Prognostic risk prediction system for EB virus related hemophagocytic syndrome patient and application

Abstract

The invention provides a risk prediction system and application of EB virus related hemophagocytic syndrome patients, five indexes UREA, DB, hscTnI, Ferr and PT are researched and developed to construct a scoring system, and if the score is greater than or equal to 3, the patient is prompted that the 28-day prognosis adverse risk is obviously increased (OR = 1.915). The model can provide a dynamic risk assessment tool for clinic and guide individualized treatment decisions.

Description

Technical Field

[0001] The present invention relates to the field of biomedical detection technology, and in particular to a prognosis risk prediction system and application for patients with Epstein-Barr virus-associated hemophagocytic syndrome. Background Art

[0002] Epstein-Barr virus-associated hemophagocytic lymphohistiocytosis (EBV-HLH) is a hyperinflammatory syndrome induced by EBV infection, characterized by uncontrolled immune activation, hemophagocytosis, and multi-organ failure, with a high mortality rate. The clinical manifestations of this disease are complex and diverse, often presenting with persistent fever, hepatosplenomegaly, progressive cytopenia, and coagulopathy. These findings can easily be confused with conditions such as sepsis and lymphoma, making early diagnosis difficult. Laboratory diagnostic criteria include significantly elevated EBV DNA levels, abnormally elevated ferritin levels, elevated sCD25 levels, and the presence of hemophagocytosis in the bone marrow. Due to the rapid progression of EBV-HLH, delayed treatment can lead to irreversible organ damage, while excessive immunosuppression can increase the risk of infection. Therefore, prognostic stratification based on laboratory characteristics is of great clinical significance for selecting treatment intensity and determining the timing of salvage therapy.

[0003] Therefore, it is necessary to develop a risk prediction system for patients with EBV-related hemophagocytic syndrome to provide important evidence-based basis for the formulation of individualized treatment strategies for patients with EBV-related hemophagocytic syndrome. Summary of the Invention

[0004] The purpose of the present invention is to provide a risk prediction system and application for patients with Epstein-Barr virus-associated hemophagocytic syndrome. By combining urea nitrogen (UREA), direct bilirubin (DB), high-sensitivity troponin I (hscTnI), ferritin (Ferr) and prothrombin time (PT) to construct a scoring system, the risk of poor short-term prognosis of patients can be accurately predicted.

[0005] The present invention adopts the following technical solutions: In a first aspect of the present invention, a prognostic risk prediction marker combination for patients with Epstein-Barr virus-associated hemophagocytic syndrome is provided, wherein the marker combination comprises: urea; Direct bilirubin; high-sensitivity troponin I; Ferritin; Prothrombin time.

[0006] Furthermore, the cutoff value corresponding to the biomarker is: Urea nitrogen (UREA) ≥5.4 mmol / L; Direct bilirubin (DB) ≥10 μmol / L; High-sensitivity troponin I (hscTnI) ≥7.4 pg / mL; Ferritin (Ferr) ≥12422 μg / L; Prothrombin time (PT) ≥14.1 s; Each increase in the index is scored as 1 point, with a total score of 0-5 points. A score of 3 points or more indicates a significant risk of poor short-term prognosis. Increase.

[0007] In a second aspect of the present invention, a risk prediction model based on the marker combination is provided, and the risk score is calculated by the following formula:

[0008] The risk score was calculated based on the input of urea, direct bilirubin, high-sensitivity troponin I, ferritin, and prothrombin time.

[0009] Furthermore, the risk score assesses the prognostic risk of patients with EBV-associated hemophagocytic syndrome as follows: 0-1 points: low risk; 2 points: medium-low risk; 3 points: medium to high risk 4-5 points: extremely high risk.

[0010] In a third aspect of the present invention, a prognostic risk prediction system for patients with Epstein-Barr virus-associated hemophagocytic syndrome is provided, characterized in that the system comprises: A processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, use the computational steps of the model.

