Diagnostic markers for sjogren's syndrome, diagnostic devices and uses thereof

Abstract

The application discloses a diagnostic marker for Sjogren's syndrome, a diagnostic device and application thereof, and relates to the technical field of Sjogren's syndrome diagnosis. The diagnostic marker for Sjogren's syndrome is selected from the markers in (1) or (2): (1) acetylcarnitine (C2); (2) C2, and at least one of the following markers: globulin concentration (G) in serum, ratio of free carnitine to acetylcarnitine (C0 / C2), decanoyl carnitine (C10), decatrienoyl carnitine (C10:3), propionyl carnitine / acetylcarnitine (C3 / C2), isovaleryl carnitine / butyryl carnitine (C5 / C4) and octanoyl carnitine / hexadecanoyl carnitine (C8 / C16). The diagnostic model constructed by single C2 has very high diagnostic efficiency for Sjogren's syndrome, and the combined use of multiple markers can further improve the diagnostic efficiency for Sjogren's syndrome.

Description

Technical Field

[0001] This invention relates to the field of diagnostic technology for Sjögren's syndrome, and more specifically, to diagnostic markers, diagnostic devices, and their applications for Sjögren's syndrome. Background Technology

[0002] The diagnosis of Sjögren's syndrome (SS) is primarily based on clinical symptoms of dryness, serological autoantibodies, and glandular tissue pathology. This diagnostic standard is consistent with the 2016 classification criteria for Sjögren's syndrome provided by the American College of Rheumatology / European League Against Rheumatism (ACR / EULAR). Currently, the classification criteria for SS emphasize glandular immune infiltration and positive anti-SSA / Ro serology; positive saliva biopsy or anti-SSA / Ro serology is mandatory. However, these criteria do not cover all symptoms of SS and are extremely limited in differentiating cases of SS with atypical clinical presentations or in their early stages. Studies show that approximately 70%-80% of patients with primary Sjögren's syndrome are positive for anti-SSA antibodies, while the remaining 20%-30% may be completely negative. SS patients may not present with typical symptoms in the early stages, and many are only diagnosed after significant dryness symptoms and marked lymphocytic infiltration of the salivary glands appear, which undoubtedly hinders timely treatment.

[0003] Therefore, early diagnosis is crucial for the effective treatment of SS.

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

[0005] The purpose of this invention is to provide diagnostic markers, diagnostic devices and their applications for Sjögren's syndrome, thereby achieving accurate, sensitive and specific diagnosis of Sjögren's syndrome.

[0006] This invention is implemented as follows: In a first aspect, the present invention provides the application of a reagent for detecting diagnostic markers of Sjögren's syndrome in the preparation of diagnostic products for Sjögren's syndrome, wherein the diagnostic markers of Sjögren's syndrome are selected from markers of (1) or (2): (1) Acetylcarnitine (C2); (2) C2, and at least one of the following markers: serum globulin concentration (G), free carnitine to acetylcarnitine ratio (C0 / C2), decanoylcarnitine (C10), decanoylcarnitine (C10:3), propionylcarnitine / acetylcarnitine (C3 / C2), isovalerylcarnitine / butyrylcarnitine (C5 / C4) and caprylcarnitine / hexadecanoylcarnitine (C8 / C16).

[0007] Secondly, the present invention provides a method for constructing a diagnostic model for Sjögren's syndrome, which includes the following steps: i: Obtain feature data representing the diagnostic biomarkers for Sjögren's syndrome in the training samples; the diagnostic biomarkers for Sjögren's syndrome are the aforementioned diagnostic biomarkers for Sjögren's syndrome; ii: Utilize feature data to construct a diagnostic model for Sjögren's syndrome through machine learning models.

[0008] Thirdly, the present invention provides a diagnostic device for Sjögren's syndrome, which includes: an input module, a control module, and an output module; The input module is configured to: acquire feature data of biomarkers in the subject sample, wherein the biomarkers are selected from the above-mentioned diagnostic biomarkers for Sjögren's syndrome; The control module includes an assessment module configured to generate a risk prediction result for Sjögren's syndrome of the subject based on the characteristic data of diagnostic markers for Sjögren's syndrome contained in the subject's sample. The output module is configured to output the subject's Sjögren's syndrome risk prediction results.

[0009] Fourthly, the present invention provides a diagnostic device for Sjögren's syndrome, the device including a processor and a memory, the memory storing a set of executable program instructions, the set of executable program instructions being loaded and executed by the processor to implement a method for diagnosing Sjögren's syndrome, the method for diagnosing Sjögren's syndrome including: The characteristic data of biomarkers in the subject's sample were obtained. The biomarkers were selected from the above-mentioned diagnostic biomarkers for Sjögren's syndrome. Based on the characteristic data of the diagnostic biomarkers for Sjögren's syndrome contained in the subject's sample, the risk prediction results for the subject's Sjögren's syndrome were generated.

