Liver disease patient long-term prognosis prediction system and method

Abstract

The invention discloses a long-term prognosis prediction system and method for patients with liver diseases, and the method comprises the following steps: S1, collecting clinical data, including anthropometric data, vital signs, laboratory data and albumin binding capacity obtained by specific detection, of patients with acute decompensation of liver cirrhosis and chronic plus acute liver failure; s2, a competitive risk model for predicting death of patients suffering from acute decompensation of liver cirrhosis and chronic and acute hepatic failure after admission for one year is constructed, the prediction model is constructed by adopting the competitive risk model, and a convenient prediction tool is made by adopting a dynamic column diagram visual prediction model; and S3, evaluating the prediction performance of the model through the working curve of the subject. According to the present invention, the index relationship between the albumin binding capacity and the long-term prognosis of the decompensated liver cirrhosis patient and the chronic plus acute liver failure patient is established so as to provide the important clinical significance, such that the clinical management can be further optimized, and the drug treatment can be guided.

Description

Technical Field

[0001] The present invention relates to the field of liver disease prediction, and in particular to a system and method for predicting the long-term prognosis of liver disease patients. Background Art

[0002] Acute decompensation (AD) is a complication of cirrhosis that occurs acutely in patients with decompensated cirrhosis, including hepatic encephalopathy, ascites, esophageal varicose vein bleeding, bacterial infection, etc. At the same time, factors such as acute onset of viral hepatitis, heavy drinking, use of drugs that damage the liver, bacterial or fungal infection, and acute gastrointestinal bleeding can all cause acute decompensation of cirrhosis, causing a sharp deterioration of liver function, resulting in liver and / or extrahepatic organ failure, which is called acute-on-chronic liver failure (ACLF). The occurrence of complications greatly increases the risk of death in patients with decompensated cirrhosis, and the risk of death in patients with cirrhosis who develop ACLF is further increased, with a 90-day mortality rate of up to 20% to 30%. There is currently no specific treatment, and liver transplantation is the only effective treatment measure that can improve their survival rate. Patients with acute decompensation of cirrhosis and ACLF can survive for a relatively long time after timely treatment, but because more than half of the patients lack definite susceptibility factors or inducing events, there is still a high risk of death without transplantation. Therefore, there is an urgent clinical need for prognostic factors that can predict the long-term survival of patients with decompensated cirrhosis and acute-on-chronic liver failure, which can help manage high-risk groups and the course of the disease.

[0003] Human serum albumin (HSA) is the most abundant protein in human plasma, accounting for about 50% of total plasma protein. Human serum albumin is not only the main component for maintaining plasma colloidal osmotic pressure, but also has the functions of binding, transporting substances, anti-oxidation, anti-coagulation and anti-thrombosis, regulating immune function, maintaining capillary integrity, promoting cardiac positive inotropy, and protecting nerves. Among them, binding ability is the main function of albumin molecules. Albumin can bind to many endogenous and exogenous ligands, thanks to its unique molecular structure. HSA has a globular heart-shaped conformation and contains three homologous domains, represented by I (1-195), II (196-383) and III (384-585). Each domain is composed of two subdomains, A and B. Each subdomain is composed of a separate α-helix, which mediates binding to various endogenous and exogenous ligands. Two important drug binding sites, Sudlow I and Sudlow II, are located in subdomains IIA and IIIA, respectively. The former mediates the binding of drugs such as warfarin and phenylbutazone, while the latter has a preferential affinity for ibuprofen. In end-stage liver disease, albumin binding capacity is found to be reduced, which may be due to the damage to the molecular structure of circulating human serum albumin caused by factors such as severe systemic inflammation and oxidative stress in cirrhosis, which in turn affects the domain structure of the albumin molecule. Damage to the binding function of albumin molecules includes not only impaired binding to drugs, but also damage to binding to bilirubin, fatty acids, metal ions, etc. At the same time, albumin binding capacity is also related to the short-term clinical outcomes of patients with cirrhosis and acute-on-chronic liver failure. The lower the albumin binding capacity, the higher the mortality rate within 28 and 90 days after admission. However, the potential value of albumin binding capacity for the long-term prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure remains to be confirmed. Exploring the relationship between albumin binding capacity and the long-term prognosis of acute decompensation of cirrhosis and acute-on-chronic liver failure has great clinical significance. It can reflect the degree of damage to albumin molecules and the steady-state changes in the body's internal environment, and can be developed as a new clinical biomarker to further optimize clinical management and guide drug treatment. Summary of the invention