[0011] In the fourth aspect of the present invention, the use of the marker combination or the risk prediction model for patients with EB virus-related hemophagocytic syndrome or the prognostic risk prediction system for patients with EB virus-related hemophagocytic syndrome in the preparation of a risk prediction product for patients with EB virus-related hemophagocytic syndrome is provided.

[0012] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages: The risk prediction model for EBV-associated hemophagocytic syndrome patients and the method for constructing the same provided by the present invention have the following advantages over existing technical solutions: The traditional HScore score relies on nonspecific indicators such as fever and cytopenia (Henter et al., 2007) and is unable to dynamically predict the short-term prognosis of EBV-HLH patients (Cui et al., 2022). Indicators such as EBV DNA load are significantly affected by the timing of testing (Zhang et al., 2024), leading to delayed clinical decision-making. This invention integrates five indicators—urea nitrogen (UREA), direct bilirubin (DB), high-sensitivity troponin I (hscTnI), ferritin (Ferr), and prothrombin time (PT)—into a dynamic scoring system (0-5 points). This system accurately stratifies EBV-HLH patients at risk of poor prognosis within 28 days (AUC = 0.798), significantly improving the accuracy of short-term prognostic assessment for EBV-HLH patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 For the correlation analysis between the initial screening variables, the following notes and explanations are provided: the more red the color of the small square is, the stronger the correlation between the two corresponding factors is; the more blue the color is, the weaker the correlation between the two corresponding factors is.

[0015] Figure 2 Figure 3 is the ROC curve of each difference index for the prognosis of EBV-HLH patients.

[0016] Figure 3 is the poor prognostic risk corresponding to the risk score of EBV-HLH at admission. DETAILED DESCRIPTION

[0017] The present invention will be described in detail below in conjunction with specific embodiments and examples, and the advantages and various effects of the present invention will be more clearly presented. It should be understood by those skilled in the art that these specific embodiments and examples are for illustrating the present invention, rather than for limiting the present invention.

[0018] Throughout this specification, unless otherwise specified, the terms used herein should be understood as having the same meaning as commonly used in the art. Therefore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. In the event of any conflict, the present specification shall take precedence.

[0019] Unless otherwise specified, various raw materials, reagents, instruments and equipment used in the present invention can be purchased from the market or obtained through existing methods.

[0020] The overall concept of the present invention is as follows: Methods: We retrospectively analyzed the clinical data of 117 patients with EBV-HLH admitted to Tongji Hospital from June 2016 to December 2024. Patients were divided into a poor prognosis group (n=48) and a good prognosis group (n=69) based on 28-day prognosis. Prognostic indicators were screened using receiver operating characteristic (ROC) curves and logistic regression, and a combined scoring system was established.

[0021] The study found that UREA, DB, hscTnI, Ferr, and PT levels were significantly higher in the poor prognosis group than in the good prognosis group (P<0.05). Receiver operating characteristic (ROC) analysis showed that the optimal cutoff values ​​for the five indicators were 5.4 mmol / L, 10.0 μmol / L, 7.4 pg / mL, 12422 μg / L, and 14.1 s, respectively, with corresponding odds ratios (ORs) for poor prognosis of 5.911 (95% CI 2.532-13.801), 2.524 (1.185-5.377), 2.747 (1.281-5.889), 2.366 (1.062-5.272), and 3.221 (1.481-7.005).

[0022] A 0-5 point risk scoring model was constructed, in which the poor prognostic rates of the score groups 0-1, 2, 3, 4, and 5 were 23.08%, 27.59%, 45%, 66.67%, and 92.3%, respectively. The OR value for each 1-point increase in risk was 1.915 (95% CI 1.425-2.574, P<0.001).

[0023] A risk prediction model was established based on the marker combination, and the risk score was calculated using the following formula:

[0024] The risk score was calculated based on the input of urea, direct bilirubin, high-sensitivity troponin I, ferritin, and prothrombin time.

[0025] Among them, risk classification: 0-1 points: low risk; 2 points: medium-low risk; 3 points: medium to high risk 4-5 points: extremely high risk.