[0010] The present invention has the following beneficial effects: This invention identifies several carnitines and clinical markers with significantly different expression levels in the blood of individuals with Sjögren's syndrome and healthy individuals. After screening, seven carnitines and one blood globulin were found to show significant differences in expression levels between these two groups. Diagnostic models were established based on these eight biomarkers, with the model based on acetylcarnitine exhibiting extremely high diagnostic efficacy. Furthermore, the combined use of multiple biomarkers can further improve diagnostic efficacy. Therefore, the diagnostic biomarkers for Sjögren's syndrome provided by this invention have promising applications in the diagnosis of Sjögren's syndrome.

[0011] The invention facilitates the early detection and treatment of Sjögren's syndrome, enabling timely treatment for SS patients. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 A graph showing the differences in the levels of eight biomarkers in the serum of SS and healthy individuals; Figure 2 The results of the Shapley Additive Explanation (SHAP) model for eight indicators are shown in the figure. Figure 3 ROC curves of six V8 models built based on six classifier algorithms (a), ROC curve of Comparative Example 1 (b), and ROC curve comparison of the constructed AdaBoost model (c) were plotted using the test set. Figure 4 To plot the ROC curve of a single marker based on the AdaBoost model using the test set; Figure 5 Plot ROC curves for various combinations of markers based on the AdaBoost model using the test set. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Where specific conditions are not specified in the embodiments, conventional conditions or conditions recommended by the manufacturer shall apply. Reagents or instruments whose manufacturers are not specified are all conventional products that can be purchased commercially.

[0015] Definition of noun The term "marker" broadly refers to any detectable compound or cell present in or derived from a sample, such as a protein, peptide, proteoglycan, glycoprotein, lipoprotein, cell, or any of the foregoing substances, that is differentiating molecule or differentiating fragment. For example, the detection of or binding to a specific antibody can indicate the presence of a specific antigen (e.g., a protein) in a sample. Here, a differentiating molecule or fragment is a molecule or fragment that, upon detection, indicates the presence or abundance of the aforementioned identified compound or cell. Markers can, for example, be isolated from the sample, measured directly in the sample, or detected or determined in the sample. Markers can, for example, be functional, partially functional, or non-functional. Markers may also be synonymous with "biomarker."

[0016] The term "sample" refers to a biological specimen obtained from or derived from an individual for a purpose. The source of the biological specimen can be a fresh, frozen, and / or preserved organ or tissue sample or solid tissue derived from a biopsy or primer; blood or any blood component. The term "sample" includes biological samples that have been manipulated in any way after acquisition, such as by reagent treatment, stabilization, enrichment for certain components (e.g., proteins or polynucleotides), or embedding in a semi-solid or solid matrix for sectioning purposes. In this invention, the sample is particularly a peripheral blood sample, a whole blood sample, or a serum sample.

[0017] The term "subject" as used in this article can be understood as anyone involved in the diagnosis of Sjögren's syndrome. A subject can be a patient in a clinical setting.

[0018] The term "predetermined threshold" refers to a parameter used to compare a marker or combination of markers in a subject's sample with a predetermined threshold when diagnosing disease risk, and outputs the subject's disease risk or disease course based on the comparison result.

[0019] In a first aspect, the present invention provides the application of a reagent for detecting diagnostic markers of Sjögren's syndrome (SS) in the preparation of diagnostic products for Sjögren's syndrome, wherein the diagnostic markers for Sjögren's syndrome are selected from the markers of (1) or (2): (1) Acetylcarnitine (C2); (2) C2, and at least one of the following markers: serum globulin concentration (G), free carnitine to acetylcarnitine ratio (C0 / C2), decanoylcarnitine (C10), decanoylcarnitine (C10:3), propionylcarnitine / acetylcarnitine (C3 / C2), isovalerylcarnitine / butyrylcarnitine (C5 / C4) and caprylcarnitine / hexadecanoylcarnitine (C8 / C16).

[0020] This invention uses three methods (Spearman, RFE-SVC, and MI) to cross-screen 55 carnitines, 21 carnitine ratios, and dozens of clinical indicators to identify the top 30 indicators with the greatest differences between Sjögren's syndrome patients and healthy individuals. Further, potential biomarkers for SS and the control group were extracted from these 30 indicators for modeling. Eight biomarkers [serum globulin concentration (G), acetylcarnitine (C2), decanoylcarnitine (C10), decanoylcarnitine (C10:3), free carnitine / acetylcarnitine (C0 / C2), propionylcarnitine / acetylcarnitine (C3 / C2), isovalerylcarnitine / butyrylcarnitine (C5 / C4), caprylylcarnitine / hexadecanoylcarnitine (C8 / C16)] were selected as candidate biomarkers to establish a diagnostic model for SS (V8). In the Shapley Additive Explanation (SHAP) model of these eight indicators, C0 / C2 contributed the most, followed by C2, C10, G (serum globulin concentration), C10:3, C5 / C4, C3 / C2, and C8 / C16. The effectiveness of the diagnostic model based on the eight candidate indicators was examined using six classifier algorithms. It was found that C2 has extremely high diagnostic efficacy for Sjögren's syndrome, and combinations of C2 with any of the other seven markers showed good diagnostic results for Sjögren's syndrome.

