Novel bunyavirus infection prognosis risk prediction model and application thereof

Abstract

The embodiment of the invention discloses a novel bunyavirus infection prognostic risk prediction model and application thereof, and a construction method of the novel bunyavirus infection prognostic risk prediction model comprises the following steps: collecting case information and detection data, and comparing data indexes of a novel bunyavirus infection survival group and a novel bunyavirus infection death group, obtaining independent variables of which differences have statistical significance; carrying out Pearson correlation analysis on the independent variables with statistical significance on the difference, removing variables with relatively high correlation, and carrying out binary Logistic regression analysis on the residual variables to obtain key model indexes; and according to the key model indexes, establishing a novel bunyavirus infection prognosis risk prediction model, and generating a column diagram. The model has better prediction effect and clinical practicability, provides specific basis for clinical medical personnel to judge the prognosis condition of the patient, and performs early intervention to prevent the occurrence of bad outcome.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of biotechnology, and in particular to a novel bunyavirus infection prognosis risk prediction model and application thereof. Background Art

[0002] Severe fever with thrombocytopenia syndrome (SFTS) is an acute epidemic infectious disease caused by Dabie Banda virus (DBV, also known as new Bunyavirus). Its clinical manifestations are mainly fever and thrombocytopenia, which may be accompanied by symptoms such as nausea, vomiting, fatigue, poor appetite, diarrhea and muscle aches. Patients with severe conditions may experience skin ecchymosis, pulmonary hemorrhage, gastrointestinal bleeding, impaired consciousness and even multiple organ failure. In the early stage of the disease, the mortality rate was as high as 30%. With the advancement of medical technology, the domestic mortality rate of SFTS dropped from 10.58% to 5.07% from 2011 to 2021. However, the mortality rate of severe patients remains high. The mortality rate of SFTS patients with central nervous system involvement and multiple organ failure can be as high as 44.7%.

[0003] At present, there are few prediction models for SFTS disease, and the indicators focused on by the existing models vary greatly, lacking a unified standard. Therefore, establishing a prognostic risk warning model for SFTS patients can help clinicians identify potential critically ill patients at an early stage, detect changes in their condition in a timely manner, and take preemptive measures and nursing interventions, which is of great significance for improving the success rate of patient treatment and reducing mortality. Summary of the invention

[0004] The purpose of the present invention is to provide a set of novel Bunyavirus infection prognosis risk prediction models and their applications, which can be used to evaluate the prognosis of novel Bunyavirus infection and possibly guide the selection of its treatment plan.

[0005] To achieve the above object, the present invention adopts the following technical solution:

[0006] In a first aspect of an embodiment of the present invention, a set of novel Bunyavirus infection prognosis risk prediction models is provided, wherein the prediction model comprises one of the following two prediction models:

[0007] Model 1: Based on the five key model indicators of multiple organ function damage markers, the new Bunyavirus infection prognosis risk prediction model formula 1 was established:

[0008] Ln(P / 1-P)=-15.06+1.345×X1+0.107×X2+0.002×X3+0.137×X4+0.005×X5;

[0009] In the above formula 1, X1 is the viral load, X2 is the age, X3 is the myoglobin correlation value, X4 is the urea nitrogen correlation value, and X5 is the pancreatic amylase correlation value;

[0010] Model 2: Based on the four key model indicators of inflammatory biomarkers, the new Bunyavirus infection prognosis risk prediction model formula 2 was established:

[0011] Ln(P / 1-P)=-15.327+0.982×X1+0.15×X2+1.015×X3+0.005×X4;

[0012] In the above formula 2, X1 is the viral load, X2 is the age, X3 is the procalcitonin association value, and X4 is the interleukin-10 association value.

[0013] In a second aspect of the embodiments of the present invention, a method for constructing the novel Bunyavirus infection prognosis risk prediction model is provided, the method comprising:

[0014] Collect case information and test data, compare the data indicators of the survival group and the death group of the new bunyavirus infection, and obtain the independent variables with statistically significant differences;

[0015] Pearson correlation analysis was performed on the independent variables with statistically significant differences, and the variables with higher correlation were eliminated. Binary Logistic regression analysis was performed on the remaining variables to obtain key model indicators;

[0016] Based on the key model indicators, a prognosis risk prediction model for novel Bunyavirus infection was established.