[0026] The EBV-HLH patient prognostic risk stratification model provided by the present invention includes the following laboratory indicators and their optimal cutoff values: Urea nitrogen (UREA) ≥ 5.4 mmol / L Direct bilirubin (DB) ≥ 10.0 μmol / L High-sensitivity troponin I (hscTnI) ≥7.4 pg / mL Ferritin (Ferr) ≥12422 μg / L Prothrombin time (PT) ≥ 14.1 s Patients are scored on a scale of 0-5 based on the elevation of these indicators. A higher score indicates a higher risk of poor prognosis. Patients with a score ≥ 3 require intensive immunomodulatory therapy.

[0027] Compared to the traditional HScore, which primarily relies on nonspecific indicators such as fever and cytopenia, the 0-5 risk stratification model constructed in this study integrates multiple dimensions of metabolic, cardiac, and coagulation indicators. Validation in 117 patients showed that those with a score ≥3 had a significantly higher rate of poor prognosis than those with a score ≤2 (45% vs 25.4%, P<0.001), with each additional point increasing the risk by 1.915-fold (95% CI 1.425-2.574). This provides a new tool for precise stratification of EBV-specific HLH. Patients with a score ≥3 require intensive treatment (such as the DEP regimen combined with ruxolitinib), providing a basis for personalized stratified management.

[0028] The risk prediction model for patients with EBV-related hemophagocytic syndrome and its construction method will be described in detail below in combination with examples and experimental data.

[0029] Example 1: Marker combination screening

[0030] 1 Materials and Methods 1.1 General Information A total of 117 patients diagnosed with EBV-HLH at Tongji Hospital between June 2016 and December 2024 were enrolled. Of these, 72 were male (61.5%) and 45 were female (38.5%), with a mean age of (50.64±16.54) years. Inclusion criteria included: ① age ≥18 years; ② evidence of EBV infection requiring either of the following two criteria: primary acute EBV infection by serological antibody testing; or positive serum or plasma EBV DNA; and ③ fulfillment of the HLH-2004 diagnostic criteria (≥5 of the following: fever, splenomegaly, cytopenia, hyperferritinemia, and bone marrow hemophagocytosis). Exclusion criteria included: ① concomitant hematologic malignancies; ② missing key laboratory data before treatment. A 28-day observation window was defined after admission; patients who died or did not respond to initial treatment (requiring intensive treatment or disease progression) within this timeframe were categorized as having a poor prognosis; patients who achieved stable disease or remission were categorized as having a good prognosis. This study was approved by the hospital's ethics committee.

[0031] 1.2 Methods This study is a case-control study, which adopts a continuous screening method to enroll patients and analyze the general information, clinical symptoms and laboratory results of patients. The collected data include the age, gender, clinical symptoms, medical history of all patients and the first laboratory index test results available to patients, including white blood cells (WBC), neutrophils (NEUT), lymphocytes (LYM), monocytes (MONO), red blood cells (RBC), hemoglobin (HGB), platelets (PLT), alanine aminotransferase (ALT), aspartate aminotransferase (AST), total protein (TP), albumin (ALB), total bilirubin (TB), direct bilirubin (DB), alkaline phosphatase (ALP), γ-glutamyl transpeptidase (GGT), lactate dehydrogenase (LDH), cholesterol (TC), triglycerides (TG), creatinine (CREA), urea nitrogen (UREA), uric acid (UA), potassium (K), sodium (NA), chloride (CL), calcium (CA), prothrombin time (PT), activated partial thromboplastin time (APTT), fibrinogen (FIB), D-dimer (DD), high-sensitivity troponin I (hscTnI), interleukin-1β (IL-1β), interleukin-2R (IL-2R), interleukin-6 (IL-6), interleukin-8 (IL-8), interleukin-10 (IL-10), tumor necrosis factor α (TNF-α), procalcitonin (PCT), ferritin (Ferr), and EBV viral load (EBV-DNA).