[0021] The invention facilitates the early detection and treatment of Sjögren's syndrome, enabling timely treatment for SS patients.

[0022] In a preferred embodiment of the present invention, the diagnostic markers for Sjögren's syndrome are selected from any combination of the following: (1) C0 / C2 and C2; (2) C2 and C10; (3) C2 and G; (4) C2 and C10:3; (5) C2 and C5 / C4; (6) C2 and C3 / C2; (7) C2 and C8 / C16; (8) C0 / C2, C2 and C10; (9) C0 / C2, C2 and G; (10) C0 / C2, C2 and C10:3; (11) C0 / C2, C2 and C5 / C4; (12) C0 / C2, C2 and C3 / C2; (13) C0 / C2, C2 and C8 / C16; (14) C0 / C2, C2, C10 and G; (15) C0 / C2, C2, C10 and C10:3; (16) C0 / C2, C2, C10 and C5 / C4; (17) C0 / C2, C2, C10 and C3 / C2; (18) C0 / C2, C2, C10 and C8 / C16; (19) C0 / C2, C2, C10, G and C10:3; (20) C0 / C2, C2, C10, G and C5 / C4; (21) C0 / C2, C2, C10, G and C3 / C2; (22) C0 / C2, C2, C10, G and C8 / C16; (23) C0 / C2, C2, C10, G, C10:3 and C5 / C4; (24) C0 / C2, C2, C10, G, C10:3 and C3 / C2; (25) C0 / C2, C2, C10, G, C10:3 and C8 / C16; (26) C0 / C2, C2, C10, G, C10:3, C5 / C4 and C3 / C2; (27) C0 / C2, C2, C10, G, C10:3, C5 / C4 and C8 / C16; (28) C0 / C2, C2, C10, C10:3, C5 / C4, C3 / C2 and C8 / C16; (29) C0 / C2, C2, C10, G, C10:3, C5 / C4, C3 / C2 and C8 / C16.

[0023] Diagnostic markers for Sjögren's syndrome are selected from any combination of the following: (1) C0 / C2 and C2; (2) C0 / C2, C2 and C10; (3) C0 / C2, C2, C10 and G; (4) C0 / C2, C2, C10, G and C10:3; (5) C0 / C2, C2, C10, G, C10:3 and C5 / C4; (6) C0 / C2, C2, C10, G, C10:3, C5 / C4 and C3 / C2; (7) C0 / C2, C2, C10, C10:3, C5 / C4, C3 / C2 and C8 / C16; (8) C0 / C2, C2, C10, G, C10:3, C5 / C4, C3 / C2 and C8 / C16.

[0024] The above combination of biomarkers has extremely high diagnostic accuracy for Sjögren's syndrome.

[0025] In a preferred embodiment of the present invention, the diagnostic product for Sjögren's syndrome is selected from: reagent kits, chips, and detection devices.

[0026] In a preferred embodiment of the present invention, the diagnostic markers for Sjögren's syndrome are diagnostic markers for Sjögren's syndrome in whole blood or serum samples.

[0027] In a preferred embodiment of the present invention, the combination of eight biomarkers has better diagnostic efficacy. The model constructed with the eight biomarkers was validated using a test set, and ROC curves were plotted. The AUC value, sensitivity, specificity, and accuracy were >0.940, >86.16%, >94.75%, and >93.0%, respectively.

[0028] Secondly, the present invention provides a method for constructing a diagnostic model for Sjögren's syndrome, which includes the following steps: i: Obtain feature data representing the diagnostic biomarkers for Sjögren's syndrome in the training samples; the diagnostic biomarkers for Sjögren's syndrome are the aforementioned diagnostic biomarkers for Sjögren's syndrome; ii: Utilize feature data to construct a diagnostic model for Sjögren's syndrome through machine learning models.

[0029] In a preferred embodiment of the present invention, the machine learning model is selected from at least one of the following: support vector machine, random forest, logistic regression, K-nearest neighbors, Gaussian Bayes, Naive Bayes, AdaBoost, XGBoost, and DT decision tree.

[0030] After multi-model validation, the random forest, decision tree, logistic regression, Gaussian Bayes, support vector machine and AdaBoost models constructed based on the diagnostic biomarkers for Sjögren's syndrome provided in this invention all have extremely high diagnostic efficacy, with extremely high diagnostic accuracy, specificity and sensitivity.

[0031] In particular, random forest and AdaBoost models have relatively higher diagnostic efficiency.

[0032] In a preferred embodiment of the present invention, the characteristic data of the diagnostic biomarkers for Sjögren's syndrome in the representative training samples are obtained by performing liquid chromatography-tandem mass spectrometry analysis on the representative training samples to obtain the concentration and / or concentration ratio of the diagnostic biomarkers for Sjögren's syndrome in the representative training samples.

