Application of a protein marker composition in radiation pneumonitis

Abstract

The present application relates to the field of biomedical technology, and in particular to an application of a protein marker composition in radiation pneumonitis; the application includes using a protein marker composition above an expression level as a biomarker for radiation pneumonitis, the protein marker composition including angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand, and chemokine 20; by performing cytokine chip detection and screening on peripheral blood specimens of multiple lung cancer patients undergoing chest radiotherapy before radiotherapy, it was found that high expression of angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20 is a risk factor for radiation pneumonitis, and combining these cytokines can improve the prediction accuracy of radiation pneumonitis. Therefore, the above-mentioned cytokine combination may become a powerful early prediction tool for radiation pneumonitis in clinical practice.

Description

Technical Field

[0001] The present application relates to the field of biomedical technology, and in particular to an application of a protein labeling composition in radiation pneumonia. Background Art

[0002] Lung cancer ranks second in incidence among all malignant tumors worldwide. Currently, one of the main treatments for lung cancer is radiotherapy. The goal of radiotherapy is to maximize tumor cell destruction while minimizing damage to surrounding normal tissue. Although advances in radiotherapy equipment and technology have improved radiation protection for normal tissue, toxicity to normal tissue within the irradiation field cannot be completely avoided. As a radiation-sensitive organ, the lung is susceptible to radiation damage during radiotherapy, leading to radiation pneumonitis. Radiation pneumonitis not only impacts patients' quality of life and lifespan but also limits the irradiated tumor volume and radiation dose, thereby limiting the effectiveness of radiotherapy equipment in tumor control. Therefore, early detection of radiation pneumonitis is crucial.

[0003] Currently, radiation therapy mostly uses dose control parameters such as MLD and V20 to reduce the occurrence of normal tissue radiation pneumonitis. However, this method has certain limitations, and in clinical practice, it has been found that some patients do not develop normal tissue radiation pneumonitis, while others develop radiation pneumonitis, but the severity varies, even with the same radiation therapy strategy. Current studies have shown that peripheral blood biomarkers have predictive value in various diseases. Among them, peripheral blood protein markers have attracted much attention due to their ease and feasibility of detection. Peripheral blood protein markers have been used in various diseases, but currently no peripheral blood protein markers have been used for the early prediction of radiation pneumonitis. Therefore, if the levels of peripheral blood protein markers can be used to achieve early prediction of radiation pneumonitis, it can help clinicians assess the risks of radiotherapy early and formulate the best treatment strategy, which can improve the patient's quality of life while ensuring tumor control. Summary of the Invention

[0004] The present application provides an application of a protein marker composition in radiation pneumonitis to fill the gap in the prior art of peripheral blood protein markers in the early prediction of radiation pneumonitis.

[0005] In a first aspect, the present application provides a use of a protein marker composition as a biomarker for radiation pneumonitis, wherein the use comprises using a protein marker composition having a higher expression level than normal as a biomarker for radiation pneumonitis, wherein the protein marker composition comprises at least one of the following:

[0006] Angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand, and chemokine 20.

[0007] Optionally, the chemokine CXC ligand includes at least one of the following:

[0008] Chemokine CXC ligand 10, chemokine CXC ligand 13 and chemokine CXC ligand 14.

[0009] Optionally, the area under the curve of the receiver operating characteristic curve of the protein marker composition is ≥0.6.

[0010] In a second aspect, the present application provides a detection kit for radiation pneumonia, which includes a reagent for detecting the expression level of a protein marker composition, wherein the protein marker composition includes angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand and chemokine 20.

[0011] Optionally, the chemokine CXC ligand includes at least one of the following:

[0012] Chemokine CXC ligand 10, chemokine CXC ligand 13 and chemokine CXC ligand 14.

[0013] In a third aspect, the present application provides an application of a protein marker composition in constructing a prediction model for predicting radiation pneumonitis, wherein the protein marker composition and the radiotherapy dose parameter V20 are used as covariates to construct the prediction model, wherein the protein marker composition includes at least one of the following:

[0014] Angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20.