[0017] In a third aspect of the embodiments of the present invention, a novel system for predicting the prognosis risk of Bunyavirus infection is provided, the system comprising:

[0018] A processor and a memory, the memory being coupled to the processor, the memory storing instructions which, when executed by the processor, use the following steps:

[0019] The values ​​of the key model indicators are input into the prediction model to obtain a prediction score for the prognosis risk of novel Bunyavirus infection.

[0020] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are performed:

[0021] The values ​​of the key model indicators are input into the prediction model to obtain a prediction score for the prognosis risk of novel Bunyavirus infection.

[0022] In a fifth aspect of an embodiment of the present invention, a computer program product is provided, comprising a computer program / instruction, which implements the calculation steps of the prediction model when executed by a processor.

[0023] In a sixth aspect of an embodiment of the present invention, there is provided an application of the novel Bunyavirus infection prognosis risk prediction model, the prediction system, the computer-readable storage medium, or the computer program product in the preparation of a product for predicting novel Bunyavirus infection risk.

[0024] In a seventh aspect of the embodiments of the present invention, a novel product for predicting the prognosis risk of Bunyavirus infection is provided, comprising:

[0025] A product for measuring key model indicators of the novel Bunyavirus infection prognosis risk prediction model;

[0026] and the prediction system or the computer-readable storage medium or the computer program product.

[0027] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages:

[0028] The novel Bunyavirus infection prognosis risk prediction system and its application provided by the embodiment of the present invention include 2 models, wherein a related nomogram model is constructed based on 5 risk factors, and the prediction efficiency of the nomogram model is good (ROC=0.924), and the accuracy rate is 84.8%. A related nomogram model is constructed based on 4 risk factors, and the prediction efficiency of the nomogram model is good (ROC=0.905), and the accuracy rate is 84.5%. The above two models both have good predictive effect and clinical practicality, and provide a specific basis for clinical medical staff to judge the prognosis of patients. For elderly SFTS patients, special attention should be paid to their viral load, inflammatory indicators, and damage to the heart, kidney, and pancreas multiple organs, and early intervention should be carried out to prevent the occurrence of adverse outcomes. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 The results of the correlation analysis between the initial screening variables in Example 1. Notes and explanations: The more the color of the small square is red, the stronger the correlation between the two corresponding factors; the more the color is blue, the weaker the correlation between the two corresponding factors.

[0031] Figure 2 ROC curves were drawn for the variables in the independent risk factors in Example 1.

[0032] Figure 3 A nomogram model for the prognosis of SFTS patients was established in Example 1.

[0033] Figure 4 To verify the model in Example 1, the calibration curve approaches the diagonal result.

[0034] Figure 5 1 is the ROC curve of the nomogram in Example 1.

[0035] Figure 6 The results of the correlation analysis between the initial screening variables in Example 2 are shown in FIG.

[0036] Figure 7 ROC curves were drawn for the variables in the independent risk factors in Example 2.

[0037] Figure 8 A nomogram model for the prognosis of SFTS patients was established in Example 2.

[0038] Fig. 9 To verify the model in Example 2, the calibration curve approaches the diagonal result.

[0039] Fig.10 This is the ROC curve of the nomogram in Example 2.

[0040] Fig.11 A flow chart of a method for constructing a novel bunyavirus infection prognosis risk prediction model provided by the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with specific implementation methods and examples to specifically describe the embodiments of the present invention, and the advantages and various effects of the embodiments of the present invention will be more clearly presented. It should be understood by those skilled in the art that these specific implementation methods and examples are used to illustrate the embodiments of the present invention, rather than to limit the embodiments of the present invention.

[0042] Throughout the specification, unless otherwise specifically stated, the terms used herein should be understood as meanings commonly used in the art. Therefore, unless otherwise defined, all technical and scientific terms used herein have the same meanings as those generally understood by those skilled in the art to which the embodiments of the present invention belong. In the event of a conflict, this specification takes precedence.

[0043] The overall idea of ​​the technical solution of the present invention is as follows:

[0044] In order to solve the technical problem of the present application, the inventors of the present application have developed two new prognosis risk models for Bunyavirus infection, namely: a new prognosis risk model for Bunyavirus infection based on multiple organ function damage markers and a new prognosis risk model for Bunyavirus infection based on inflammatory biomarkers.