[0033] Thirdly, the present invention provides a diagnostic device for Sjögren's syndrome, which includes: an input module, a control module, and an output module; The input module is configured to: acquire feature data of biomarkers in the subject sample, wherein the biomarkers are selected from the above-mentioned diagnostic biomarkers for Sjögren's syndrome; The control module includes an assessment module configured to generate a risk prediction result for Sjögren's syndrome of the subject based on the characteristic data of diagnostic markers for Sjögren's syndrome contained in the subject's sample. The output module is configured to output the subject's Sjögren's syndrome risk prediction results.

[0034] In a preferred embodiment of the present invention, the evaluation module is configured to: input the characteristic data of the diagnostic markers of Sjögren's syndrome contained in the subject's sample into a pre-established diagnostic model for Sjögren's syndrome, obtain a risk prediction value for Sjögren's syndrome, compare the risk prediction value for Sjögren's syndrome with a predetermined threshold, and generate a risk prediction result for the subject's Sjögren's syndrome based on the comparison result.

[0035] For example, a logistic regression model can be established to obtain the cut-off value of the model. For example, if the cut-off value is 0.50 (i.e., a predetermined threshold), the sample is diagnosed as having Sjögren's syndrome if the predicted risk value is >0.50, and as not having Sjögren's syndrome if it is <0.50 (healthy control).

[0036] Fourthly, the present invention provides a diagnostic device for Sjögren's syndrome, the device comprising a processor and a memory, the memory storing a set of executable program instructions, the set of executable program instructions being loaded and executed by the processor to implement a method for diagnosing Sjögren's syndrome, the method for diagnosing Sjögren's syndrome comprising: The characteristic data of biomarkers in the subject's sample were obtained. The biomarkers were selected from the above-mentioned diagnostic biomarkers for Sjögren's syndrome. Based on the characteristic data of the diagnostic biomarkers for Sjögren's syndrome contained in the subject's sample, the risk prediction results for the subject's Sjögren's syndrome were generated.

[0037] The features and performance of the present invention will be further described in detail below with reference to embodiments.

[0038] Example 1 This embodiment involves the screening of diagnostic biomarkers.

[0039] 1. Materials and Methods (1) Participants Patients included in this study visited Xijing Hospital (Xi'an, China) between June 1, 2022 and November 2, 2023, and were divided into two groups: SS (n=108) and control group (n=103). All SS patients met the 2016 ACR / EULAR criteria. SS patients included those who had not received any steroid, immunosuppressive, or antibiotic treatment in the past three months. Participants in the control group were healthy and without disease. Exclusion criteria were: (1) receiving or having a history of immunosuppressive therapy, and (2) receiving or having a history of hormone therapy.

[0040] (2) Blood preparation After fasting overnight, venous blood is collected by an experienced nurse and processed according to the requirements of carnitine, biochemistry, immunology and routine blood tests.

[0041] (3) Data collection All tests were performed in the clinical laboratory of Xijing Hospital, and the data was uploaded and stored in the LIS system. Patient basic information was collected and entered by trained personnel. All test results underwent quality control before, during, and after the tests to ensure quality and accuracy.

[0042] (4) LC-MS / MS materials and equipment The ratios of 55 carnitines and 21 carnitines were analyzed by HPLC-MS / MS.

[0043] The 55 carnitines include free carnitine (C0), acetylcarnitine (C2), propionylcarnitine (C3), butyrylcarnitine (C4), isovalerylcarnitine (C5), hexanoylcarnitine (C6), heptaylcarnitine (C7), caprylylcarnitine (C8), nonanoylcarnitine (C9), decanoylcarnitine (C10), dodecylcarnitine (C12), tetradecylcarnitine (C14), hexadecylcarnitine (C16), heptadecanylcarnitine (C17), octadecylcarnitine (C18), eicosylcarnitine (C20), dodecylcarnitine (C22), and tetradecylcarnitine. Carbonyl carnitine (C24), pentacarnitine (C25), hexacarnitine (C26), methyl crotonyl carnitine (C5:1), octenyl carnitine (C8:1), decenoyl carnitine (C10:1), decadienoyl carnitine (C10:2), dectrienoyl carnitine (C10:3), dodecenoyl carnitine (C12:1), tetradecenoyl carnitine (C14:1), tetradecadienoyl carnitine (C14:2), hexadecenoyl carnitine (C16:1), octadecenoyl carnitine (C18:1), octadecadienoyl carnitine (C18:2), eicosenoylcarnitine (C20:1), eicosadienoylcarnitine (C20:2), eicostrienoylcarnitine (C20:3), malonylcarnitine (C3DC), methylmalonylcarnitine (C4DC), glutarylcarnitine (C5DC), adipicoylcarnitine (C6DC), octanoylcarnitine (C8DC), sebacylcarnitine (C10DC), dodecanoylcarnitine (C12DC), tetradecanoylcarnitine (C14DC), hexadecanoylcarnitine (C16DC), octadecanoylcarnitine ( (C18DC), eicosadecanoylcarnitine (C20DC), hydroxybutyrylcarnitine (C4-OH), hydroxyisovaleroylcarnitine (C5-OH), hydroxyhexanoylcarnitine (C6-OH), hydroxydodecanoylcarnitine (C12-OH), hydroxytetradecanoylcarnitine (C14-OH), hydroxyhexadecanoylcarnitine (C16:1-OH), hydroxyhexadecanoylcarnitine (C16-OH), hydroxyoctadecanoylcarnitine (C18:1-OH), hydroxyoctadecanoylcarnitine (C18-OH), hydroxyeicosadecanoylcarnitine (C20-OH).

