A system and method for predicting late-stage schistosomiasis

Abstract

The present invention relates to a system and method for predicting late-stage schistosomiasis. The system comprises a data collector and a processor. After the data collector acquires biomarkers from the blood of a patient to be diagnosed, an SPSS statistical analysis software package embedded in the processor inputs the acquired biomarkers into a discriminant diagnostic model to determine whether the patient has late-stage schistosomiasis. This method enables early detection and intervention, effectively reducing the incidence of new cases of late-stage schistosomiasis.

Description

Technical Field

[0001] The present invention relates to the technical field of medical systems, and in particular to a system and method for predicting late-stage schistosomiasis. Background Art

[0002] Late-stage schistosomiasis is primarily characterized by hepatic and splenic lesions, such as periportal fibrosis, portal hypertension, and splenomegaly and congestion, as well as severe growth and developmental impairment or significant granulomatous colonic proliferation. Tissue fibrosis associated with egg deposition is the most severe outcome of schistosomiasis infection. The long course of illness, high treatment costs, and poor prognosis place a significant psychological and financial burden on patients and their families. Schistosomiasis is an immunological disease, its pathogenesis rooted in the host's immune response to the parasites and eggs. Eggs produced by adult worms residing in the portal vein enter the liver through the bloodstream. Due to their large size, the eggs become lodged in the presinusoidal space, occluding blood vessels and releasing egg antigens that sensitize delayed-type hypersensitive T lymphocytes. These sensitized T lymphocytes then produce a series of lymphokines, which attract inflammatory cells (including macrophages, lymphocytes, and eosinophils) to the eggs, triggering a series of inflammatory reactions and forming egg granulomas. Macrophages and other cells in the egg granuloma release profibrotic cytokines that activate hepatic stellate cells (HSCs) to transform into myofibroblasts. Myofibroblasts, in turn, produce large amounts of extracellular matrix (ECM) and secrete profibrotic factors, leading to an imbalance between fibroblast production and degradation. Without effective intervention, fibrosis continues to develop, ultimately leading to late-stage schistosomiasis. Complete recovery from late-stage schistosomiasis is difficult. Therefore, as cases of late-stage schistosomiasis represent an increasing proportion of the overall schistosomiasis disease spectrum, effective preventive strategies for early detection, diagnosis, and treatment are essential for the effective control of schistosomiasis.

[0003] Currently, the main diagnostic methods for schistosomiasis-associated liver fibrosis include: ① Histological examination, which is a reliable method for diagnosing liver fibrosis but is highly invasive to the tissue, and the sampling site may not reflect the overall condition of the patient's liver; ② Imaging methods, with ultrasound currently being the most widely used method, is used for the diagnosis of schistosomiasis-associated liver disease, assessment and grading of liver fibrosis, and observation of therapeutic efficacy; ③ Body fluid (serum or plasma) markers, including extracellular matrix components, degradation products, enzymes involved in their metabolism, and cytokines, are easy to measure and non-invasive, but their specificity remains to be evaluated. The liver is the primary site for the synthesis of coagulation factors, anticoagulants (such as AT-III, PC, PS), and fibrinolytic substances (such as PLG) in the blood. Damage to liver function and liver parenchyma caused by schistosomiasis, chronic hepatitis B, and cirrhosis may lead to abnormal synthesis of coagulation factors, anticoagulants, and fibrinolytic substances.

[0004] However, existing methods have problems such as low accuracy and low efficiency in judging the development of late-stage schistosomiasis. Summary of the Invention

[0005] Based on the above problems existing in the prior art, the present invention provides a system and method for predicting late-stage schistosomiasis, so as to achieve the purpose of early detection and early intervention, and effectively reduce the incidence of new cases of late-stage schistosomiasis.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A system for predicting late-stage schistosomiasis, comprising:

[0008] A data collector, used for obtaining biomarkers from the blood of a patient to be predicted;

[0009] A processor is connected to the data collector and is embedded with an SPSS statistical analysis software package; the SPSS statistical analysis software package is used to perform the following operations:

[0010] The biomarkers in the patient's blood to be predicted are input into the discriminant diagnosis model to obtain a prediction result.