[0045] The method for constructing a prognostic risk model for new bunyavirus infection based on markers of multiple organ dysfunction was as follows: 204 SFTS patients admitted to Tongji Hospital affiliated to Tongji Medical College of Huazhong University of Science and Technology from April 1, 2023 to July 18, 2024 were selected as research subjects for retrospective analysis. According to the prognosis of the patients, they were divided into a survival group (n=127) and a death group (n=77). The general information of the patients, blood routine tests within 24 hours, viral load, and markers of multiple organ dysfunction (heart, liver, kidney, pancreas) were analyzed by univariate analysis and multivariate logistic regression analysis to obtain independent risk factors affecting the prognosis of the patients, and a risk warning model was established. Results: Viral load (OR=3.838, 95%CI (2.497-6.372), P<0.001), age (OR=1.113, 95%CI (1.055-1.183), P<0.001), MYO (OR=1.002, 95%CI (1.0-1.003), P=0.032), UREA (OR=1.147, 95%CI (1.028-1.295), P=0.018), AMY-P (OR=1.005, 95%CI (1.001-1.009), P=0.011) were independent risk factors affecting the prognosis of patients. A related nomogram model was constructed based on the five risk factors, and the predictive efficiency of the nomogram model was good (ROC=0.924) and the accuracy rate was 84.8%.

[0046] The method for constructing a new prognostic risk model for bunyavirus infection based on inflammatory biomarkers is as follows: 207 SFTS patients admitted to Tongji Hospital affiliated to Tongji Medical College of Huazhong University of Science and Technology from April 1, 2023 to July 18, 2024 were selected as research subjects, and retrospective analysis was performed. According to the prognosis of the patients, they were divided into a survival group (n=133) and a death group (n=74). The general information of the patients and the first inflammatory index within 24 hours were analyzed by univariate analysis and multivariate logistic regression analysis to obtain independent risk factors affecting the prognosis of the patients, and a risk warning model was established. Results: Age (OR=1.162, 95%CI (1.102-1.236), P<0.001), viral load (OR=2.669, 95%CI (1.764-4.239), P<0.001), PCT (OR=2.758, 95%CI (1.586-5.231), P=0.001), and IL-10 (OR=1.005, 95%CI (1.001-1.009), P=0.019) were independent risk factors affecting the prognosis of patients. A related nomogram model was constructed based on the four risk factors, and the predictive efficiency of the nomogram model was good (ROC=0.905) and the accuracy rate was 84.5%.

[0047] In summary, the SFTS patient prognosis risk warning model constructed in this application has a good predictive effect and can be used as a tool for clinically predicting the prognosis of SFTS patients.

[0048] Unless otherwise specified, various raw materials, reagents, instruments and equipment used in the embodiments of the present invention can be purchased from the market or prepared by existing methods.

[0049] The following will describe in detail a set of novel Bunyavirus infection prognosis risk prediction systems and their applications in combination with embodiments, comparative examples and experimental data.

[0050] Example 1: A novel prognostic risk prediction model for bunyavirus infection based on multiple organ dysfunction markers and its construction method

[0051] 1 Objects and methods

[0052] 1.1 Research subjects

[0053] This study is a retrospective analysis. A total of 204 SFTS patients admitted to the Department of Infectious Diseases and the Intensive Care Unit of this hospital from April 1, 2023 to July 18, 2024 were selected as the research subjects, including 95 males and 109 females, with an average age of (64.848±9.452) years. Inclusion criteria: ① Age ≥ 18 years old; ② Meet the diagnostic criteria for SFTS. That is, the case specimens tested positive for novel Bunyavirus nucleic acid. Exclusion criteria: ① Patients with incomplete laboratory-related information; ② Patients diagnosed in the outpatient clinic but not admitted to the hospital; ③ Patients with malignant tumors and blood system diseases. The 28 days after admission were set as the observation window. Patients who died within this time limit were classified as the death group, and patients who continued to survive were included in the survival group. This study was reviewed and approved by the hospital ethics committee.

[0054] 1.2 General Information Collection

[0055] The relevant risk factor data were collected by reviewing the electronic medical records of the selected SFTS during their hospitalization. The clinical data of SFTS included: age, gender, diabetes, hypertension, coronary heart disease, cerebral infarction, smoking history, drinking history, poor appetite, nausea, vomiting, abdominal pain, diarrhea, chest tightness, lymphadenopathy, changes in consciousness, body temperature, and the number of days from onset to diagnosis.