[0044] The corresponding ratios for the 21 carnitines include: C0 / C2, C0 / C16, C3 / C0, C3 / C2, C3 / C16, C4 / C3, C5 / C4, C5DC / C8, C5DC / C16, C8 / C2, C8 / C3, C8 / C10, C8 / C12, C8 / C16, C14:1 / C16, C16OH / C16, C24 / C22, C25 / C22, C26 / C20, C26 / C22, and C26 / C24.

[0045] The internal standards included free carnitine (d9-C0), acetylcarnitine (d3-C2), propionylcarnitine (d3-C3), butyrylcarnitine (d3-C4), isovalerylcarnitine (d9-C5), caprylcarnitine (d3-C8), tetradecylcarnitine (d9-C14), and hexadecylcarnitine (d3-C16). The above internal standards were diluted with methanol to prepare working solutions and stored at 4 °C.

[0046] (5) HPLC-MS / MS sample pretreatment 50 μL of serum was dropped onto blank blood collection filter paper and allowed to permeate before detecting 76 carnitine parameters. A 3.5 mm diameter disc of dried serum filter paper was accurately cut and extracted with 100 μL of extraction reagent at 25°C for 15 min. All extracts were transferred to a new tube and dried under nitrogen. A derivatization reagent was prepared using n-butanol and acetyl chloride at a volume ratio of 9:1. Then, 60 μL of the derivatization reagent was added to the dried sample and reacted at 65°C for 20 min. The final derivatized solution was dried under nitrogen and then dissolved in 100 μL of acetonitrile. This solution was used as the detection solution for mass spectrometry analysis.

[0047] (6) Mass spectrometry analysis 100% acetonitrile was used as the mobile phase for HPLC-MS / MS. The HPLC instrument was specifically an HPLC 1100 (Agilent, Waldbronn, Germany), and the optimized parameters for HPLC detection are shown in Table 1. The injection volume for mass spectrometry (3200 QTRAP, AB Sciex, Darmstadt, Germany) was 20 μL. In positive ion mode of the electrospray ionization source, precursor ion scanning (85 Da, 210 Da-600.00 Da) was used, with an inlet voltage of 15.27 V-27.48 V and a collision energy of 35.00 V-45.00 V. The optimized parameters for the mass spectrometer are shown in Table 2.

[0048] Table 1: HPLC detection conditions for 55% carnitine

[0049] Table 2: Optimized parameters for QTRAP mass spectrometry detection of 55% carnitine

[0050] (7) Statistical analysis Mass spectrometry data were analyzed using Analyst (version 1.6.2) and ChemView software (version 1.6.1; ABSciex, Darmstadt, Germany). Quantitative data were analyzed using SPSS (version 23.0; IBM, Armonk, NY, USA), with independent t-tests and p-values ​​(p<0.05) used for comparisons. Quantitative data are expressed as mean ± standard deviation. Data visualization was performed using GraphPad Prism (version 5; GraphPad Software, San Diego, CA, USA) and R software (version 3.6.2; R Statistical Computing Project, p<0.05).

[0051] 2. Establishment of the diagnostic model To build an effective diagnostic model, Spearman, RFE-SVC, and MI methods were used to screen for the 30 indicators with the highest contribution values, and common indicators were considered as potential indicators for model building. To enhance and validate the effectiveness of the SS diagnostic model, six machine learning classification algorithms (random forest, decision tree, logistic regression, Gaussian Bayes, support vector machine, and AdaBoost) were used to construct the model. The sensitivity, specificity, accuracy, positive predictive value, negative predictive value, area under the curve (AUC), and ROC curve of these models were evaluated. To ensure the stability of all algorithms, 5-fold cross-validation was performed on the data from step 1, with 5 runs used for training and 5 runs used for testing.

[0052] Patient characteristics results show: By analyzing participants' basic information, including height, weight, blood pressure, and lifestyle habits, as well as the expression levels and differences of all indicators, there were no significant differences in basic information between the SS group and the control group. Specifically, the SS group and the control group were similar in age, sex, and BMI, with no significant differences; there were also no significant differences in blood type, smoking, and alcohol consumption.