[0011] Preferably, the discriminant diagnosis model is:

[0012] CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211

[0013] CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621

[0014] Among them, CAS is the prediction value of late schistosomiasis, CCS is the prediction value of chronic schistosomiasis, X1 is the value of the biomarker hemoglobin, X2 is the value of the biomarker monocyte, X3 is the value of the biomarker globulin, X4 is the value of the biomarker gamma-glutamyl transferase, X5 is the value of the biomarker activated partial thromboplastin time, X6 is the value of the biomarker factor VIII activity, and X7 is the value of the biomarker fibrinogen.

[0015] Preferably, the processor further includes:

[0016] a curve generating module connected to the data collector, for obtaining an ROC curve using patients with advanced schistosomiasis and patients with chronic schistosomiasis as state variables, and using the detection values ​​of biomarkers in the blood of patients with advanced schistosomiasis and the detection values ​​of biomarkers in the blood of patients with chronic schistosomiasis as test variables;

[0017] An index determination module, connected to the curve generation module, for obtaining the sensitivity and specificity corresponding to the ROC curve coordinates, and determining the Youden index based on the sensitivity and specificity;

[0018] A critical value determination module, connected to the index determination module, for obtaining the value of the Youden index and using the obtained value as the diagnostic critical value;

[0019] a marker screening module, connected to the data collector, for screening the biomarkers in the blood of the late-stage schistosomiasis patient and the biomarkers in the blood of the chronic schistosomiasis patient to obtain screening biomarkers;

[0020] The model building module is connected to the marker screening module and the critical value determination module respectively, and is used to build a discriminant diagnosis model based on the screening biomarkers and the diagnostic critical value.

[0021] Preferably, the marker screening module comprises:

[0022] The marker screening unit is used to screen the biomarkers in the blood of the late-stage schistosomiasis patient and the biomarkers in the blood of the chronic schistosomiasis patient based on single factors and multiple factors to obtain screening biomarkers.

[0023] Preferably, the processor further includes:

[0024] The storage module is used to store the SPSS statistical analysis software package.

[0025] Preferably, the storage module is a computer-readable storage medium.

[0026] Preferably, the processor is a computer.

[0027] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0028] The system for predicting late-stage schistosomiasis provided by the present invention comprises a data collector and a processor. After the data collector acquires biomarkers from the patient's blood, the processor, embedded with the SPSS statistical analysis software package, inputs the acquired biomarkers into a discriminant diagnostic model to determine whether the patient has late-stage schistosomiasis. This system can achieve early detection and intervention, effectively reducing the incidence of new cases of late-stage schistosomiasis.

[0029] Corresponding to the specific functions implemented by the above-mentioned system for predicting late-stage schistosomiasis, the present invention further provides a method for predicting late-stage schistosomiasis, the method comprising:

[0030] Obtaining biomarkers from the blood of the patient to be predicted;

[0031] Obtaining a discriminant diagnostic model;

[0032] The biomarkers in the patient's blood to be predicted are input into the discriminant diagnosis model to obtain a prediction result.

[0033] Preferably, the discriminant diagnosis model is:

[0034] CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211

[0035] CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621

[0036] Among them, CAS is the prediction value of late schistosomiasis, CCS is the prediction value of chronic schistosomiasis, X1 is the value of the biomarker hemoglobin, X2 is the value of the biomarker monocyte, X3 is the value of the biomarker globulin, X4 is the value of the biomarker gamma-glutamyl transferase, X5 is the value of the biomarker activated partial thromboplastin time, X6 is the value of the biomarker factor VIII activity, and X7 is the value of the biomarker fibrinogen.