[0032] 1.3 Statistical methods Data were analyzed using SPSS 20.0 statistical software. The Shapiro-Wilk test was used to test for normality. Normally distributed data were expressed as mean ± standard deviation, and skewed data were expressed as median (interquartile range) (P<0.05, P<0.05). Normally distributed data were compared using the independent sample t-test, skewed data were compared using the Mann-Whitney U test, and the chi-square test was used to compare the constituent ratios between the two groups. Receiver operating characteristic (ROC) curves were used to evaluate the performance of each test indicator in predicting the short-term prognosis of EBV-HLH. The cutoff points for each significant difference were identified, and sensitivity, specificity, and area under the curve (AUC) were calculated. A P<0.05 was considered statistically significant. Logistic regression was used to calculate relative risk.

[0033] 2 Results 2.1 Comparison of general information between the two groups of patients There were no statistically significant differences between the two groups in terms of gender, fever, hepatosplenomegaly, and length of hospital stay (P>0.05). However, the age of the patients in the good prognosis group was significantly higher than that in the poor prognosis group (P<0.05). See Table 1.

[0034] Table 1 General information of the two groups of EBV-HLH patients

[0035] 2.2 Comparison of laboratory-related indicators between the two groups of patients Comparison of laboratory indicators between the two groups showed that the levels of UREA, TB, DB, hscTnI, Ferr, and PT in the poor prognosis group were significantly higher than those in the good prognosis group (P<0.05), as shown in Table 2.

[0036] Table 2 Laboratory parameters of the two groups of EBV-HLH patients

[0037]

[0038] 2.2 Correlation analysis of independent variables The above six independent variables with statistically significant differences were analyzed by Pearson correlation. After removing TB with correlation > 0.7, the remaining five independent variables were UREA, DB, hscTnI, Ferr, and PT. Figure 1 At the same time, to reduce the impact of homoscedasticity on the model, a variance homogeneity analysis was performed, and it was found that there were no variables with a variance inflation factor (VIF) greater than 10, so there was no need to eliminate the variables.

[0039] 2.3. Assessment of Poor Prognostic Risk Based on Differential Indicators The ROC curve was used to find the optimal cut-off value for differential indicators including UREA, DB, hscTnI, Ferr, and PT to predict the prognosis of EBV-HLH patients. Figure 2 .

[0040] After analysis, the cut-off values ​​of UREA, DB, hscTnI, Ferr, and PT were 5.4 mmol / L, 10 μmol / L, 7.4 pg / ml, 12422 μg / L, and 14.1 s, respectively. The areas under the curves were 0.698 (95% CI 0.608-0.799), 0.652 (95% CI 0.577-0.738), 0.648 (95% CI 0.532-0.745), 0.608 (95% CI 0.518-0.700), and 0.639 (95% CI 0.552-0.732), respectively (Table 3).

[0041] Table 3 AUC of ROC of subjects

[0042] The cases were divided into a low-level group and a high-level group according to the cut-off value. The results of logistic regression are shown in Table 4.

[0043] Table 4 UREA, DB, hscTnI, Ferr and PT predict the prognostic risk of EBV-HLH

[0044] As shown in Table 4, compared with those with low levels, the OR values ​​of poor prognosis risk in patients with high levels of UREA, DB, hscTnI, Ferr, and PT at admission were 5.911 (95%CI 2.532-13.801, P < 0.001), 2.524 (95%CI 1.185-5.377, P = 0.016), 2.747 (95%CI 1.281-5.889, P = 0.009), 2.366 (95%CI 1.062-5.272, P = 0.035), and 3.221 (95%CI 1.481-7.005, P = 0.003), respectively.