[0056] 1.3 Laboratory test indicators

[0057] All research subjects collected blood routine, viral load, multiple organ damage markers (heart, liver, kidney, pancreas) and other related indicators when SFTS patients were first admitted to the hospital, including white blood cells (WBC), neutrophils (NEU#), lymphocytes (LYM#), the ratio of absolute neutrophil to absolute lymphocyte value (NLR), red blood cells (RBC), hemoglobin (HGB), platelets (PLT), atrial natriuretic peptide (BNP), creatine kinase (CK-MB), myoglobin (MYO), troponin (CTnI), alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALP), glutamyl transpeptidase (GGT), lactate dehydrogenase (LDH), creatinine (CREA), urea nitrogen (UREA), uric acid (UA), potassium (K), sodium (NA), chloride (CL), calcium (CA), lipase (LIP), pancreatic amylase (AMY-P), and SFTSV load as the observation objects. The blood routine related indicators were detected by Japanese SYSMES blood cell analyzer XE2100; CK-MB, MYO, and CTnI were detected by Abbott automatic biochemical immunoassay analyzer, and ALT, AST, ALP, GGT, LDH, CREA, UREA, UA, K, NA, CL, CA, LIP, AMY-P and other biochemical indicators were detected by Roche C8000 biochemical analyzer. The SFTSV load was measured by Xi'an Tianlong PANA9600s extractor and GENTIER 96E amplifier, and the amplification reagents were produced by Sun Yat-sen University Da'an Gene Co., Ltd. The experimental steps were performed according to the instructions.

[0058] 1.4 Statistical methods

[0059] SPSS 20.0 statistical software was used for data analysis. The Shapiro-Wilk test was used to test the normality of the data. Normally distributed data were expressed as mean ± standard deviation, and skewed distribution data were expressed as median (quartile) M (P25, P75). Independent sample t test was used to compare normal distribution data, Mann-Whitney U test was used to compare skewed distribution data, and χ2 test was used to compare the constituent ratio between the two groups. ROC curves were drawn, and sensitivity, specificity and AUC were calculated. P < 0.05 was considered statistically significant. Binary multivariate logistic regression analysis and Hosmer-Lemeshow test were used to evaluate the model fit. The independent risk factors obtained were used to establish a nomogram model using R language (4.3.1). Bootstrap method was used for internal validation, and C index, calibration curve and ROC curve were used to verify the predictive ability of the model. P < 0.05 was considered statistically significant.

[0060] 2 Results

[0061] 2.1 Comparison of general information between the two groups of patients

[0062] There was no significant difference in gender ratio, history of diabetes, cerebral infarction, hypertension, coronary heart disease, history of smoking, history of alcoholism, poor appetite, nausea, vomiting, abdominal pain, diarrhea, lymphadenopathy, body temperature, and days from onset to hospitalization between the two groups (P>0.05); however, the proportion of age, chest tightness, abdominal pain, and mental changes in the survival group was lower than that in the death group, and the difference was statistically significant (P<0.05). See Table 1

[0063] Table 1 General information of patients in the two SFTS groups

[0064]

[0065]

[0066] 2.2 Comparison of laboratory test and other related indicators between the two groups of patients

[0067] There was no significant difference in WBC, NEU#, LYM#, NLR, RBC, HGB, NA, and CL between the two groups (P>0.05). Compared with the survival group, the death group had significantly lower PLT and CA, and significantly higher BNP, CK-MB, MYO, CTnI, ALT, AST, ALP, GGT, LDH, CREA, UREA, UA, K, LIP, and AMY-P, with statistically significant differences (P<0.05). See Table 2.

[0068] Table 2 Comparison of blood routine and multiple organ dysfunction related indicators between the two groups

[0069]

[0070]

[0071] 2.3 Correlation analysis of independent variables

[0072] The above 22 independent variables with statistically significant differences were analyzed by Pearson correlation. After removing the indicators with high correlation, such as CREA, UA, LIP, GGT, and ALT, the correlations of the remaining 17 independent variables were as follows: Figure 1 At the same time, in order to reduce the impact of homoscedasticity on the model, variance homogeneity analysis was performed, and it was found that there were no variables with variance inflation factor (VIF) greater than 10, so there was no need to eliminate the variables.

[0073] 2.4 Multivariate analysis of prognosis in SFTS patients

[0074] Binary Logistic multivariate analysis was performed with the above 17 variables as independent variables and prognosis as dependent variable. Finally, 5 independent risk factors were identified, including viral load (OR=3.838, 95%CI (2.497-6.372), P<0.001), age (OR=1.113, 95%CI (1.055-1.183), P<0.001), MYO (OR=1.002, 95%CI (1.0-1.003), P=0.032), UREA (OR=1.147, 95%CI (1.028-1.295), P=0.018), AMYP (OR=1.005, 95%CI (1.001-

[0075] 1.009), P = 0.011) see Table 3. The regression equation was established: Ln (P / 1-P) = -15.06 + 1.345 × X1 + 0.107 × X2 + 0.002 × X3 + 0.137 × X4 + 0.005 × X5.