[0037] Preferably, the process of constructing the discriminant diagnosis model includes:

[0038] The ROC curve was obtained by taking patients with advanced schistosomiasis and patients with chronic schistosomiasis as state variables and the detection values ​​of biomarkers in the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis as test variables;

[0039] Obtaining the sensitivity and specificity corresponding to the ROC curve coordinates, and determining the Youden index based on the sensitivity and the specificity;

[0040] Obtaining a value of the Youden index, and using the obtained value as a diagnostic critical value;

[0041] screening the biomarkers in the blood of the patients with advanced schistosomiasis and the biomarkers in the blood of the patients with chronic schistosomiasis based on single factors and multiple factors to obtain screening biomarkers;

[0042] A discriminant diagnostic model is constructed based on the screening biomarkers.

[0043] Since the technical effects achieved by the method for predicting late-stage schistosomiasis provided by the present invention are the same as the technical effects achieved by the system for predicting late-stage schistosomiasis provided above, they will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only 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.

[0045] Figure 1 A schematic diagram of the structure of a system for predicting late-stage schistosomiasis provided by the present invention;

[0046] Figure 2 A flow chart of the method for predicting late-stage schistosomiasis provided by the present invention. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0048] The purpose of the present invention is to provide a system and method for predicting late-stage schistosomiasis, which can achieve the purpose of early detection and early intervention, and effectively reduce the incidence of new cases of late-stage schistosomiasis.

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] like Figure 1 As shown, the system for predicting late-stage schistosomiasis provided by the present invention comprises: a data collector and a processor. The processor is connected to the data collector. The data collector is used to obtain biomarkers from the blood of the patient to be predicted. The processor is embedded with the SPSS statistical analysis software package. The SPSS statistical analysis software package is used to input the biomarkers from the blood of the patient to be predicted into a discriminant diagnostic model to obtain a prediction result. The processor used in the present invention can be a computer or other device capable of running and processing software.

[0051] Among them, the discriminant diagnosis model adopted by the present invention is:

[0052] CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211

[0053] CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621

[0054] where CAS is the prediction value for advanced schistosomiasis, CCS is the prediction value for chronic schistosomiasis, X1 is the value of the biomarker hemoglobin (HGB), X2 is the value of the biomarker monocyte (MON), X3 is the value of the biomarker globulin (GLB), X4 is the value of the biomarker gamma-glutamyl transferase (GGT), X5 is the value of the biomarker activated partial thromboplastin time (APTT), X6 is the value of the biomarker factor VIII activity (VIII), and X7 is the value of the biomarker fibrinogen (Fbg).

[0055] In the present invention, the data collector can be a hospital-based testing instrument used to obtain blood biomarkers, wirelessly connected to a processor that crawls the data generated by the testing instrument. Alternatively, the data collector can be a computer, and the blood biomarkers obtained can be manually input.

[0056] Furthermore, to improve the accuracy of prediction results, the processor employed in the present invention may further include: a curve generation module, an index determination module, a critical value determination module, a marker screening module, and a model construction module. The curve generation module is connected to the data acquisition device. The index determination module is connected to the curve generation module. The critical value determination module is connected to the index determination module. The marker screening module is connected to the data acquisition device. The model construction module is connected to the marker screening module and the critical value determination module, respectively.

[0057] After the data collector crawls and obtains biomarkers from the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis, the curve generation module uses the patients with advanced schistosomiasis and patients with chronic schistosomiasis as state variables and the detection values ​​of the biomarkers in the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis as test variables to generate the ROC curve. The index determination module obtains the sensitivity and specificity corresponding to the coordinates of the ROC curve and calculates the maximum Youden index using [(sensitivity + specificity) - 1]. The critical value determination module obtains the value of the Youden index and uses the obtained number as the diagnostic critical value, which is the optimal diagnostic critical value. The marker screening module screens the biomarkers in the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis to obtain screening biomarkers. The model construction module constructs a discriminant diagnostic model based on the screening biomarkers and the diagnostic critical value.