[0004] The purpose of the present invention is to provide a system and method for predicting the long-term prognosis of patients with liver diseases, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, one aspect of the present invention provides a long-term prognosis prediction system for patients with liver disease, wherein the prognosis prediction system is for patients with decompensated cirrhosis and acute-on-chronic liver failure, and comprises a data collection module, a model building module, and an evaluation and prediction module, wherein:

[0006] The data collection module is used to collect clinical data of patients with acute decompensation of liver cirrhosis and acute-on-chronic liver failure, including anthropometric data, vital signs, laboratory data, and albumin binding capacity obtained by specific detection; the albumin binding capacity obtained by specific detection is evaluated by experimentally measuring the residual binding amount of albumin binding site II to the specific fluorescent marker dansylsarcosine;

[0007] The model building module is used to build a prediction model for the death of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure one year after admission. The prediction model is built using a competing risk model, and a dynamic nomogram visualization prediction model is used to create a convenient prediction tool;

[0008] The prediction evaluation module is used to evaluate the prediction performance of the model through the receiver operating curve.

[0009] Furthermore, the prognostic factors of the competing risk model for predicting long-term mortality in patients with acute decompensation of cirrhosis and acute-on-chronic liver failure include albumin binding capacity, mean arterial pressure, white blood cell count, and international normalized ratio.

[0010] Furthermore, the method for predicting the long-term prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure is used to predict the 1-year survival rate.

[0011] Furthermore, the prediction model formula is:

[0012] Prognostic score = -0.0136*albumin binding capacity -0.0210*mean arterial pressure +0.0767*white blood cell count +0.7374*international normalized ratio

[0013] The albumin binding capacity (%) = fluorescence in the ultrafiltrate of the standard / fluorescence in the ultrafiltrate of the sample × 100. If the prognostic score is ≥ -1.48, it is a high-risk group for death, and if the prognostic score is < -1.48, it is a low-risk group for death.

[0014] Another aspect of the present invention provides a method for predicting the long-term prognosis of a patient with liver disease, wherein the method is for patients with decompensated liver cirrhosis and acute-on-chronic liver failure, and comprises the following steps:

[0015] Step S1, collecting clinical data of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure, including anthropometric data, vital signs, laboratory data, and albumin binding capacity obtained by specific detection;

[0016] Step S2, constructing a competing risk model for predicting death of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure one year after hospitalization, wherein the prediction model is constructed using a competing risk model, and a dynamic nomogram visualization prediction model is used to produce a convenient prediction tool;

[0017] Step S3, evaluating the prediction performance of the model through the receiver operating curve.

[0018] Furthermore, the albumin binding capacity obtained by the specific detection is evaluated by experimentally measuring the residual binding amount of albumin binding site II to the specific fluorescent marker dansylsarcosine.

[0019] Furthermore, the prognostic factors of the competing risk model for predicting long-term mortality in patients with acute decompensation of cirrhosis and acute-on-chronic liver failure include albumin binding capacity, mean arterial pressure, white blood cell count, and international normalized ratio.

[0020] Furthermore, the method for predicting the long-term prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure is used to predict the 1-year survival rate.

[0021] Furthermore, the prediction model formula is:

[0022] Prognostic score = -0.0136*albumin binding capacity -0.0210*mean arterial pressure +0.0767*white blood cell count +0.7374*international normalized ratio

[0023] The albumin binding capacity (%) = fluorescence in the ultrafiltrate of the standard / fluorescence in the ultrafiltrate of the sample × 100. If the prognostic score is ≥ -1.48, it is a high-risk group for death, and if the prognostic score is < -1.48, it is a low-risk group for death.

[0024] Compared with the prior art, the present system and method have the following advantages:

[0025] 1. The present invention can accurately evaluate the long-term survival probability of hospitalized patients with acute decompensation of cirrhosis and acute-on-chronic liver failure through rapid and simple laboratory tests, timely identify people at high risk of death, provide early treatment to avoid deterioration of the disease or perform liver transplantation as soon as possible to ensure maximum survival; for people at low risk of death, provide symptomatic treatment for corresponding complications, control the occurrence and development of subsequent complications, and prolong the survival of patients with cirrhosis.

