Application of a molecular marker combination in radiation pneumonitis

Abstract

The present application relates to the field of biomedical technology, and in particular to an application of a molecular marker combination in radiation pneumonitis; the application includes: using the molecular marker combination as a biomarker for radiation pneumonitis, the molecular marker combination including CXC chemokine ligand 16 and / or CC chemokine ligand 24; by performing cytokine chip detection and screening on peripheral blood specimens of multiple lung cancer patients undergoing chest radiotherapy after radiotherapy, it was found that patients with high expression of CXC chemokine ligand 16 and CC chemokine ligand 24 early after radiotherapy have a higher risk of developing radiation pneumonitis in the future, and therefore the expression levels of CXC chemokine ligand 16 and CC chemokine ligand 24 can be used to make early predictions of the occurrence of radiation pneumonitis, and therefore the above-mentioned molecular marker combination may become an 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 the application of a molecular marker combination in radiation pneumonitis. Background Art

[0002] Radiation therapy is one of the main treatments for chest tumors, including lung cancer, esophageal cancer, and breast cancer. With improvements in radiotherapy equipment and technology, radiotherapy is playing an increasingly important role in cancer treatment. Radiotherapy can serve not only as an adjuvant to surgery and a palliative treatment to alleviate symptoms, but can even be a radical cure for some tumors. The primary goal of radiotherapy is to kill tumor cells. Although the accuracy of radiotherapy is constantly improving, damage to surrounding normal tissue cannot be completely avoided.

[0003] The lungs are radiation-sensitive organs, and their normal tissues are easily damaged by radiation during radiotherapy, causing radiation-induced lung injury. Severe cases require hospitalization and may even be life-threatening, further affecting the patient's quality of life and survival time, and increasing the medical burden. The harmful effects of radiation-induced lung injury may also limit the dose administered to chest tumors, making it difficult to optimally control the lesions in some patients. Therefore, being able to predict radiation-induced lung injury in advance can assist physicians in developing radiotherapy strategies that minimize radiation-induced lung injury while ensuring optimal local tumor control, thereby improving the patient's quality of life and survival time.

[0004] Currently, radiation therapy mostly relies on setting dosimetric parameters such as MLD and V20 to control radiation dose and reduce the incidence of normal tissue radiation pneumonitis. However, the setting of dosimetric parameters has certain limitations. Furthermore, in clinical practice, some patients who adopt the same radiotherapy strategy will not develop normal tissue radiation pneumonitis, while others will develop radiation pneumonitis. Furthermore, the severity of radiation pneumonitis varies among these patients. Therefore, the current use of dosimetric parameter settings alone cannot fully reflect the patient's risk of radiation-induced lung injury. Summary of the Invention

[0005] The present application provides an application of a molecular marker combination in radiation pneumonitis to solve the technical problem in the prior art that the setting of dosimetric parameters alone cannot fully represent the risk of radiation-induced lung injury in patients.

[0006] In a first aspect, the present application provides an application of a molecular marker combination as a biomarker for radiation pneumonitis, wherein the application includes: using the molecular marker combination as a biomarker for radiation pneumonitis, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24.

[0007] Optionally, the area under the receiver operating curve of the molecular marker combination is ≥0.6.

[0008] Optionally, the area under the receiver operating curve of the CXC chemokine ligand 16 is ≥0.62.

[0009] Optionally, the area under the receiver operating curve of the CC chemokine ligand 24 is ≥0.60.

[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 molecular marker combination, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24.

[0011] In a third aspect, the present application provides an application of a molecular marker combination in constructing a predictive model for predicting radiation pneumonia, characterized in that the molecular marker combination is used as a covariate to construct a predictive model, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24.

[0012] Optionally, the step of constructing the prediction model includes:

[0013] 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;

[0014] The preset factor parameters include the expression level of the CXC chemokine ligand 16 and / or the expression level of the CC chemokine ligand 24 .

[0015] Optionally, the prediction model is:

[0016] Linear prediction value = (-21.4621) + 2.1677*[CXCL16] + 0.8367*[CCL24],

[0017] Wherein, [CXCL16] is the expression level parameter of the CXC chemokine ligand 16;

[0018] [CCL24] is the expression level parameter of the CC chemokine ligand 24.

[0019] Optionally, the prediction probability of the prediction model is:

[0020] p=exp(lp) / [1+exp(lp)],

[0021] Wherein, lp is the linear prediction value.

[0022] Optionally, the area under the curve of the receiver operating characteristic curve of the prediction model is ≥0.65.