[0015] Optionally, the step of constructing the prediction model includes:

[0016] Logistic regression analysis was performed using the preset factor parameters as covariates and the occurrence of grade 2 or above radiation pneumonitis as the dependent variable to establish a regression model and obtain a prediction model;

[0017] The preset factor parameters include at least one of the following:

[0018] The expression levels of the angiopoietin-like protein 4, the growth differentiation factor 15, the chemokine CXC ligand 10, the chemokine CXC ligand 13, the chemokine CXC ligand 14, and the chemokine 20, and the radiotherapy dose parameter V20.

[0019] Optionally, the prediction model is:

[0020] Linear prediction value = (-26.48725) + 0.11788*[V20] + 0.68878*[CXCL13] + 0.23726*[CCL20] + 0.30182*[GD F-15] + 0.48689*[CXCL14] + 0.21408*[CXCL10] + 1.09337*[ANGPTL4],

[0021] Wherein, [V20] is the radiotherapy dose parameter V20;

[0022] [CXCL13] is the expression level parameter of the chemokine CXC ligand 13;

[0023] [CCL20] is the expression level parameter of the chemokine 20;

[0024] [GDF-15] is the expression level parameter of the growth differentiation factor 15;

[0025] [CXCL14] is the expression level parameter of the chemokine CXC ligand 14;

[0026] [CXCL10] is the expression level parameter of the chemokine CXC ligand 10;

[0027] [ANGPTL4] is the expression level parameter of angiopoietin-like protein 4.

[0028] Optionally, the prediction probability of the prediction model is:

[0029] p=exp(lp) / [1+exp(lp)],

[0030] Wherein, lp is the linear prediction value.

[0031] Optionally, the area under the curve of the receiver operating characteristic curve of the prediction model is ≥0.7;

[0032] The Brill score of the prediction model is 0.15-0.16.

[0033] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0034] The present application provides an example of a protein marker composition for use as a biomarker for radiation pneumonitis. By performing cytokine chip detection and screening on peripheral blood specimens of multiple lung cancer patients undergoing chest radiotherapy before radiotherapy, it was found that high expression of angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20 before radiotherapy was a risk factor for radiation pneumonitis. Therefore, the occurrence of radiation pneumonitis can be predicted at an early stage. Any combination of these cytokines can improve the prediction accuracy of radiation pneumonitis. At the same time, the predictive value of this cytokine combination has been verified in multiple scenarios. Therefore, the above-mentioned cytokine combination may become a powerful predictive tool for radiation pneumonitis in clinical practice. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0036] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] Figure 1 A graph showing the results of a Logistic regression analysis of cytokine expression levels in the plasma of multiple lung cancer patients provided in the examples of this application;

[0038] Figure 2 A schematic diagram of the receiver operating characteristic curves of cytokine expression levels in plasma of multiple lung cancer patients provided in the examples of the present application;

[0039] Figure 3 A schematic diagram of a receiver operating characteristic curve of the prediction model provided in the embodiments of the present application;

[0040] Figure 4 A schematic diagram of a calibration curve for the prediction model provided in an embodiment of the present application;

[0041] Figure 5 A schematic diagram of a receiver operating characteristic curve during the verification of the prediction model provided in an embodiment of the present application;

[0042] Figure 6 A schematic diagram of a calibration curve during the verification of a prediction model provided in an embodiment of the present application;

[0043] Figure 7 A schematic diagram of the steps for constructing the prediction model provided in the embodiments of the present application. DETAILED DESCRIPTION

[0044] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0045] Unless otherwise specified, all raw materials, reagents, instruments and equipment used in this application can be purchased from the market or prepared by existing methods.

[0046] like Figure 2 As shown, the present embodiment provides an application of a protein marker composition as a biomarker for radiation-induced pneumonia, wherein the application includes using the protein marker composition above the expression level as a biomarker for radiation-induced pneumonia, wherein the protein marker composition includes at least one of the following:

[0047] Angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand, and chemokine 20.

[0048] In some optional embodiments, the chemokine CXC ligand comprises at least one of the following:

[0049] Chemokine CXC ligand 10, chemokine CXC ligand 13 and chemokine CXC ligand 14.

[0050] In the examples of the present application, by refining the specific types of chemokine CXC ligands, the types of chemokine CXC ligands that are highly expressed due to radiation pneumonitis can be further clarified, thereby clarifying the specific chemokine CXC ligands that serve as biomarkers for radiation pneumonitis.