[0058] For example, the marker screening module can be provided with a marker screening unit for screening biomarkers in the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis based on single-factor and multi-factor analysis to obtain screening biomarkers. For the single-factor analysis, the quantitative values ​​of the 22 included blood biomarkers were converted to qualitative values ​​of 0 and 1 using the optimal diagnostic cutoff value as the standard. A chi-square test was then performed on the data for six biomarkers, including SJ and the five hepatitis B test items. The results showed that, with the exception of seven biomarkers, including SJ, RBC, HBsAg, HBsAb, HBeAg, HBeAb, and HBcAb, which showed no statistical significance, significant differences were observed between the AS and CS groups for the other biomarkers. However, because the P values ​​for RBC and HBcAb were <0.2, the present invention still included them in the multi-factor analysis based on the initial statistical constraints.

[0059] Multivariate analysis: 23 blood biomarkers with P < 0.2 in univariate analysis were subjected to multivariate analysis, and finally 9 blood biomarkers including HGB, LYM, MON, DBiL, GLB, GGT, APTT, Fbg and VIII were screened out.

[0060] Furthermore, the curve generation module, index determination module, critical value determination module, marker screening module and model construction module provided above can all be software functional units.

[0061] Furthermore, to increase the software's operating speed, the processor further includes a storage module for storing the SPSS statistical analysis software package. In the present invention, the storage module can be either a software functional unit or a computer-readable storage medium. In the case of a computer-readable storage medium, the storage module can be sold or used as a standalone product.

[0062] The following provides specific verification examples to illustrate the technical effects that can be achieved by the system for predicting late-stage schistosomiasis provided by the present invention.

[0063] Example 1

[0064] In this example, the male to female ratios of patients with advanced schistosomiasis (AS) and chronic schistosomiasis (CS) participating in the study were 1:0.76 and 1:1.03, respectively (χ = 1.567, P = 0.211). The mean age of male AS and CS patients was 64.1 and 61.8 years, respectively, while that of female patients was 57.8 and 59.9 years. There was no statistically significant difference in the mean age between the two groups (t Male =2.401,t Female =1.484, Pall>0.05). The AS and CS groups were matched in terms of gender and age, as shown in Table 1.

[0065] Table 1 Basic information of patients

[0066]

[0067]

[0068] Using AS and CS patients as the state variables and the blood biomarker values ​​as the test variables, the sensitivity and specificity corresponding to the ROC curve coordinates were used to calculate the maximum Youden index, and the resulting value was used to determine the optimal diagnostic cutoff for the biomarker values ​​in the two patient groups. The analysis results showed that optimal diagnostic cutoffs could not be calculated for 8 of the 30 blood biomarkers, and therefore these 8 blood biomarkers were discarded, as shown in Table 2.

[0069] Table 2 Optimal diagnostic cutoff values ​​of blood biomarkers for screening AS and CS patients by ROC

[0070]

[0071] The quantitative values ​​of the 22 included blood biomarkers were converted to qualitative values ​​of 0 and 1 using the optimal diagnostic cutoff value as the standard. Chi-square tests were then performed on the data for six biomarkers, including SJ and the five hepatitis B test items. The results showed that, with the exception of seven biomarkers, including SJ, RBC, HBsAg, HBsAb, HBeAg, HBeAb, and HBcAb, which showed no statistical significance, significant differences were observed between the AS and CS groups for the other biomarkers (Table 4). However, because the P values ​​for RBC and HBcAb were <0.2, they were still included in the multivariate analysis according to the initial statistical constraints, as shown in Table 3.

[0072] Table 3 Univariate analysis of qualitative data of blood biomarkers in AS and CS groups

[0073]

[0074] The 23 blood biomarkers with P < 0.2 in the univariate analysis were subjected to multivariate analysis, and finally 9 blood biomarkers including HGB, LYM, MON, DBiL, GLB, GGT, APTT, Fbg and VIII were included, as shown in Table 4.