[0053] Performance evaluation of candidate metrics based on classification algorithms: Based on the differences in the expression levels of various carnitine and clinical indicators, three methods (Spearman, RFE-SVC, and MI) were used to cross-screen the top 30 indicators with the greatest differences, and potential biomarkers for SS and control groups were extracted for modeling.

[0054] Eight biomarkers showing the greatest reproducibility across Spearman, RFE-SVC, and MI methods [serum globulin concentration (G), acetylcarnitine (C2), decanoylcarnitine (C10), decanoylcarnitine (C10:3), free carnitine / acetylcarnitine (C0 / C2), propionylcarnitine / acetylcarnitine (C3 / C2), isovalerylcarnitine / butyrylcarnitine (C5 / C4), caprylcarnitine / hexadecanoylcarnitine (C8 / C16)] were selected as candidate biomarkers. The levels of these eight biomarkers in SS and healthy individuals were referenced. Figure 1 As shown in the figure. The results showed that there were significant differences in these eight biomarkers between SS and healthy individuals (p<0.0001).

[0055] Eight-indicator Shapley Additive Explanation (SHAP) model reference Figure 2 As shown, C0 / C2 contributes the most to the model, followed by C2, C10, G (serum globulin concentration), C10:3, C5 / C4, C3 / C2, and C8 / C16.

[0056] Furthermore, six classifier algorithms were used to build a joint diagnostic model (V8) for eight biomarkers, and the effectiveness of the diagnostic model was tested. The ROC, sensitivity, specificity, and accuracy of the V8 model obtained in the training set were >0.968, 89.51%, 96.74%, and 94.19%, respectively (Table 3).

[0057] Table 3 shows the statistical results of the combined diagnostic model using eight biomarkers.

[0058] ROC curves were plotted for six V8 models built based on six different classifier algorithms using the test set. AUC values, sensitivity, specificity, and accuracy were calculated. Figure 3 Figure a shows that the AUC values ​​in the test set are all >0.940, the sensitivity is all >86.16%, the specificity is all >94.75%, and the accuracy is all >93.0%.

[0059] Example 2 This embodiment provides a diagnostic method for Sjögren's syndrome, which uses a combination of 7 biomarkers (V7) to construct a logistic regression model for Sjögren's syndrome.

[0060] (1) Mass spectrometry was performed on 42 serum samples according to the method in Example 1, and C0 / C2, C2, C10, C10:3, C5 / C4, C3 / C2 and C8 / C16 results were obtained respectively.

[0061] (2) Then substitute the parameters from step (1) into the logistic regression model of the 7 biomarker combinations and output the prediction results.

[0062] Sjögren's syndrome is diagnosed based on the following criteria.

[0063] The cut-off value of the diagnostic model of the combination of 7 biomarkers for Sjögren's syndrome was 0.50. A value >0.50 was used to diagnose Sjögren's syndrome (SS), and a value <0.50 was used to diagnose non-SS (healthy control).

[0064] The results in Table 4 show that the combination of the seven biomarkers has extremely high diagnostic accuracy and consistency.

[0065] Table 4 shows the diagnostic efficacy statistics of the logistic regression model for Sjögren's syndrome constructed using a combination of 7 biomarkers (V7).

[0066] Comparative Example 1 ROC curves of six anti-SSA (immunoblotting) models built based on six classifier algorithms were plotted using the test set of Example 1.

[0067] Results reference Figure 3 As shown in Figure b, the results indicate that the AUC value of the ROC curves plotted for the six anti-SSA models established by the six classifier algorithms was only 0.797, far lower than the effect of the combined diagnosis of eight biomarkers in Example 1. The sensitivity, specificity, and accuracy were 59.98%, 100%, and 85.92%, respectively.

[0068] Based on the AdaBoost model with eight biomarker combinations established above and the anti-SSA AdaBoost model of Comparative Example 1, diagnostic efficacy was tested using a test set sample. The results are referenced... Figure 3 As shown in c, the results show that, under the same type of AdaBoost model, the combination of 8 biomarkers provided by this invention has significantly better diagnostic efficacy for Sjögren's syndrome.

[0069] Experimental Example 1 The diagnostic efficacy of a single biomarker was evaluated using the test set samples from Example 1. AdaBoost models were constructed separately, and the diagnostic results are shown in [link to example]. Figure 4 The cutoff value for the diagnostic models is 0.5.

[0070] The AUC value of the ROC curve of the C0 / C2 model was 0.932, with sensitivity, specificity, and accuracy of 82.23%, 90.32%, and 87.31%, respectively.

[0071] The AUC value of the ROC curve of the C2 model was 0.973, and the sensitivity, specificity and accuracy were 94.12%, 92.44% and 92.98%, respectively.

[0072] The AUC value of the ROC curve of the C3 / C2 model was 0.882, with sensitivity, specificity, and accuracy of 78.19%, 86.95%, and 83.78%, respectively.

[0073] The AUC value of the ROC curve of the C5 / C4 model was 0.842, with sensitivity, specificity, and accuracy of 64.34%, 85.91%, and 78.21%, respectively.