[0076] Table 3 Multivariate binary logistic regression analysis of prognosis of SFTS patients

[0077]

[0078]

[0079] 2.5 Establishment of a prognostic risk warning model for SFTS patients

[0080] The ROC curves were drawn for the variables in the independent risk factors. Figure 2. The AUC of each independent risk factor is shown in Table 4. The AUC for predicting the risk of death in SFTS patients based on age alone was 0.701 (95% CI: 0.623-0.771), and the optimal cutoff value was 59 years old (sensitivity 99.2%, specificity 39.4%); the AUC for viral load (logarithmic value) to measure the risk of death in SFTS patients was 0.838 (95% CI: 0.773-0.894), and the optimal cutoff value was 4.068lg copies / ml (sensitivity 74.0%, specificity 83.5%), the AUC for MYO to predict the risk of death in SFTS patients was 0.802 (95% CI: 0.730-0.859), and the optimal cutoff value was 282.4ng / ml (sensitivity 75.3%, specificity 78%), and the AUC for UREA to predict the risk of death in SFTS patients was 0.754 (95% CI: 0.764-0.894), and the optimal cutoff value was 4.068lg copies / ml (sensitivity 74.0%, specificity 83.5%). CI: 0.689-0.817), the best cutoff value was 5.8mmol / L (sensitivity 80.5%, specificity 59.1%), the AUC of AMY-P for predicting the risk of death in SFTS patients was 0.658 (95% CI: 0.581-0.735), and the best cutoff value was 115.0U / L (sensitivity 51.9%, specificity 76.4%). Based on the independent risk factors obtained by Logistic regression analysis, a nomogram model for the prognosis of SFTS patients was established. Figure 3 The model was verified, and the calibration curve approached the diagonal line, indicating that the predicted probability of the model was close to the actual incidence rate, and the constructed nomogram had a high accuracy. Figure 4 The area under the ROC curve of the nomogram was 0.924, 95% CI (0.887-0.960), P < 0.001. This indicates that the established nomogram model has good predictive efficiency. Figure 5 .

[0081] Table 4 AUC of ROC of subjects

[0082]

[0083]

[0084] Example 2: A novel prognostic risk prediction model for bunyavirus infection based on inflammatory biomarkers and its construction method 1. Subjects and methods

[0085] 1.1 Research subjects

[0086] This study is a retrospective analysis. A total of 207 SFTS patients admitted to the Department of Infectious Diseases and the Intensive Care Unit of this hospital from April 1, 2023 to July 18, 2024 were selected as the research subjects, including 89 males and 118 females, with an average age of (64.309±9.978) years. Inclusion criteria: ① Age ≥ 18 years old; ② Meet the diagnostic criteria for SFTS. That is, the case specimens tested positive for novel Bunyavirus nucleic acid. Exclusion criteria: ① Patients with incomplete laboratory-related information; ② Patients diagnosed in the outpatient clinic but not admitted to the hospital; ③ Patients with malignant tumors and blood system diseases. The 28 days after admission were set as the observation window. Patients who died within this time limit were classified as the death group, and patients who continued to survive were included in the survival group. This study was reviewed and approved by the hospital ethics committee.

[0087] 1.2 General Information Collection

[0088] The relevant risk factor data were collected by reviewing the electronic medical records of the selected SFTS during their hospitalization. The clinical data of SFTS included: body temperature, days from onset to diagnosis, length of hospitalization, poor appetite, nausea, vomiting, abdominal pain, diarrhea, lymphadenopathy, changes in mental status, diabetes, hypertension, coronary heart disease, cerebral infarction, smoking history, drinking history, etc.