[0023] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0024] The present application provides an example of a molecular marker combination for use as a biomarker in 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 patients with high expression of CXC chemokine ligand 16 and CC chemokine ligand 24 were at higher risk of developing radiation pneumonitis. Therefore, the expression levels of CXC chemokine ligand 16 and CC chemokine ligand 24 can be used to make early predictions of the occurrence of radiation pneumonitis, thereby improving the accuracy of radiation pneumonitis prediction. Therefore, the above-mentioned molecular marker combination may become a clinical tool for early prediction of radiation pneumonitis. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] 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.

[0026] 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.

[0027] Figure 1 The test results of cytokine expression levels in the plasma of multiple lung cancer patients provided in the examples of this application are shown in FIG. Figure 1 A is the result of detecting the expression level of CXCL16 in the plasma of multiple lung cancer patients 2 weeks after radiotherapy. Figure 1 B is the result of detecting the expression level of CCL24 in the plasma of multiple lung cancer patients 2 weeks after radiotherapy;

[0028] Figure 2 This is a Logistic regression analysis result diagram of cytokine expression levels in plasma of multiple lung cancer patients provided in the examples of this application, wherein: Figure 2 A is the result of univariate logistic regression analysis of plasma CCL24 in multiple lung cancer patients 2 weeks after radiotherapy. Figure 2 B is the result of multivariate logistic regression analysis of plasma CCL24 in multiple lung cancer patients 2 weeks after radiotherapy;

[0029] Figure 3The results of the Logistic regression analysis of the cytokine expression levels in the plasma of multiple lung cancer patients 2 weeks after radiotherapy provided in the examples of this application are shown in FIG. Figure 3 A is the result of univariate logistic regression analysis of CXCL16 in plasma of multiple lung cancer patients 2 weeks after radiotherapy. Figure 3 B is the result of multivariate logistic regression analysis of CXCL16 in the plasma of multiple lung cancer patients;

[0030] Figure 4 This is a schematic diagram of the receiver operating characteristic curve of cytokine expression levels in plasma of multiple lung cancer patients 2 weeks after radiotherapy provided in the examples of this application, wherein: Figure 4 A is a diagram of the receiver operating characteristic curve of CXCL16 in plasma of multiple lung cancer patients 2 weeks after radiotherapy. Figure 4 B is a diagram of the receiver operating characteristic curve of plasma CCL24 in multiple lung cancer patients 2 weeks after radiotherapy;

[0031] Figure 5 The results of the Logistic regression analysis of the cytokine combination in the plasma of multiple lung cancer patients 2 weeks after radiotherapy provided in the examples of this application are shown in FIG. Figure 5 A is the result of univariate logistic regression analysis of cytokine combination in plasma of multiple lung cancer patients 2 weeks after radiotherapy. Figure 5 B is the result of multivariate logistic regression analysis of plasma cytokine combinations in multiple lung cancer patients 2 weeks after radiotherapy;

[0032] Figure 6 A schematic diagram showing a comparison of receiver operating characteristic curves of cytokines and their combinations in the plasma of multiple lung cancer patients provided in the examples of this application;

[0033] Figure 7 A flowchart illustrating the steps of constructing a prediction model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] 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.

[0035] 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.

[0036] Figure 4 Schematic diagram of receiver operating characteristic curves of cytokine expression levels in plasma of multiple lung cancer patients provided in the examples of the present application;

[0037] like Figure 4 As shown, an embodiment of the present application provides an application of a molecular marker combination as a biomarker in radiation pneumonia, wherein the application includes: using the molecular marker combination as a biomarker for radiation pneumonia, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24.

[0038] In some optional embodiments, the area under the receiver operating curve of the molecular marker combination is ≥0.6.

[0039] In the examples of the present application, the receiver operating characteristic (ROC) curve 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 is. When the AUC is in the range of 0.5 to 1, it indicates that these classification results have a certain correlation. Therefore, refining the specific area under the receiver operating characteristic curve of the molecular marker combination can indicate that high-level expression of CXC chemokine ligand 16 (CXCL16) and CC chemokine ligand 24 (CCL24) has a certain correlation with radiation pneumonitis. Therefore, it is shown that the high-level expression of these molecular marker combinations can serve as risk factors for radiation pneumonitis, that is, the high-level expression of these molecular marker combinations can serve as biomarkers for radiation pneumonitis.

[0040] In some optional embodiments, the area under the receiver operating curve of the CXC chemokine ligand 16 is ≥0.62.

[0041] In some optional embodiments, the area under the receiver operating curve of the CC chemokine ligand 24 is ≥0.60.