[0026] 2. The present invention has a high efficacy in predicting the 1-year mortality rate of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure, which is significantly higher than the conventional Model for End-stage Liver Disease (MELD) score, with an area under the AUC curve of 0.80 vs. 0.76 (p = 0.02).

[0027] 3. The present invention establishes a prediction model for the 1-year prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure, and converts it into a webpage tool. By inputting the values ​​of four parameters, the corresponding scoring scores and 1-year survival probabilities can be obtained, thereby completing the risk assessment of patients with cirrhosis. The operation is simple and convenient, and the accuracy is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 The present invention is a flow chart of a method for predicting the long-term prognosis of patients with liver disease.

[0029] Figure 2 Dynamic nomogram for the prognostic model of the test cohort.

[0030] Figure 3 ROC curve diagram for evaluating the performance of the prognostic prediction model for the test cohort.

[0031] Figure 4 ROC curve diagram for evaluating the effectiveness of the prognostic prediction model in the validation cohort. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0033] like Figure 1 The flowchart of the method of the present invention is shown. The present invention provides a method for predicting the long-term prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure based on human serum albumin binding capacity. The specific prediction model construction method includes the following steps:

[0034] Step S1, collecting clinical data of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure, including anthropometric data, vital signs, laboratory data, and albumin binding capacity obtained by specific detection;

[0035] Step S2, constructing a competing risk model and dynamic nomogram for predicting mortality of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure one year after admission;

[0036] Step S3, evaluating the prediction performance of the model through the receiver operating characteristic curve (ROC).

[0037] Clinical cohort construction in the present invention: This study prospectively and non-selectively screened patients with acute decompensation of cirrhosis and acute-on-chronic liver failure who were admitted to the Department of Infectious Diseases, Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine between June 2016 and November 2018, and finally enrolled 385 cases for analysis. All procedures involved were implemented in accordance with the principles of the Declaration of Helsinki and the International Conference on Harmonization and Good Clinical Practice Guidelines. The present invention involves human participants, and the research protocol was reviewed and approved by the Ethics Committee of Ruijin Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, with the ethics approval number:

[2018] Lunshen No.

[162] .

[0038] The inclusion criteria of the present invention are: (1) age 18-80 years old; (2) cirrhosis: cirrhosis diagnosed in the past or during the current hospitalization. The diagnosis of cirrhosis is based on: liver tissue pathological diagnosis; or comprehensive judgment through imaging (magnetic resonance imaging, CT, B-mode ultrasound), gastrointestinal endoscopy (esophageal-gastric varices, portal hypertension signs), liver elasticity examination and corresponding clinical manifestations of cirrhosis and / or laboratory test indicators; (3) This admission is non-selective, and the reason for admission is one or more of the following combinations of cirrhosis decompensation events: ascites (grade 2-3), upper gastrointestinal bleeding, jaundice (total bilirubin ≥5mg / dL), hepatic encephalopathy, bacterial / fungal infection.

[0039] The exclusion criteria of the present invention are: (1) age < 18 years or age > 80 years; (2) after liver transplantation; (3) receiving commercial albumin solution infusion, plasma infusion, plasma exchange, artificial liver, etc. within 15 days before enrollment; (4) hepatocellular carcinoma at any stage and other advanced malignant tumors; (5) combined with acute or chronic extrahepatic diseases of other systems that affect short-term prognosis, such as chronic kidney disease in the uremic stage (requiring dialysis treatment), chronic left heart failure, obstructive pulmonary disease, chronic respiratory failure, etc.; (6) long-term use of immunosuppressants for non-liver disease reasons, such as nephrotic syndrome, rheumatic system diseases, anti-rejection reaction after organ transplantation, etc.; (7) long-term use of anticoagulant drugs, such as warfarin for atrial fibrillation, etc.; (8) this admission is elective, such as only to complete the scheduled diagnosis and treatment, including but not limited to liver biopsy puncture, splenectomy, TIPS (Transjugular Intrahepatic Portosystemic Shunt), HVPG measurement (Hepatic Venous Pressure Gradient, Hepatic Venous Pressure Gradient), endoscopic ligation, MDT consultation (Multi-Disciplinary Team), simple reexamination, etc.; (9) HIV antibody positive;

[0040] (10) Pregnant or lactating women; (11) Patients who refuse to participate in this study and refuse to sign the informed consent form; (12) None of the above conditions are met, but the patient is temporarily unable to sign the informed consent form due to coma or other reasons, and there is no legal agent to sign for them. Based on the patient's condition, it is estimated that the patient may not be able to wake up and sign the informed consent form.