[0075] Table 4 Multivariate analysis of qualitative data of blood biomarkers in AS and CS groups

[0076]

[0077]

[0078] The AS and CS groups were distinguished based on blood biomarkers. The FDA model was constructed using the nine biomarkers selected based on multivariate analysis. Based on the statistical analysis, seven statistically significant variables were identified: HGB (X1), MON (X2), GLB (X3), GGT (X4), APTT (X5), VIII (X6), and Fbg (X7). The following discriminant function was obtained (Wilks' lambda = 0.624, χ2 = 125.033, df = 7, P = 0.000):

[0079] CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211

[0080] CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621

[0081] The accuracy of the FDA model was self-assessed using a cross-validation method. The classification results showed that 86.7% of the participants were correctly classified into the AS and CS groups, as shown in Table 5.

[0082] Table 5 Classification results of original and cross-validation methods

[0083]

[0084] Furthermore, the blood biomarker data of the 109 retained CS patients were replaced with a discriminant function, and the CAS and CCS values ​​were calculated separately. By comparing the CAS and CCS values, the CS patients not included in the statistical analysis were classified according to the following principle: if CAS > CCS, they were considered to have AS; otherwise, they were considered to have CS. Follow-up visits were conducted in 2020 to determine whether these patients had developed AS. A total of 7 CS patients were lost to follow-up. The results showed that of the 29 patients diagnosed with AS by the discriminant function, 18 eventually developed AS, with a concordance rate of 62.1%. Among the 73 patients diagnosed with CS, 8 eventually developed AS, accounting for 11.0% of the interviewed patients, for an overall concordance rate of 81.4%, as shown in Table 6.

[0085] Table 6 Results of follow-up visits for 109 CS patients

[0086]

[0087] In summary, this characteristic framework is a reliable prediction model that combines clinically accessible indicators. It plays an important guiding role in effectively controlling the occurrence of late-stage schistosomiasis and lays a solid foundation for achieving the goal of schistosomiasis elimination.

[0088] This example retrospectively compared and analyzed 36 body fluid (serum / plasma) markers and related clinical data of 271 schistosomiasis patients (132 CS patients and 139 AS patients). It was found that HGB, MON, GLB, GGT, APTT, VIII, and Fbg were associated with fibrosis. The new non-invasive diagnostic function model established in the present invention can predict the possibility of chronic schistosomiasis progressing to late-stage schistosomiasis in advance. This model has sufficient reliability in diagnosing fibrosis and can predict the progression of liver fibrosis.

[0089] In the FDA model ultimately constructed from seven markers in this embodiment, three markers reflect coagulation function. The life cycle of adult schistosomiasis, including parasitism and migration in the venous system and the deposition of worm eggs in liver tissue, causes specific pathological reactions in the host. In theory, vascular damage first causes a local inflammatory reaction, followed by an imbalance in the coagulation and fibrinolytic systems. The interaction between the two ultimately leads to systemic pathological reactions in the host. Systemic coagulation, as a subsequent response of inflammation to schistosomiasis parasitism, plays an important role in the compensation of parasitic immunity. However, to maintain the homeostasis of the blood system, the fibrin excessively secreted in the coagulation needs to be further degraded by fibrinolytic factors such as plasminogen and fibrinolytic protein. Previous studies have reported abnormal coagulation function in patients with schistosomiasis, especially in patients with advanced schistosomiasis. If the coagulation and anticoagulation systems, as well as the fibrinolytic and antifibrinolytic systems, are in balance, a hypercoagulable state or bleeding tendency may occur. Elevated factor VIII is primarily seen in hypercoagulable states and thrombotic disorders. This may be due to the deposition of numerous eggs within the mesenteric vessels after schistosoma japonicum infection, where egg antigens stimulate the vascular wall and activate the coagulation system. Currently, there are no clinically applicable serum biomarkers or assays to assess fibrosis in patients with advanced schistosomiasis. Activated partial thromboplastin time (APTT), fibrinogen globulin (Fbg), and factor VIII activity may be good candidates.