[0051] In some optional embodiments, the area under the curve of the receiver operating characteristic curve of the protein marker composition is ≥0.6.

[0052] In the examples of the present application, the receiver operating characteristic curve (ROC) is a tool used to evaluate the performance of a classifier at different thresholds. The closer the area under the ROC curve (AUC) is to 1, the more accurate the classification result. When the AUC is in the range of 0.5 to 1, it indicates that these classification results have a certain correlation. Therefore, by defining the specific area under the receiver operating characteristic curve of the protein marker composition, it can be shown that high levels of expression of angiopoietin-like protein 4 (ANGPTL4), growth differentiation factor 15 (GDF-15), chemokine CXC ligand 10 (CXCL10), chemokine CXC ligand 13 (CXCL13), chemokine CXC ligand 14 (CXCL14), and chemokine 20 (CCL20) are associated with radiation pneumonitis. Therefore, it is shown that high levels of expression of these cytokines can serve as risk factors for radiation pneumonitis, that is, high levels of expression of these cytokines can serve as biomarkers for radiation pneumonitis.

[0053] Based on a general inventive concept, embodiments of the present application provide a detection kit for radiation pneumonitis, the detection kit comprising a reagent for detecting the expression level of a protein marker composition, wherein the protein marker composition comprises at least one of the following:

[0054] Angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand, and chemokine 20.

[0055] The detection kit is implemented based on the application of the above-mentioned protein marker composition as a biomarker for radiation-induced pneumonia. The specific principles of the application of the protein marker composition as a biomarker for radiation-induced pneumonia can be referred to the above-mentioned embodiments. Since the detection kit adopts part or all of the technical solutions of the above-mentioned embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above-mentioned embodiments, which will not be described in detail here.

[0056] In some optional embodiments, the chemokine CXC ligand comprises at least one of the following:

[0057] Chemokine CXC ligand 10, chemokine CXC ligand 13 and chemokine CXC ligand 14.

[0058] Based on a general inventive concept, an embodiment of the present application provides an application of a protein marker composition in constructing a prediction model for predicting radiation pneumonitis, wherein the protein marker composition and a radiotherapy dose parameter V20 are used as covariates to construct the prediction model, wherein the protein marker composition includes angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20.

[0059] The application of the protein marker composition in constructing a prediction model for predicting radiation pneumonitis is achieved based on the application of the above-mentioned protein marker composition as a biomarker for radiation pneumonitis. The specific principles of the application of the protein marker composition as a biomarker for radiation pneumonitis can be referred to the above-mentioned embodiments. Since the application of the protein marker composition in constructing a prediction model for predicting radiation pneumonitis adopts part or all of the technical solutions of the above-mentioned embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above-mentioned embodiments, which will not be described in detail here.

[0060] like Figure 7 As shown, in some optional embodiments, the step of constructing the prediction model includes:

[0061] S1. Using the pre-set factor parameters as covariates and the occurrence of grade 2 or higher radiation pneumonitis as the dependent variable, logistic regression analysis was performed to establish a regression model and obtain a prediction model;

[0062] The preset factor parameters include at least one of the following:

[0063] The expression levels of the angiopoietin-like protein 4, the growth differentiation factor 15, the chemokine CXC ligand 10, the chemokine CXC ligand 13, the chemokine CXC ligand 14, and the chemokine 20, and the radiotherapy dose parameter V20.

[0064] In an embodiment of the present application, by using the above-mentioned cytokine combined with the radiotherapy dose parameter V20 as a covariate and the corresponding occurrence of grade 2 or above radiation pneumonitis as the dependent variable, the occurrence of radiation pneumonitis can be predicted by the expression levels of angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20 and the radiotherapy dose parameter V20.

[0065] It should be noted that the statistical steps for the occurrence of grade 2 and above radiation pneumonitis include:

[0066] First, the occurrence of respiratory symptoms and chest CT images of lung cancer patients were recorded, and then the grade of radiation pneumonitis of the patients was evaluated according to CTCAE4.0. There are 5 grades in total, among which grade 2 and above radiation pneumonitis is symptomatic radiation pneumonitis, which will affect the patient's life and require intervention.