[0089] 1.3 Laboratory test indicators

[0090] All research subjects collected blood routine, inflammatory factors, CRP, PCT, ferritin and other related inflammatory indicators when SFTS patients were first admitted to the hospital, including white blood cells (WBC), neutrophils (NEU#), lymphocytes (LYM#), the ratio of absolute neutrophil value to absolute lymphocyte value (NLR), red blood cells (RBC), hemoglobin (HGB), platelets (PLT), interleukin IL-1β, interleukin IL-2R, interleukin IL-6, interleukin IL-8, interleukin IL-10, tumor necrosis factor TNF-α, C-reactive protein (CRP), procalcitonin (PCT), ferritin (FER), SFTSV load and other indicators as the observation objects. The blood routine related indicators were detected by Japanese SYSMES blood cell analyzer XE2100; CRP, PCT, FER and other biochemical parameters were detected by Roche C8000 biochemical analyzer; cytokines IL-1β, IL-2R, IL-6, IL-8, IL-10, TNF-α and other cytokines were detected by Soling automatic chemiluminescence analyzer. The SFTSV load was measured by Xi'an Tianlong PANA9600s extraction instrument and GENTIER 96E amplification instrument, and the amplification reagents were produced by Sun Yat-sen University Da'an Gene Co., Ltd. The experimental steps were performed according to the instructions.

[0091] 1.4 Statistical methods

[0092] SPSS 20.0 statistical software was used for data analysis. The Shapiro-Wilk test was used to test the normality of the data. Normally distributed data were expressed as mean ± standard deviation, and skewed distribution data were expressed as median (quartile) M (P25, P75). Independent sample t test was used to compare normal distribution data, Mann-Whitney U test was used to compare skewed distribution data, and χ2 test was used to compare the constituent ratio between the two groups. ROC curves were drawn, and sensitivity, specificity and AUC were calculated. P < 0.05 was considered statistically significant. Binary multivariate logistic regression analysis and Hosmer-Lemeshow test were used to evaluate the model fit. The independent risk factors obtained were used to establish a nomogram model using R language (4.3.1). Bootstrap method was used for internal validation, and C index, calibration curve and ROC curve were used to verify the predictive ability of the model. P < 0.05 was considered statistically significant.

[0093] 2 Results

[0094] 2.1 Comparison of general information between the two groups of patients

[0095] There were no significant differences in gender ratio, history of diabetes, cerebral infarction, hypertension, history of smoking, history of alcoholism, poor appetite, nausea, vomiting, abdominal pain, diarrhea, lymphadenopathy, body temperature, and the number of days from onset to hospitalization between the two groups (P>0.05). However, the proportion of age, history of coronary heart disease, and mental changes in the survival group was lower than that in the death group, and the difference was statistically significant (P<0.05), as shown in Table 1.

[0096] Table 1 General information of patients in the two SFTS groups

[0097]

[0098]

[0099] 2.2 Comparison of blood routine and inflammation-related indicators between the two groups of patients

[0100] There was no significant difference in WBC, NEU#, LYM#, NLR, RBC, and HGB between the two groups (P>0.05); compared with the survival group, the death group had a significant decrease in PLT, and a significant increase in CRP, PCT, FER, IL-1β, IL-2R, IL-6, IL-8, IL-10, and TNF-α, with statistically significant differences (P<0.05). See Table 2.

[0101] Table 2 Comparison of blood routine and inflammation-related indicators between the two groups of patients

[0102]

[0103]

[0104] 2.3 Correlation analysis of independent variables

[0105] The 14 independent variables included were analyzed using Pearson correlation analysis to analyze the correlation between the variables. Figure 6 ,The analysis showed that there was no significant correlation between the independent variables. At the same time, in order to reduce the impact of homoscedasticity on the model, variance homogeneity analysis was performed, and it was found that there was no variable with a variance inflation factor (VIF) greater than 10, so there was no need to eliminate the variable.

[0106] 2.4 Multivariate analysis of prognosis in SFTS patients

[0107] Binary Logistic multivariate analysis was performed with the above 14 variables as independent variables and prognosis as dependent variable. Finally, 4 independent risk factors were identified, including viral load (OR = 2.669, 95% CI (1.764-4.239), P < 0.001), age (OR = 1.162, 95% CI (1.102-1.236), P < 0.001), PCT (OR = 2.758, 95% CI (1.586-5.231), P = 0.001), IL-10 (OR = 1.005, 95% CI (1.001-1.009), P = 0.019) (see Table 3). Establish the regression equation: Ln(P / 1-P)=-15.327+0.982×X1+0.15×X2+1.015×X3+0.005×X4.