[0090] In summary, through the establishment and validation of the FDA model, the present invention has found that a discriminant function established using body fluid (serum / plasma) markers can effectively provide risk warnings for the occurrence of AS. This is a reliable predictive model that combines clinically accessible indicators and is highly practical. This model plays an important guiding role in effectively controlling the occurrence of AS and lays a solid foundation for achieving the goal of eliminating schistosomiasis. The system provided by the present invention will further enable early therapeutic intervention for CS patients who are likely to develop AS, establish optimal treatment strategies for patients with chronic schistosomiasis, and effectively prevent the development of AS.

[0091] Corresponding to the specific functions implemented by the above-mentioned system for predicting late-stage schistosomiasis, the present invention also provides a method for predicting late-stage schistosomiasis, such as Figure 2 As shown, the method includes:

[0092] Step 100: Obtain biomarkers from the patient's blood to be predicted.

[0093] Step 101: Obtain a discriminant diagnosis model.

[0094] Step 102: Input the biomarkers in the patient's blood to be predicted into the discriminant diagnosis model to obtain a prediction result.

[0095] Preferably, the discriminant diagnosis model is:

[0096] CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211

[0097] CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621

[0098] Among them, CAS is the prediction value of late schistosomiasis, CCS is the prediction value of chronic schistosomiasis, X1 is the value of biomarker HGB, X2 is the value of biomarker MON, X3 is the value of biomarker GLB, X4 is the value of biomarker GGT, X5 is the value of biomarker APTT, X6 is the value of biomarker VIII, and X7 is the value of biomarker Fbg.

[0099] Preferably, the process of constructing the discriminant diagnosis model includes:

[0100] The ROC curve was obtained by taking patients with advanced schistosomiasis and patients with chronic schistosomiasis as state variables and the detection values ​​of biomarkers in the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis as test variables.

[0101] The sensitivity and specificity corresponding to the ROC curve coordinates were obtained, and the Youden index was determined based on the sensitivity and specificity.

[0102] The numerical value of the Youden index was obtained and used as the diagnostic cutoff value.

[0103] Based on single factor and multifactor screening of biomarkers in the blood of patients with late-stage schistosomiasis and biomarkers in the blood of patients with chronic schistosomiasis, screening biomarkers were obtained.

[0104] Construct a discriminant diagnostic model based on screening biomarkers.

[0105] Example 2

[0106] Based on the technical solution provided above, in this embodiment, the case-control study included two groups of cases from eight counties in the Poyang Lake area of ​​Jiangxi Province (Nanchang, Xinjian, Jinxian, Xingzi, Duchang, Yongxiu, Poyang, and Yugan), which are severely affected by schistosomiasis. A total of 271 cases were recruited from February to March 2013, including 139 AS patients and 132 CS patients. The diagnostic criteria were based on the "Diagnostic Criteria for Schistosomiasis" (WS261-2006) issued by the Ministry of Health of the People's Republic of China. These cases did not include metabolic hereditary liver diseases, other parasitic infections, tumors, cardiovascular system, kidney diseases, respiratory system, digestive system, diabetes, infection and tissue necrosis, bacteremia, and systemic lupus erythematosus, while minimizing the confounding effects of other liver diseases (except hepatitis B). In addition, this embodiment also retained 109 CS patients to observe whether they had developed AS in 2020 to evaluate the accuracy of the discriminant function warning.

[0107] All study subjects were required to obtain cubital venous blood under sterile conditions in the morning and after fasting, and biomarker testing was completed within 2 hours. Biomarkers included 36 tests, including complete blood count, liver function, fibrin degradation product D-dimer, coagulation markers, HBV, alpha-fetoprotein, and four liver fibrosis tests (see Table 7).