[0067] In some optional embodiments, the prediction model is:

[0068] Linear prediction value = (-26.48725) + 0.11788*[V20] + 0.68878*[CXCL13] + 0.23726*[CCL20] + 0.30182*[GD F-15] + 0.48689*[CXCL14] + 0.21408*[CXCL10] + 1.09337*[ANGPTL4],

[0069] Wherein, [V20] is the radiotherapy dose parameter V20;

[0070] [CXCL13] is the expression level parameter of the chemokine CXC ligand 13;

[0071] [CCL20] is the expression level parameter of the chemokine 20;

[0072] [GDF-15] is the expression level parameter of the growth differentiation factor 15;

[0073] [CXCL14] is the expression level parameter of the chemokine CXC ligand 14;

[0074] [CXCL10] is the expression level parameter of the chemokine CXC ligand 10;

[0075] [ANGPTL4] is the expression level parameter of angiopoietin-like protein 4.

[0076] In the embodiments of the present application, by limiting the specific prediction model formula, it can be clarified that there is a linear relationship between the expression levels of angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20 and the radiotherapy dose parameter V20 and grade 2 or above radiation pneumonitis, that is, the possible probability of grade 2 or above radiation pneumonitis can be determined by these cytokines and the radiotherapy dose parameter V20.

[0077] In some optional embodiments, the prediction probability of the prediction model is:

[0078] p=exp(lp) / [1+exp(lp)],

[0079] Wherein, lp is the linear prediction value.

[0080] In the embodiment of the present application, the prediction probability of the prediction model is limited, and the probability of radiation pneumonitis occurring in lung cancer patients can be calculated by linear prediction value.

[0081] In some optional embodiments, the area under the curve of the receiver operating characteristic curve of the prediction model is ≥0.7;

[0082] The Brill score of the prediction model is 0.15-0.16.

[0083] In the embodiment of the present application, since the area under the curve is within the range of 0.7 to 0.9, it indicates that the prediction model has a certain degree of accuracy. By limiting the specific area under the curve of the receiver operating characteristic curve of the prediction model, it is shown that the prediction model can effectively reflect the possible probability of radiation pneumonitis of grade 2 or above, thereby better distinguishing patients with radiation pneumonitis.

[0084] Since the Brier score is a tool for evaluating the overall performance and calibration of a model, the closer it is to 0, the better the model performance and the more consistent the predicted value is with the actual value. Therefore, when the Brier score is less than 0.25, it means that the model has a certain predictive value, which suggests that the predicted probability of the prediction model is highly consistent with the actual probability of occurrence, indicating that the model can relatively accurately predict the occurrence of grade 2 and above radiation pneumonitis.

[0085] The present application will be further described below in conjunction with specific examples. It should be understood that these examples are intended to illustrate the present application only and are not intended to limit the scope of the present application. The experimental methods in the following examples where specific conditions are not specified are generally measured according to industry standards. If there are no corresponding industry standards, then the methods are carried out according to general international standards, conventional conditions, or the conditions recommended by the manufacturer.

[0086] Example 1

[0087] Step 1: Collect peripheral blood samples from lung cancer patients before radiotherapy and perform protein chip testing:

[0088] In a study of 144 lung cancer patients enrolled in Tongji Hospital affiliated with Tongji Medical College of Huazhong University of Science and Technology, it was found that ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, and CCL20 can be used as early predictive indicators of radiation pneumonitis:

[0089] Peripheral blood samples were collected from 144 lung cancer patients before they received chest radiotherapy. The blood samples were then centrifuged at 2500 rpm / min at 4°C for 20 minutes to separate the upper plasma, which was then stored at -80°C.

[0090] Patients were followed up regularly, and the occurrence of respiratory symptoms and chest CT images were recorded. The grade of radiation pneumonitis was assessed according to CTCAE4.0, which has 5 grades. Grade 2 and above radiation pneumonitis is symptomatic radiation pneumonitis, which affects the patient's life and requires intervention.