[0042] In the examples of the present application, by respectively refining the specific areas under the receiver operating curves of CXC chemokine ligand 16 (CXCL16) and CC chemokine ligand 24 (CCL24), it can be clearly determined that high-level expression of CXCL16 has a certain correlation with radiation pneumonitis, and that CCL24 has a certain correlation with radiation pneumonitis. Therefore, it is shown that the combination of these molecular markers expressed at high levels can serve as a risk factor for radiation pneumonitis, that is, high-level expression of CXCL16 or CCL24 can serve as a biomarker for radiation pneumonitis.

[0043] Based on a general inventive concept, an embodiment of the present application provides a detection kit for radiation pneumonitis, wherein the detection kit includes reagents for detecting the expression level of a molecular marker combination, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24.

[0044] The detection kit is implemented based on the application of the above-mentioned molecular marker combination as a biomarker for radiation-induced pneumonia. The specific principles of the application of the molecular marker combination 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.

[0045] Based on a general inventive concept, an embodiment of the present application provides an application of a molecular marker combination in constructing a prediction model for predicting radiation pneumonitis, wherein the molecular marker combination is used as a covariate to construct the prediction model, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24.

[0046] The application of this molecular marker combination in constructing a prediction model for predicting radiation pneumonitis is achieved based on the application of the above-mentioned molecular marker combination as a biomarker in radiation pneumonitis. The specific principles of the application of this molecular marker combination as a biomarker in radiation pneumonitis can be referred to the above-mentioned embodiments. Since the application of this molecular marker combination 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.

[0047] Figure 7 The following is a flow chart showing the steps of constructing a prediction model according to an embodiment of the present application;

[0048] like Figure 7 As shown, in some optional embodiments, the step of constructing the prediction model includes:

[0049] 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;

[0050] The preset factor parameters include the expression level of the CXC chemokine ligand 16 and / or the expression level of the CC chemokine ligand 24 .

[0051] In the embodiment of the present application, by using the expression levels of the above-mentioned CXC chemokine ligand 16 and / or CC chemokine ligand 24 as covariates and the occurrence of grade 2 or above radiation pneumonitis as the dependent variable, the occurrence of radiation pneumonitis can be predicted by CXC chemokine ligand 16 and CC chemokine ligand 24.

[0052] It should be noted that the statistical steps for the occurrence of grade 2 and above radiation pneumonitis include:

[0053] 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.

[0054] In some optional embodiments, the prediction model is:

[0055] Linear prediction value = (-21.4621) + 2.1677*[CXCL16] + 0.8367*[CCL24],

[0056] Wherein, [CXCL16] is the expression level parameter of the CXC chemokine ligand 16;

[0057] [CCL24] is the expression level parameter of the CC chemokine ligand 24.

[0058] In the embodiments of the present application, by defining a specific prediction model formula, it can be clarified that there is a linear relationship between the combination of molecular markers such as CXC chemokine ligand 16 and CC chemokine ligand 24 and radiation pneumonitis of grade 2 or above, that is, the possible probability of radiation pneumonitis of grade 2 or above can be clarified through the combination of these molecular markers.

[0059] In some optional embodiments, the prediction probability of the prediction model is:

[0060] p=exp(lp) / [1+exp(lp)],

[0061] Wherein, lp is the linear prediction value.

[0062] 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.

[0063] In some optional embodiments, the area under the curve of the receiver operating characteristic curve of the prediction model is ≥0.65.

[0064] In the embodiment of the present application, since the area under the curve is within the range of 0.6 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.

[0065] 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.

[0066] Example 1

[0067] Step 1: Collect peripheral blood samples from lung cancer patients before radiotherapy and perform protein chip testing

[0068] Peripheral blood samples were collected from 149 lung cancer patients 2 weeks after 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.

[0069] 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.

[0070] Step 2: Analyze the relationship between the expression levels of CXCL16 and CCL24 in peripheral blood and radiation pneumonitis

[0071] The Luminex cytokine chip was used to detect the plasma samples of patients and compare the expression levels of CXCL16 and CCL24 in the patient group of grade 2 and above and other patient groups. Figure 1 As shown; Univariate and multivariate Logistic regression analysis was performed on CXCL16 and CCL24, and the results were as follows Figure 2 and Figure 3 As shown, and the ROC curve is drawn, the results are as follows Figure 4 shown.

[0072] Depend on Figure 1 It can be seen that the levels of CXCL16 and CCL24 in peripheral blood samples were higher in the group of patients with grade 2 or above (P<0.05).

[0073] Depend on Figure 2It can be seen that in the univariate logistic regression analysis, CXCL16 and CCL24 were risk factors for radiation pneumonitis.

[0074] Depend on Figure 3 It can be seen that in the multivariate logistic regression analysis, CXCL16 and CCL24 are still risk factors for radiation pneumonitis, and the effect of CXCL16 on radiation pneumonitis is independent of clinical factors and dose factor V20.