[0108] Table 7 Blood biomarker detection methods and product providers

[0109]

[0110]

[0111] Among the 36 blood biomarkers, 30 are continuous variables. The normality test of these variables indicates that not all variable data are normally distributed. Although logarithmic correction is taken, some data are still non-normally distributed. Therefore, to facilitate unified data analysis, this embodiment converts these continuous variables into categorical variables. That is, the receiving characteristics (ROC) curve is used to evaluate the various biomarkers of AS and CS patients, find the optimal clinical diagnostic critical point, and complete qualitative classification, that is, when it is less than the critical value, it is assigned a value of "0", otherwise it is assigned a value of "1". At the same time, biomarkers with area under the ROC curve (AUC) ≤ 0.5 or P> 0.05 are eliminated.

[0112] Statistical analysis was performed using SPSS Statistics 22.0 software (SPSS Inc., Chicago, IL, USA) with an α-level of 0.05. The data analysis included the following:

[0113] First, general characteristics of the participants were described based on gender and age to ensure consistency across samples. Second, univariate analysis of the differences in biomarker categorical variables between the AS and CS groups was performed using chi-square tests to identify variables that could be used for the next step.

[0114] We also considered the potential for associations between variables that were not significantly different in univariate analysis and other confounding variables. To prevent the true effect of these variables from being masked by the influence of other confounding factors, we included all variables with a P value < 0.2 in the univariate analysis in the multivariate analysis. Variables with a P value < 0.10 were then retained in the multivariate model through a stepwise backward selection process. The final report presents odds ratios (ORs), 95% confidence intervals (95% CIs), and significance levels (P-values).

[0115] Fisher discriminant analysis (FDA) is a commonly used multivariate statistical method that uses projection techniques for dimensionality reduction to determine linear functions of variables in order to maximize the differences between samples from multiple classes and minimize the differences between samples from the same class. Therefore, this example uses the FDA model selection stepwise method to establish a discriminant function based on the variables selected by the multivariate analysis, and then performs a self-test on the established discriminant function.

[0116] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0117] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A system for predicting late-stage schistosomiasis, characterized in that: include: A data collector, used for obtaining biomarkers from the blood of a patient to be predicted; A processor is connected to the data collector and is embedded with an SPSS statistical analysis software package; the SPSS statistical analysis software package is used to perform the following operations: Inputting the biomarkers in the patient's blood to be predicted into a discriminant diagnosis model to obtain a prediction result; The processor further includes: a curve generating module connected to the data collector, for obtaining an ROC curve using patients with advanced schistosomiasis and patients with chronic schistosomiasis as state variables, and using the detection values ​​of biomarkers in the blood of patients with advanced schistosomiasis and the detection values ​​of biomarkers in the blood of patients with chronic schistosomiasis as test variables; An index determination module, connected to the curve generation module, for obtaining the sensitivity and specificity corresponding to the ROC curve coordinates, and determining the Youden index based on the sensitivity and specificity; a critical value determination module, connected to the index determination module, for obtaining the value of the Youden index and using the obtained value as the diagnostic critical value; the diagnostic critical value is the optimal diagnostic critical value; A marker screening module, connected to the data collector, is used to screen the biomarkers in the blood of the patients with advanced schistosomiasis and the biomarkers in the blood of the patients with chronic schistosomiasis to obtain screening biomarkers; wherein, in a univariate analysis, the quantitative values ​​of the 22 included blood biomarkers were converted to qualitative values ​​of 0 and 1 based on the optimal diagnostic critical value, and then a chi-square test was performed together with the six biomarker data of SJ and hepatitis B five items. The results showed that the seven biomarkers of SJ, RBC, HBsAg, HBsAb, HBeAg, HBeAb and HBcAb were not statistically significant; in a multivariate analysis, the 23 blood biomarkers with P < 0.2 in the univariate analysis were subjected to a multivariate analysis, and finally nine blood biomarkers of HGB, LYM, MON, DBiL, GLB, GGT, APTT, Fbg and VIII were screened out; A model building module is connected to the marker screening module and the critical value determination module, respectively, for building a discriminant diagnostic model based on the screening biomarkers and the diagnostic critical value; wherein the discriminant diagnostic model is: CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211; CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621; Among them, CAS is the prediction value of late schistosomiasis, CCS is the prediction value of chronic schistosomiasis, X1 is the value of the biomarker hemoglobin, X2 is the value of the biomarker monocyte, X3 is the value of the biomarker globulin, X4 is the value of the biomarker gamma-glutamyl transferase, X5 is the value of the biomarker activated partial thromboplastin time, X6 is the value of the biomarker factor VIII activity, and X7 is the value of the biomarker fibrinogen.