[0074] The AUC value of the ROC curve of the C8 / C16 model was 0.906, with sensitivity, specificity, and accuracy of 74.39%, 85.95%, and 81.66%, respectively.

[0075] The AUC value of the ROC curve of the C10 model was 0.928, and the sensitivity, specificity and accuracy were 78.31%, 89.18% and 85.18%, respectively.

[0076] The AUC value of the ROC curve of the C10:3 model was 0.786, with sensitivity, specificity, and accuracy of 69.98%, 82.54%, and 78.18%, respectively.

[0077] The AUC value of the ROC curve of the G model was 0.836, with sensitivity, specificity, and accuracy of 68.01%, 80.50%, and 76.05%, respectively.

[0078] Experiment Example 2 The diagnostic efficacy of the two biomarker combinations was evaluated using the test set samples from Example 1. An AdaBoost model was constructed, and the diagnostic efficacy was referenced... Figure 5 As shown.

[0079] The AUC value of the ROC curve for the C2+C0 / C2 model was 0.976, with sensitivity, specificity, and accuracy of 94.12%, 92.44%, and 92.98%, respectively. (See ROC curve diagram for reference.) Figure 5 As shown.

[0080] Experimental Example 3 The diagnostic efficacy of the three biomarker combinations was evaluated based on the test set samples from Example 1. An AdaBoost model was constructed, and the diagnostic efficacy was compared with... Figure 5 As shown.

[0081] The AUC value of the ROC curve for the C2+C10+C0 / C2 model was 0.992, with sensitivity, specificity, and accuracy of 96.08%, 96.74%, and 96.48%, respectively. (See ROC curve diagram for reference.) Figure 5 As shown.

[0082] Experiment Example 4 The diagnostic efficacy of four biomarker combinations was evaluated based on the test set samples from Example 1. An AdaBoost model was constructed, and the diagnostic efficacy was compared with... Figure 5 As shown.

[0083] The AUC value of the ROC curve for the G+C2+C10+C0 / C2 model was 0.986, with sensitivity, specificity, and accuracy of 96.08%, 93.51%, and 94.34%, respectively. (See ROC curve diagram for reference.) Figure 5 As shown.

[0084] Experimental Example 5 The diagnostic efficacy of five biomarker combinations was evaluated based on the test set samples from Example 1. An AdaBoost model was constructed, and the diagnostic efficacy was compared with... Figure 5 As shown.

[0085] The AUC value of the ROC curve for the G+C2+C10+C10:3+C0 / C2 model was 0.992, with sensitivity, specificity, and accuracy of 96.08%, 96.74%, and 96.50%, respectively. (See ROC curve for reference.) Figure 5 As shown.

[0086] Experimental Example 6 The diagnostic efficacy of six biomarker combinations was evaluated based on the test set samples from Example 1. An AdaBoost model was constructed, and the diagnostic efficacy was compared with... Figure 5 As shown.

[0087] The AUC value of the ROC curve for the G+C2+C10+C10:3+C0 / C2+C5 / C4 model was 0.987, with sensitivity, specificity, and accuracy of 90.20%, 94.62%, and 92.97%, respectively. (See ROC curve for reference.) Figure 5 As shown.

[0088] Experimental Example 7 The diagnostic efficacy of seven biomarker combinations was evaluated based on the test set samples from Example 1. An AdaBoost model was constructed, and the diagnostic efficacy was compared with... Figure 5 As shown.

[0089] The AUC value of the ROC curve for the G+C2+C10+C10:3+C0 / C2+C3 / C2+C5 / C4 model was 0.984, with sensitivity, specificity, and accuracy of 92.16%, 96.77%, and 95.08%, respectively. (See ROC curve for reference.) Figure 5 As shown.

[0090] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. The application of a reagent for detecting diagnostic markers of Sjögren's syndrome in the preparation of diagnostic products for Sjögren's syndrome, characterized in that, The diagnostic markers for Sjögren's syndrome are selected from markers in (1) or (2): (1) Acetylcarnitine (C2); (2) C2, and at least one of the following markers: serum globulin concentration (G), free carnitine to acetylcarnitine ratio (C0 / C2), decanoylcarnitine (C10), decanoylcarnitine (C10:3), propionylcarnitine / acetylcarnitine (C3 / C2), isovalerylcarnitine / butyrylcarnitine (C5 / C4) and caprylcarnitine / hexadecanoylcarnitine (C8 / C16).