[0108] Table 3 Multivariate binary logistic regression analysis of prognosis of SFTS patients

[0109]

[0110] 2.5 Establishment of a prognostic risk warning model for SFTS patients

[0111] The ROC curves were drawn for the variables in the independent risk factors. Figure 7. The AUC of each independent risk factor is shown in Table 4. The AUC for predicting the risk of death in SFTS patients based on age alone was 0.706 (95% CI: 0.628-0.779), and the optimal cutoff value was 64 years old (sensitivity 78.4%, specificity 54.9%); the AUC for viral load (logarithmic value) to predict the risk of death in SFTS patients was 0.822 (95% CI: 0.756-0.883), and the optimal cutoff value was 4.068lg copies / mL (sensitivity 73.0%, specificity 82.0%), the AUC for PCT to predict the risk of death in SFTS patients was 0.770 (95% CI: 0.704-0.831), and the optimal cutoff value was 0.51ng / mL (sensitivity 56.8%, specificity 83.5%), and the AUC for IL-10 to predict the risk of death in SFTS patients was 0.770 (95% CI: 0.710-0.831), and the optimal cutoff value was 0.51ng / mL (sensitivity 56.8%, specificity 83.5%). CI: 0.704-0.831), the optimal cutoff value was 66.6 pg / ml (sensitivity 56.8%, specificity 83.5%). Based on the independent risk factors obtained by Logistic regression analysis, a nomogram model for the prognosis of SFTS patients was established. Figure 8 The model was verified, and the calibration curve approached the diagonal line, indicating that the predicted probability of the model was close to the actual incidence rate, and the constructed nomogram had a high accuracy. Fig. 9 The area under the ROC curve of the nomogram was 0.905, 95% CI (0.862-0.949), P < 0.001. This indicates that the established nomogram model has good predictive efficiency. Fig.10 .

[0112] Table 4 AUC of ROC of subjects

[0113]

[0114] Example 3: New Bunyavirus Infection Prognosis Risk Prediction System

[0115] The embodiment of the present invention provides a novel system for predicting the prognosis risk of Bunyavirus infection, the system comprising:

[0116] A processor and a memory, the memory being coupled to the processor, the memory storing instructions which, when executed by the processor, use the following steps:

[0117] The values ​​of the key model indicators are input into the prediction model to obtain a prediction score for the prognosis risk of novel Bunyavirus infection.

[0118] The key model indicators are selected from the 5 key model indicators of multiple organ dysfunction markers in Example 1 or the 4 key model indicators of inflammatory biomarkers in Example 2.

[0119] Embodiment 4: Computer readable storage medium

[0120] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in Embodiment 1 and / or the method in Embodiment 2 are implemented.

[0121] Of course, the computer executable instructions of a storage medium including computer executable instructions provided by an embodiment of the present invention are not limited to the operations of the method described above, but can also execute related operations in the method provided by any embodiment of the present invention.

[0122] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an 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, and the computer software product 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 an electronic device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0123] 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 divisions, 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.

[0124] Application example 1: Predicting the prognosis of patients infected with a new clinical Bunyavirus

[0125] The data indicators of patients infected with the new Bunyavirus admitted to the clinic are collected and brought into Model 1 of Example 1.

[0126] Example: For example, the prognosis of a patient who is 60 years old, with a viral load of 4 (lg copies / mL), MYO 300ng / mL, UREA 20mmol / L, and AMY-P 100U / L. Substitute the above five indicators into the logistics regression equation: Ln(P / 1-P) = -15.06 + 1.345×X1 + 0.107×X2 + 0.002×X3 + 0.137×X4 + 0.005×X5. In the above formula, X1 is the viral load, X2 is the age, X3 is the myoglobin correlation value, X4 is the urea nitrogen correlation value, and X5 is the pancreatic amylase correlation value. The obtained disease occurrence probability P is 64%.

[0127] Or calculate according to the nomogram: draw a vertical line from the point on the age axis to the scoring standard axis, and the score is 50 points. Similarly, the viral load score is 50 points, the MYO score is 10 points, the UREA score is 50 points, the AMY-P score is 10 points, and the total score is 170 points. Draw a vertical line from the point corresponding to the total score axis to the patient's prognosis analysis axis to obtain the prognosis, and the probability of poor prognosis for this patient is about 64%. The nomogram uses line segments with high and low scores to transform complex regression equations into simple visual line segments, which enhances the practical value. According to the nomogram, the threshold for disease occurrence is 41.5%. If the disease probability is higher than the threshold, it is considered that the possibility of disease is high.

[0128] Application Example 2: Predicting the prognosis of patients infected with a new clinical Bunyavirus

[0129] The data indicators of patients infected with the new Bunyavirus admitted to the clinic are collected and brought into Model 2 of Example 2.