[0091] The Luminex cytokine chip was used to detect the patient's plasma samples, and the expression level of cytokines in each patient's plasma was calculated. Then, a logistic regression analysis was performed. The results were as follows: Figure 1 As shown, and the ROC curve is drawn, the results are as follows Figure 2 As shown by Figure 1 and Figure 2 As shown in the results, it was found that ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14 and CCL20 were risk factors for radiation pneumonitis, and patients with high expression of these cytokines were more likely to develop grade 2 or above radiation pneumonitis after radiotherapy.

[0092] Step 2: Combine ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, CCL20, and V20 to establish a prediction model:

[0093] The combination of ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, CCL20 and V20 can better predict the occurrence of radiation pneumonitis:

[0094] Radiotherapy dose is one of the influencing factors of radiation pneumonitis. Multiple studies have shown that the radiotherapy dose parameter V20 (the proportion of lung volume irradiated with a dose of 20 Gy or more to the total lung volume) can predict the occurrence of radiation pneumonitis. Using plasma ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, and CCL20 expression levels and V20 as covariates, and the occurrence of grade 2 or higher radiation pneumonitis as the dependent variable, a regression model was established in a cohort of 144 lung cancer patients undergoing radiotherapy at Tongji Hospital, affiliated with Huazhong University of Science and Technology. The prediction model formula was obtained:

[0095] Linear prediction value (lp) = (-26.48725) + 0.11788*[V20] + 0.68878*[CXCL13] + 0.23726*[CCL20] + 0.30182*[GDF-15] + 0.48689*[CXCL14] + 0.21408*[CXCL10] + 1.09337*[ANGPTL4],

[0096] Wherein, [V20] is the radiotherapy dose parameter V20;

[0097] [CXCL13] is the expression level parameter of the chemokine CXC ligand 13;

[0098] [CCL20] is the expression level parameter of the chemokine 20;

[0099] [GDF-15] is the expression level parameter of the growth differentiation factor 15;

[0100] [CXCL14] is the expression level parameter of the chemokine CXC ligand 14;

[0101] [CXCL10] is the expression level parameter of the chemokine CXC ligand 10;

[0102] [ANGPTL4] is the expression level parameter of angiopoietin-like protein 4;

[0103] The predicted probability is then converted using the formula p=exp(lp) / (1+exp(lp)).

[0104] By substituting the values ​​of the above cytokines and V20 into the formula of the prediction model, the probability of radiation pneumonitis in the patient can be calculated.

[0105] like Figure 3 As shown in the figure, the area under the ROC curve of the prediction model is 0.788, indicating that the model can better distinguish patients with radiation pneumonia.

[0106] like Figure 4 As shown in the figure, the Brier score of the prediction model is 0.157, and the calibration curve shows that the predicted probability is highly consistent with the actual probability of occurrence, indicating that the model can accurately predict the occurrence of radiation pneumonitis.

[0107] Compared with a single indicator, the combination of cytokines and V20 can improve the prediction accuracy of radiation pneumonitis.

[0108] Step 3: Validate the predictive value of the prediction model combining ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, CCL20, and V20 in other centers:

[0109] The predictive value of the above model was verified in a cohort of 91 lung cancer radiotherapy patients from Hubei Cancer Hospital and Jingjiang People's Hospital. Figure 5 As shown in , the area under the ROC curve is 0.687. Figure 6 As mentioned above, the Brier score was 0.202, indicating that in other centers, the combination of ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, CCL20 and V20 can still accurately predict the occurrence of radiation pneumonitis. The combination of these cytokines is a more robust predictive tool for radiation pneumonitis.

[0110] The above-mentioned cytokines are made into test kits, and clinically, peripheral blood can be drawn from patients before radiotherapy to detect the levels of the above-mentioned cytokines using the test kits. If the levels are high, the patient's chest radiotherapy dose can be appropriately reduced when formulating the radiotherapy plan to avoid serious symptoms in the patient; conversely, if the levels are low, the radiotherapy dose can be appropriately increased to strengthen local control of the tumor.

[0111] Step 4: Any combination of ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, and CCL20 was used to verify its predictive value:

[0112] ANGPTL4, GDF-15, CXCL10, CXCL13, CXCL14, and CCL20 were randomly combined, and regression models were established based on their expression levels. The area under the ROC curve (AUC) of each combination model was calculated. The results are shown in Table 1.