[0045] 2.5. Combining UREA, DB, hscTnI, Ferr, and PT to predict poor prognosis in patients with EBV-HLH The prognostic prediction score was constructed by combining the five indicators at admission. Each increase in one indicator was scored as 1 point, and the patient's cumulative score was calculated. The patient's score range was 0-5 points. This study found that the poor prognosis rates of the groups with scores of 0-1, 2, 3, 4, and 5 were 23.08%, 27.59%, 45%, 66.67%, and 92.3%, respectively ( Figure 3The higher the patient's score, meaning the more elevated indicators, the higher the rate of poor short-term prognosis. Logistic regression using the score as the independent variable showed that for every one-point increase in risk, the odds ratio (OR) for poor short-term prognosis in EBV-HLH patients was 1.915 (95% CI 1.425-2.574, P < 0.001).

[0046] Example 2: Comparison of the Five-Indicator Joint Detection Method of the Present Application with the Existing Method 1. HScore scoring system in existing technology The HScore scoring system was proposed by Henter et al. in 2004 to standardize the diagnosis and prognostic assessment of hemophagocytic lymphohistiocytosis (HLH). Its core indicators include fever, cytopenia, splenomegaly, hypertriglyceridemia, hypofibrinogenemia and other nonspecific inflammatory markers. (Henter JI, Horne A, Aricó M, et al. HLH-2004: Diagnostic and therapeutic guidelines for hemophagocytic lymphohistiocytosis. Pediatr Blood Cancer. 2007;48(2):124–131.DOI: 10.1002 / pbc.20955) 2. Limitations of traditional HScore: Nonspecific: Relying on generalized inflammatory indicators such as fever and cytopenia, it is unable to distinguish EBV-HLH from other similar diseases (such as sepsis and lymphoma).

[0047] Static evaluation: Based only on a single test result, it lacks dynamic prediction capabilities.

[0048] Subjective weighting: The detection methods of some indicators (such as NK cell activity) are complex and have low standardization.

[0049] 3. Comparison of the Five-Indicator Joint Model of This Application with Existing Methods Table 5

[0050] As shown in Table 5, the dynamic scoring system constructed by combining the five laboratory indicators of UREA, DB, hscTnI, Ferr, and PT significantly improved the specificity of short-term prognostic prediction for EBV-HLH (AUC=0.798 vs 0.652 of HScore) and can be directly associated with the selection of treatment intensity.

[0051] Example 3: Risk prediction model based on the marker combination The risk prediction model based on the marker combination is characterized in that the risk score is calculated by the following formula:

[0052] The risk score was calculated based on the input of urea, direct bilirubin, high-sensitivity troponin I, ferritin, and prothrombin time.

[0053] Each indicator increase is worth 1 point, with a total score of 0-5 points: 0-1 points: low risk (poor prognosis rate ≤ 25%); 2 points: low to medium risk (25%-30%); 3 points: medium-high risk (40%-50%); 4-5 points: very high risk (≥65%); For every 1 point increase, the OR value of poor prognosis was 1.915 (95% CI 1.425-2.574).

[0054] Example 4: Risk assessment system based on the marker combination An embodiment of the present invention provides a risk assessment system based on the marker combination, the system comprising: A processor and a memory, wherein the memory is coupled to the processor and stores instructions. When the instructions are executed by the processor, the steps described in embodiment 1 or embodiment 3 are used.

[0055] Example 5: Computer-readable storage medium An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method of embodiment 1 and / or the steps of embodiment 2 are implemented.

[0056] Of course, the computer executable instructions of a storage medium containing computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, and can also execute related operations in the method provided by any embodiment of the present invention.

[0057] Through the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0058] It is worth noting that in the above embodiments, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0059] Application Example 1: Example of risk prognosis prediction for patients with EB virus-associated hemophagocytic syndrome Patient basic information Gender: Male Age: 45 Chief complaint: persistent fever (39.5°C), hepatosplenomegaly, and fatigue for 1 week Medical history: No history of hematologic malignancies, recent infection, or immunosuppressive therapy Laboratory test results Table 6

[0060] Risk score calculation: Total score = 1 (UREA) + 1 (DB) + 1 (hscTnI) + 1 (Ferr) + 1 (PT) = 5 points Risk level: Very high risk (score ≥ 3 points) Poor prognosis rate: 92.3% Clinical decision-making recommendations Treatment options: Immediately initiate intensive immunomodulatory therapy (eg, DEP regimen combined with ruxolitinib).