[0130] Example: For example, the prognosis of a patient who is 60 years old, has a viral load of 4.5 (lg copies / mL), PCT 2.5ng / mL, and IL-10 200pg / ml. Substitute the above four indicators into the logistics regression equation Ln(P / 1-P)=-15.327+0.982×X1+0.15×X2+1.015×X3+0.005×X4. In the above formula 2, X1 is the viral load, X2 is the age, X3 is the procalcitonin association value, and X4 is the interleukin-10 association value. The obtained disease occurrence probability P is 83.6%.

[0131] Or calculate according to the nomogram: draw a vertical line from the point on the age axis to the scoring standard axis, and the score is 55 points. Similarly, the viral load score is 30 points, the PCT score is 30 points, the IL-10 score is 10 points, and the total score is 125 points. Draw a vertical line from the point corresponding to the total score axis to the patient's prognosis analysis axis to obtain the prognosis, and the probability of disease occurrence in this patient is about 84%. The nomogram uses line segments with high and low scores to transform complex regression equations into simple visual line segments, which enhances the practical value. According to the nomogram, the threshold for disease occurrence is 34.7%. If the disease probability is higher than the threshold, it is considered that the possibility of disease is high.

[0132] 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 series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements that are inherent to such process, method, article, or apparatus.

[0133] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other 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 embodiments of the present invention.

[0134] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present invention without departing from the spirit and scope of the embodiments of the present invention. Thus, if these modifications and variations of the embodiments of the present invention fall within the scope of the claims of the embodiments of the present invention and their equivalents, the embodiments of the present invention are also intended to include these modifications and variations.

Claims

1. A novel prognosis risk prediction model for bunyavirus infection, characterized in that: The prediction model includes one of the following two prediction models: Model 1: Based on the five key model indicators of multiple organ function damage markers, the new Bunyavirus infection prognosis risk prediction model formula 1 was established: Ln(P / 1-P)=-15.06+1.345×X1+0.107×X2+0.002×X3+0.137×X4+0.005×X5; In the above formula 1, X1 is the viral load, X2 is the age, X3 is the myoglobin correlation value, X4 is the urea nitrogen correlation value, and X5 is the pancreatic amylase correlation value; Model 2: Based on the four key model indicators of inflammatory biomarkers, the new Bunyavirus infection prognosis risk prediction model formula 2 was established: Ln(P / 1-P)=-15.327+0.982×X1+0.15×X2+1.015×X3+0.005×X4; In the above formula 2, X1 is the viral load, X2 is the age, X3 is the procalcitonin association value, and X4 is the interleukin-10 association value.

2. A method for constructing a novel Bunyavirus infection prognosis risk prediction model according to claim 1, characterized in that: The method comprises: Collect case information and test data, compare the data indicators of the survival group and the death group of the new bunyavirus infection, and obtain the independent variables with statistically significant differences; Pearson correlation analysis was performed on the independent variables with statistically significant differences, and the variables with higher correlation were eliminated. The remaining variables were then subjected to binary logistic regression analysis to obtain key model indicators; Based on the key model indicators, a prognosis risk prediction model for novel Bunyavirus infection was established.

3. A novel Bunyavirus infection prognosis risk prediction system, characterized in that: The system comprises: A processor and a memory, the memory being coupled to the processor, the memory storing instructions which, when executed by the processor, use the following steps: The numerical values ​​of the key model indicators are input into the prediction model as claimed in claim 1 to obtain the prognosis risk prediction score of the novel Bunyavirus infection.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program, when executed by a processor, uses the following steps: The numerical values ​​of the key model indicators are input into the prediction model as claimed in claim 1 to obtain the prognosis risk prediction score of the novel Bunyavirus infection.

5. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the calculation steps of the prediction model described in claim 1 are implemented.

6. Use of the novel bunyavirus infection prognosis risk prediction model according to claim 1, the prediction system according to claim 3, the computer-readable storage medium according to claim 4, or the computer program product according to claim 5 in preparing a product for predicting novel bunyavirus infection risk.

7. A novel product for predicting the prognosis risk of Bunyavirus infection, characterized in that: include: A product for measuring key model indicators of the novel Bunyavirus infection prognosis risk prediction model as described in claim 1; and the prediction system of claim 3 or the computer-readable storage medium of claim 4 or the computer program product of claim 5.

Images