2.

[0075] 5.1.2 Comprehensive analysis was performed using multiple machine learning (ML) classification models. These include Extreme Gradient Boosting (XGBoost), Logistic Regression (logistic), Light Gradient Boosting Machine (LightGBM), Random Forest, Gaussian Naive Bayes (GNB), Multi-Layer Perceptron (MLP), Support Vector Machine (SVN), and k-Nearest Neighbor (KNN).

[0076] The ML models were trained using the training set and then their performance was evaluated using the validation set. To evaluate the predictive ability, various performance metrics were calculated, including AUC, accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and Kappa. In addition, calibration curves, Decision Curve Analysis (DCA), and Precision-Recall (PR) curves were evaluated to further verify the performance of the models.

[0077] The results are as Figures 4 - 6 shown in and Table 2 - 3. The evaluation results of multiple machine learning models revealed different performance trends. XGBoost had the highest area under the AUC curve in both the training set (0.998) and the validation set (0.934), making it the best choice for further developing and validating the prediction model.

[0078] Table 2 Performance metrics of each machine learning classification model based on the training set

[0079]

[0080]

[0081] Table 3 Performance Metrics of Each Machine Learning Classification Model Based on the Validation Set

[0082]

[0083] 5.2 Construction and Validation of the Diagnostic Model

[0084] An Extreme Gradient Boosting (XGBoost) algorithm was used to establish a diagnostic model for chronic endometritis (CE), and grid search was used to determine the optimal parameters: learning rate 0.1, maximum depth 6, and number of trees 200.

[0085] Through 10-fold cross-validation of the validation set, the results are as Figure 7 shown. The model showed robust performance metrics, and the AUC of the validation set could reach 0.994 (0.989 - 0.999).

[0086] The AUC of the test set reached 0.929 (95% CI: 0.885 - 0.974), sensitivity 0.762, specificity 0.889, positive predictive value 0.906( Figure 8 ). Decision curve analysis (DCA) further verified the clinical applicability of the model, showing stable net clinical benefits within a wide range of threshold probabilities (10% - 90%). In the intermediate threshold range (30% - 70%), the net benefit rate significantly exceeded the "all-treatment" and "no-treatment" strategies, consolidating its role in optimizing clinical decisions( Figure 9 ). The Brier score of the calibration curve for the test set was 0.12, and the calibration curve showed a high consistency between the predicted probability and the true probability( Figure 10 ).

[0087] The above results indicate that the model demonstrated excellent performance in differentiating patients from non-patients. It has strong diagnostic validity, with a sensitivity of 0.762 and a specificity of 0.889, reflecting its dual ability to accurately identify true positive cases while minimizing false positive misclassifications. The high positive predictive value (0.906) further emphasizes its clinical application in the context of high-risk screening, where reliable identification of positive cases is crucial.

[0088] 6. Interpretability of the Diagnostic Model

[0089] The XGBoost diagnostic model constructed in Step 5 can be subjected to interpretability analysis through the SHAP (Shapley Additive Explanations) method. The specific steps are as follows:

[0090] 1. SHAP value calculation: Based on the training set data, the SHAP algorithm is used to quantify the contribution of each biomarker to the model output and generate a feature contribution matrix for individual samples.

[0091] 2. Feature Importance Ranking: Summarize the SHAP values of all samples and sort them in descending order of absolute contribution to determine the priority of key biomarkers. Figure 11 As shown in the figure, the top-ranked features such as interleukin 10 (IL-10), CD3+ T cells, IgG4, and NK count have the most significant impact on the model output.

[0092] 3. Feature influence direction analysis: Through SHAP dependency graph ( Figure 12 ) shows the correlation direction between each eigenvalue and the prediction result. The red mark indicates a positive contribution, such as an increase in the proportion of CD3+ T cells increases the risk of CE, and the blue mark indicates a negative contribution.

[0093] 4. Individualized interpretation application: For a single sample (e.g., patient A), generate a SHAP waterfall chart ( Figure 13 ), intuitively displaying the cumulative impact of each feature on the prediction results and supporting clinical decision-making.

[0094] Making the model transparent through the SHAP method not only improves clinical credibility, but also guides personalized treatment based on the type of characteristic abnormalities, which is significantly better than traditional machine learning models that only rely on probabilistic output.

[0095] The embodiments described above are merely descriptions of preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by persons skilled in the art should fall within the scope of protection defined by the claims of the present invention.

Claims

1. A biomarker combination for diagnosing chronic endometritis, characterized in that, Including lymphocyte count, percentage of CD3+ T cells, percentage of CD8+ T cells, CD19+ B cell count, NK cell count, IL10, IgG, and IgG4.

2. Use of the biomarker combination according to claim 1 in the preparation of a product for the early diagnosis of chronic endometritis.

3. The application according to claim 2, characterized in that, The product includes a reagent or a kit.

4. The application according to claim 2, wherein The product diagnoses chronic endometritis by detecting the content of the biomarker combination in peripheral blood.

5. A kit for early diagnosis of chronic endometritis, characterized in that, The kit contains reagents for detecting the lymphocyte count, percentage of CD3+ T cells, percentage of CD8+ T cells, CD19+ B cell count, NK cell count, and the contents of IL10, IgG, and IgG4 in peripheral blood.

6. Use of the biomarker combination according to claim 1 in the construction of a diagnostic model for chronic endometritis.

7. A method for constructing a diagnostic model for chronic endometritis, characterized in that, The diagnostic model for chronic endometritis is constructed using the XGBoost algorithm.

8. The construction method according to claim 7, characterized in that, Including the following steps: Obtain data on the lymphocyte count, percentage of CD3+ T cells, percentage of CD8+ T cells, CD19+ B cell count, NK cell count, IL10 content, IgG content, and IgG4 content in the peripheral blood of patients as a data set; Randomly divide the data set into a training set, a validation set, and a test set; Using the training set, construct a diagnostic model based on the XGBoost algorithm; use the validation set to perform cross-validation on the diagnostic model; use the test set to evaluate the clinical applicability and diagnostic performance of the diagnostic model.

9. A diagnostic model for chronic endometritis constructed by the construction method according to claim 7 or 8.

Images