[0061] Monitor multiple organ functions (liver and kidney function, coagulation indicators, and ECG monitoring).

[0062] Further inspection: Bone marrow puncture: Confirm hemophagocytosis and evidence of EBV infection.

[0063] EBV-DNA dynamic monitoring: assess changes in viral load.

[0064] Supportive care: Blood component transfusion: Correction of thrombocytopenia (PLT < 50 × 10 9 / L).

[0065] Hepatoprotective treatment: Elevated direct bilirubin indicates liver damage (DB=14.2 μmol / L).

[0066] Application Example 2: Low-risk patient example Patient basic information Gender: Female Age: 32 Chief complaint: fever (38.2°C), lymphadenopathy for 3 days Medical history: no underlying disease, no recent history of surgery or blood transfusion Laboratory test results Table 7

[0067] Risk score calculation Total score = 0 + 0 + 0 + 0 + 0 = 0 points; Risk level: low risk (score ≤ 1 point); Poor prognosis rate: 23.08%; Treatment recommendations: Routine immunosuppressive therapy (such as glucocorticoids combined with cyclosporine) should be administered. Close monitoring of indicators should be performed (recheck blood count, liver and kidney function every 48 hours).

[0068] Further testing: EBV antibody testing to confirm primary acute infection. Abdominal ultrasound to assess the extent of hepatosplenomegaly. Supportive care: Fluid replacement and electrolyte balance to prevent dehydration and electrolyte imbalance.

[0069] Finally, it should be noted that the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0070] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0071] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A combination of prognostic risk prediction markers for patients with Epstein-Barr virus-associated hemophagocytic syndrome, characterized in that: The marker combination includes: urea; Direct bilirubin; high-sensitivity troponin I; Ferritin; Prothrombin time.

2. The combination of prognostic risk prediction markers for patients with Epstein-Barr virus-associated hemophagocytic syndrome according to claim 1, characterized in that: The cutoff values ​​corresponding to the biomarkers are: Urea nitrogen (UREA) ≥5.4 mmol / L; Direct bilirubin (DB) ≥10 μmol / L; High-sensitivity troponin I (hscTnI) ≥7.4 pg / mL; Ferritin (Ferr) ≥12422 μg / L; Prothrombin time (PT) ≥14.1 s; Each increase in the index is scored as 1 point, with a total score of 0-5 points. A score of 3 points or more indicates a significant risk of poor short-term prognosis. Increase.

3. A prognostic risk prediction model for patients with Epstein-Barr virus-associated hemophagocytic syndrome based on the marker combination according to any one of claims 1-2, characterized in that: The risk score is calculated using the following formula: ； The risk score was calculated based on the input of urea, direct bilirubin, high-sensitivity troponin I, ferritin, and prothrombin time.

4. The prognostic risk prediction model for patients with Epstein-Barr virus-associated hemophagocytic syndrome based on the marker combination according to claim 3, characterized in that: The prognostic risk of patients with EBV-associated hemophagocytic syndrome was assessed according to the risk score as follows: 0-1 points: low risk; 2 points: medium-low risk; 3 points: medium to high risk 4-5 points: extremely high risk.

5. A prognosis risk prediction system for patients with Epstein-Barr virus-associated hemophagocytic syndrome, characterized in that: The system comprises: A processor and a memory, the memory being coupled to the processor, the memory storing instructions that, when executed by the processor, use the calculation steps of the model according to any one of claims 3 to 4.

6. Use of the marker combination according to any one of claims 1-2, the prognostic risk prediction model for patients with Epstein-Barr virus-associated hemophagocytic syndrome according to any one of claims 3-4, or the prognostic risk prediction system for patients with Epstein-Barr virus-associated hemophagocytic syndrome according to claim 5 in the preparation of a risk prediction product for patients with Epstein-Barr virus-associated hemophagocytic syndrome.

Images