2. The system for predicting late-stage schistosomiasis according to claim 1, characterized in that: The marker screening module comprises: The marker screening unit is used to screen the biomarkers in the blood of the late-stage schistosomiasis patient and the biomarkers in the blood of the chronic schistosomiasis patient based on single factors and multiple factors to obtain screening biomarkers.

3. The system for predicting late-stage schistosomiasis according to claim 1, characterized in that: The processor further includes: The storage module is used to store the SPSS statistical analysis software package.

4. The system for predicting late-stage schistosomiasis according to claim 3, characterized in that: The storage module is a computer-readable storage medium.

5. The system for predicting late-stage schistosomiasis according to claim 1, characterized in that: The processor is a computer.

6. A method for predicting late-stage schistosomiasis, characterized in that: include: Obtaining biomarkers from the blood of the patient to be predicted; Obtaining a discriminant diagnostic model; Inputting the biomarkers in the patient's blood to be predicted into the discriminant diagnosis model to obtain a prediction result; The construction process of the discriminant diagnosis model includes: The ROC curve was obtained by taking patients with advanced schistosomiasis and patients with chronic schistosomiasis as state variables and the detection values ​​of biomarkers in the blood of patients with advanced schistosomiasis and patients with chronic schistosomiasis as test variables; Obtaining the sensitivity and specificity corresponding to the ROC curve coordinates, and determining the Youden index based on the sensitivity and the specificity; Obtaining a value of the Youden index, and using the obtained value as a diagnostic critical value; the diagnostic critical value is an optimal diagnostic critical value; The biomarkers of the blood of the patients with late-stage schistosomiasis and the biomarkers of the blood of the patients with chronic schistosomiasis were screened based on univariate and multivariate analysis to obtain screening biomarkers; wherein, univariate analysis: the quantitative values ​​of the 22 included blood biomarkers were converted to qualitative values ​​of 0 and 1 based on the optimal diagnostic critical value, and then chi-squared test was performed together with the six biomarker data of SJ and hepatitis B five items. The results showed that the seven biomarkers of SJ, RBC, HBsAg, HBsAb, HBeAg, HBeAb and HBcAb had no statistical significance; multivariate analysis: the 23 blood biomarkers with P < 0.2 in the univariate analysis were subjected to multivariate analysis, and finally nine blood biomarkers of HGB, LYM, MON, DBiL, GLB, GGT, APTT, Fbg and VIII were screened; A discriminant diagnostic model is constructed based on the screening biomarkers; wherein the discriminant diagnostic model is: CAS=0.923X1+3.058X2+2.672X3+2.694X4+4.364X5+2.226X6+7.744X7-8.211 CCS=1.843X1+1.930X2+1.002X3+1.586X4+2.893X5+2.863X6+8.875X7-7.621 Among them, CAS is the prediction value of late schistosomiasis, CCS is the prediction value of chronic schistosomiasis, X1 is the value of the biomarker hemoglobin, X2 is the value of the biomarker monocyte, X3 is the value of the biomarker globulin, X4 is the value of the biomarker gamma-glutamyl transferase, X5 is the value of the biomarker activated partial thromboplastin time, X6 is the value of the biomarker factor VIII activity, and X7 is the value of the biomarker fibrinogen.

Images