[0075] Combine Figure 2 and Figure 4 It can be seen that CXCL16 and CCL24 are risk factors for radiation pneumonitis, and the AUCs of CXCL16 and CCL24 for predicting radiation pneumonitis are 0.628 and 0.609, respectively, which shows that single indicators of CXCL16 and CCL24 have the value of predicting radiation pneumonitis.

[0076] Example 2

[0077] Based on the relationship between the expression levels of CXCL16 and CCL24 and radiation pneumonitis determined in Example 1, further operations were performed:

[0078] Step 3: Combine CXCL16 and CCL24 to establish a predictive model

[0079] The expression levels of CXCL16 and CCL24 in peripheral blood were used as covariates, and the occurrence of grade 2 or higher radiation pneumonitis was used as the dependent variable. A regression model was established in a cohort of 149 lung cancer patients undergoing radiotherapy at Tongji Hospital affiliated to Tongji Hospital of Huazhong University of Science and Technology. The prediction model formula was obtained:

[0080] Linear prediction value (lp) = (-21.4621) + 2.1677*[CXCL16] + 0.8367*[CCL24],

[0081] Wherein, [CXCL14] is the expression level parameter of CXC chemokine ligand 16;

[0082] [CXCL10] is the expression level parameter of CC chemokine ligand 24;

[0083] The predicted probability is then converted using the formula p=exp(lp) / (1+exp(lp)).

[0084] By substituting the values ​​of the above cytokines into the formula on the right side of the regression model, the probability of radiation pneumonitis occurring in the patient can be calculated.

[0085] The prediction model was subjected to univariate logistic regression analysis, and the results were as follows Figure 5As shown in the results, the OR value of the prediction model was 2 (P < 0.001, confidence interval 1.382-3.005). Multivariate logistic regression analysis of the prediction model showed that the OR value of the prediction model was 1.897 (P = 0.02, confidence interval 1.276-2.821), which indicated that the prediction model was a risk factor for radiation pneumonitis, and its effect on radiation pneumonitis was independent of the dose index V20.

[0086] like Figure 6 As shown in the figure, the area under the ROC curve of the prediction model is 0.674, which indicates that the model can better distinguish patients with radiation pneumonitis. At the same time, compared with the single indicators of CXCL16 and CCL24, the AUCs for predicting radiation pneumonitis are 0.628 and 0.609, respectively, which indicates that the combined use of CXCL16 and CCL24 can effectively improve the prediction accuracy of radiation pneumonitis compared with a single indicator.

[0087] This predictive model also has guiding significance in clinical practice: using this predictive model, peripheral blood can be drawn from patients early after radiotherapy, and the radiotherapy dose can be controlled by detecting changes in the expression levels of the above-mentioned cytokines CXCL16 and CCL24. For example, patients with higher expression levels of the above two cytokines need to be vigilant about the occurrence of radiation pneumonitis, and the radiotherapy dose can be appropriately adjusted to avoid the occurrence of radiation pneumonitis. Patients with lower expression levels are relatively less likely to develop radiation pneumonitis, and the radiotherapy dose can be appropriately increased to strengthen local control of the tumor.

[0088] In summary, the application of a molecular marker combination as a biomarker in radiation pneumonitis provided in the embodiments of the present application, by detecting and screening peripheral blood samples of multiple lung cancer patients undergoing chest radiotherapy 2 weeks after radiotherapy using a cytokine chip, found that patients with high expression of CXC chemokine ligand 16 and CC chemokine ligand 24 had a higher risk of developing radiation pneumonitis. Therefore, the expression levels of CXC chemokine ligand 16 and CC chemokine ligand 24 can be used to predict the occurrence of radiation pneumonitis early to improve the prediction accuracy of radiation pneumonitis. Therefore, by detecting changes in the expression levels of the above-mentioned cytokines CXCL16 and CCL24, the radiotherapy dose can be controlled.

[0089] 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.

[0090] 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.

[0091] 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. Application of a molecular marker combination in constructing a prediction model for radiation pneumonitis, characterized in that: constructing a prediction model using the molecular marker combination as a covariate, wherein the molecular marker combination includes CXC chemokine ligand 16 and / or CC chemokine ligand 24; 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; Wherein, the preset factor parameters include the expression level of the CXC chemokine ligand 16 and / or the expression level of the CC chemokine ligand 24; The prediction model is: Linear prediction value = (-21.4621) + 2.1677*[CXCL16] + 0.8367*[CCL24], Wherein, [CXCL16] is the expression level parameter of the CXC chemokine ligand 16; [CCL24] is the expression level parameter of the CC chemokine ligand 24.

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 ≥0.65.

Images