2. The application according to claim 1, characterized in that, The diagnostic markers for Sjögren's syndrome are selected from any combination of the following: (1) C0 / C2 and C2; (2) C2 and C10; (3) C2 and G; (4) C2 and C10:3; (5) C2 and C5 / C4; (6) C2 and C3 / C2; (7) C2 and C8 / C16; (8) C0 / C2, C2 and C10; (9) C0 / C2, C2 and G; (10) C0 / C2, C2 and C10:3; (11) C0 / C2, C2 and C5 / C4; (12) C0 / C2, C2 and C3 / C2; (13) C0 / C2, C2 and C8 / C16; (14) C0 / C2, C2, C10 and G; (15) C0 / C2, C2, C10 and C10:3; (16) C0 / C2, C2, C10 and C5 / C4; (17) C0 / C2, C2, C10 and C3 / C2; (18) C0 / C2, C2, C10 and C8 / C16; (19) C0 / C2, C2, C10, G and C10:3; (20) C0 / C2, C2, C10, G and C5 / C4; (21) C0 / C2, C2, C10, G and C3 / C2; (22) C0 / C2, C2, C10, G and C8 / C16; (23) C0 / C2, C2, C10, G, C10:3 and C5 / C4; (24) C0 / C2, C2, C10, G, C10:3 and C3 / C2; (25) C0 / C2, C2, C10, G, C10:3 and C8 / C16; (26) C0 / C2, C2, C10, G, C10:3, C5 / C4 and C3 / C2; (27) C0 / C2, C2, C10, G, C10:3, C5 / C4 and C8 / C16; (28) C0 / C2, C2, C10, C10:3, C5 / C4, C3 / C2 and C8 / C16; (29) C0 / C2, C2, C10, G, C10:3, C5 / C4, C3 / C2 and C8 / C16.

3. The application according to claim 1, characterized in that, The diagnostic markers for Sjögren's syndrome are selected from any combination of the following: (1) C0 / C2 and C2; (2) C0 / C2, C2 and C10; (3) C0 / C2, C2, C10 and G; (4) C0 / C2, C2, C10, G and C10:3; (5) C0 / C2, C2, C10, G, C10:3 and C5 / C4; (6) C0 / C2, C2, C10, G, C10:3, C5 / C4 and C3 / C2; (7) C0 / C2, C2, C10, C10:3, C5 / C4, C3 / C2 and C8 / C16; (8) C0 / C2, C2, C10, G, C10:3, C5 / C4, C3 / C2 and C8 / C16.

4. The application according to claim 1, characterized in that, The diagnostic products for Sjögren's syndrome are selected from: reagent kits, chips, and detection devices.

5. The application according to claim 1, characterized in that, The diagnostic markers for Sjögren's syndrome are those found in whole blood or serum samples.

6. A method for constructing a diagnostic model for Sjögren's syndrome, characterized in that, It includes the following steps: i: Obtain feature data representing the diagnostic biomarkers for Sjögren's syndrome in the training samples; the diagnostic biomarkers for Sjögren's syndrome are any one of claims 1-5; ii: Using the aforementioned feature data, a diagnostic model for Sjögren's syndrome is constructed through a machine learning model.

7. The method for constructing a diagnostic model for Sjögren's syndrome according to claim 6, characterized in that, The machine learning model is selected from at least one of the following: Support Vector Machine, Random Forest, Logistic Regression, K Nearest Neighbors, Gaussian Bayes, Naive Bayes, AdaBoost, XGBoost, and DT Decision Tree; The characteristic data of the diagnostic biomarkers for Sjögren's syndrome in the representative training samples were obtained by performing liquid chromatography-tandem mass spectrometry analysis on the representative training samples to obtain the concentration and / or concentration ratio of the diagnostic biomarkers for Sjögren's syndrome in the representative training samples.

8. A diagnostic device for Sjögren's syndrome, characterized in that, It includes: Input module, control module, and output module; The input module is configured to: acquire feature data of biomarkers in subject samples, wherein the biomarkers are selected from the diagnostic biomarkers for Sjögren's syndrome according to any one of claims 1-5; The control module includes an evaluation module configured to generate a risk prediction result for Sjögren's syndrome of the subject based on the characteristic data of diagnostic markers for Sjögren's syndrome contained in the subject's sample. The output module is configured to output the subject's Sjögren's syndrome risk prediction results.

9. The diagnostic device for Sjögren's syndrome according to claim 8, characterized in that, The assessment module is configured to: input the characteristic data of the diagnostic markers of Sjögren's syndrome contained in the subject's sample into a pre-established diagnostic model for Sjögren's syndrome, obtain a risk prediction value for Sjögren's syndrome, compare the risk prediction value for Sjögren's syndrome with a predetermined threshold, and generate a risk prediction result for the subject's Sjögren's syndrome based on the comparison result.

10. A diagnostic device for Sjögren's syndrome, characterized in that, The device includes a processor and a memory, the memory storing a set of executable program instructions, which are loaded and executed by the processor to implement a method for diagnosing Sjögren's syndrome, the method for diagnosing Sjögren's syndrome including: The characteristic data of biomarkers in the subject's sample are obtained, wherein the biomarkers are selected from the diagnostic biomarkers for Sjögren's syndrome according to any one of claims 1-5; based on the characteristic data of the diagnostic biomarkers for Sjögren's syndrome contained in the subject's sample, the risk prediction result of Sjögren's syndrome for the subject is generated.

Images