[0113] Table 1 Combination models formed by various protein marker combinations and corresponding areas under the ROC curves

[0114]

[0115]

[0116]

[0117]

[0118] As shown in Table 1, any combination of two, three, four, five, and six cytokine combinations in the protein marker composition have predictive value for radiation pneumonitis.

[0119] In summary, the application of a protein marker composition provided in the examples of the present application as a biomarker for radiation pneumonitis, through screening of peripheral blood samples from multiple lung cancer patients, found that high expression of angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20 is a risk factor for radiation pneumonitis, and therefore the occurrence of radiation pneumonitis can be predicted. Combining these cytokines can improve the prediction accuracy of radiation pneumonitis, and make this cytokine combination a powerful predictive tool for radiation pneumonitis in the clinic. It can be used for early prediction and screening of radiation pneumonitis in patients undergoing chest radiotherapy for lung cancer before radiotherapy, thereby facilitating the implementation of precise radiotherapy and personalized treatment of lung cancer.

[0120] Various embodiments of the present application may be presented in the form of a range; it should be understood that the description in the form of a range is only for convenience and brevity and should not be understood as a hard limitation on the scope of the present application; therefore, the range description should be considered to have specifically disclosed all possible sub-ranges and single numbers within the range. For example, the description of a range from 1 to 6 should be considered to have specifically disclosed sub-ranges such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as single numbers within the range, such as 1, 2, 3, 4, 5 and 6, which applies regardless of the range. In addition, whenever a numerical range is indicated herein, it is meant to include any cited number (fractional or integer) within the indicated range.

[0121] In this application, unless otherwise specified, the directional words used, such as "upper" and "lower", refer specifically to the directions of the drawings in the accompanying drawings. In addition, in the description of the present application specification, the terms "including", "comprising", etc. mean "including but not limited to". In this article, relational terms such as "first" and "second" are merely used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. In this article, "and / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. Wherein A and B can be singular or plural. In this article, "at least one" refers to one or more, and "plurality" refers to two or more. "At least one", "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c", or "at least one of a, b and c", can both mean: a, b, c, ab (i.e., a and b), ac, bc, or abc, where a, b, c can be single or multiple.

[0122] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. Use of a protein marker composition in constructing a prediction model for predicting radiation pneumonitis, characterized in that: A prediction model is constructed using the protein marker composition and the radiotherapy dose parameter V20 as covariates, wherein the protein marker composition includes at least one of the following: angiopoietin-like protein 4, growth differentiation factor 15, chemokine CXC ligand 10, chemokine CXC ligand 13, chemokine CXC ligand 14, and chemokine 20; The steps of constructing the prediction model include: Logistic regression analysis was performed using the preset factor parameters as covariates and the occurrence of grade 2 or above radiation pneumonitis as the dependent variable to establish a regression model and obtain a prediction model; The preset factor parameters include at least one of the following: the expression levels of the angiopoietin-like protein 4, the growth differentiation factor 15, the chemokine CXC ligand 10, the chemokine CXC ligand 13, the chemokine CXC ligand 14, and the chemokine 20, and the radiotherapy dose parameter V20; The prediction model is: Linear prediction value = (-26.48725)+0.11788*[V20]+0.68878*[CXCL13]+0.23726*[CCL20]+0.30182*[GDF-15]+0.48689*[CXCL14]+0.21408*[CXCL10]+1.09337*[ANGPTL4], where [V20] is the radiotherapy dose parameter V20; [CXCL13] is the expression level parameter of the chemokine CXC ligand 13; [CCL20] is the expression level parameter of the chemokine 20; [GDF-15] is the expression level parameter of the growth differentiation factor 15; [CXCL14] is the expression level parameter of the chemokine CXC ligand 14; [CXCL10] is the expression level parameter of the chemokine CXC ligand 10; [ANGPTL4] is the expression level parameter of angiopoietin-like protein 4.

2. The use according to claim 1, characterized in that The predicted probability of the prediction model is: p=exp(lp) / [1+exp(lp)], Wherein, lp is the linear prediction value.

3. The use according to claim 2, characterized in that The area under the receiver operating characteristic curve of the prediction model is ≥0.7; The Brill score of the prediction model is 0.15-0.16.

Images