[0041] Within 48 hours after enrollment, 5 mL of peripheral venous blood was collected from the patients and the serum was immediately separated and frozen in a refrigerator at -80 degrees Celsius. The baseline anthropometric data, medical history information, vital signs, and laboratory data of the enrolled patients were collected through the electronic medical record information system. Clinical data collection included: (1) gender, age, height, weight, and blood pressure;

[0042] (2) History of hypertension, history of diabetes, history of etiology of cirrhosis, history of decompensation of cirrhosis, decompensation events during hospitalization, acute-on-chronic liver failure during hospitalization, admission time, discharge time, and survival outcome 1 year after admission; (3) Laboratory examination indicators: white blood cell count (WBC), hemoglobin (Hb), platelet count (Plt), alanine aminotransferase

[0043] (ALT), aspartate aminotransferase (AST), total bilirubin (TB), serum albumin (Alb), serum creatinine (Cr), prothrombin time (PT), international normalized ratio (INR), C-reactive protein (CRP). The MELD score of the patient was calculated based on laboratory data. The albumin binding capacity was evaluated by experimentally measuring the residual binding amount of albumin binding site II to the specific fluorescent marker dansylsarcosine. The albumin binding capacity was calculated as follows: albumin binding capacity (%) = fluorescence in the standard ultrafiltrate / fluorescence in the sample ultrafiltrate × 100.

[0044] Statistical methods included: All statistical tests were performed using R software (version 4.3.2). The Shapiro test was used to test for normal distribution. Continuous variables with normal distribution were expressed as mean ± standard deviation (SD), and skewed distributions were expressed as median (interquartile range, IQR). Categorical variables were described as counts (percentages). Comparisons between groups were performed using Student t test, Mann-Whitney U test, or χ2 test. 2Test. Analysis of variance or Kruskal-Wallis test was used for more than two groups. Competing risk regression analysis was used to identify risk factors associated with 1-year mortality in patients with acute decompensation of cirrhosis, with transplantation as a competing risk, followed by a backward stepwise method between variables with p<0.05 in univariate analysis to select the optimal variables for further multivariate analysis and nomogram drawing. Parameters with strong correlations (Spearman correlation coefficients exceeding 0.5) were not included in the multivariate analysis due to multicollinearity. Receiver operating curves were used to evaluate the prognostic performance of the model, assuming that the survival outcome of patients who had undergone liver transplantation was death and that no one would survive at the end of the follow-up period. Gray's method was used to estimate the cumulative incidence function, stratify the risk of death, and determine the optimal threshold based on the Youden index. In all analyses, the significance level was set at a two-sided p<0.05.

[0045] Among the 385 patients included in the final analysis of the present invention, there were 332 patients with acute decompensation of liver cirrhosis and 53 patients with acute-on-chronic liver failure. According to the survival outcome after 1 year of admission, 251 patients survived, 106 patients died, and 28 patients underwent liver transplantation. As can be seen from Table 1, the baseline characteristics of the survivors and non-survivors of the 1-year survival outcome were compared, and it was found that there were statistical differences in the history of hypertension, mean arterial pressure at admission, white blood cell count, C-reactive protein, alanine aminotransferase, aspartate aminotransferase, total bilirubin, serum albumin, international normalized ratio, MELD score, and albumin binding capacity.

[0046] Table 1. Baseline demographics, clinical data, and laboratory data of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure at admission:

[0047]

[0048]

[0049] As shown in Table 2, multivariate competing risk analysis identified independent predictors of 1-year mortality in hospitalized patients with acute decompensation of cirrhosis and acute-on-chronic liver failure as albumin binding capacity, mean arterial pressure, white blood cell count, and international normalized ratio. The sub-distribution hazard ratios were albumin binding capacity (sHR 0.986; 95% CI, 0.979-0.994; p < 0.001), mean arterial pressure (sHR 0.979; 95% CI, 0.962-0.997; p = 0.022), white blood cell count (sHR 1.080; 95% CI, 1.049-1.111; p < 0.001), and international normalized ratio (sHR 2.091; 95% CI, 1.656-2.639; p < 0.001).

[0050] Table 2. Multivariate independent risk factors for mortality in patients with acute decompensation of cirrhosis and acute-on-chronic liver failure 1 year after admission:

[0051] variable Regression coefficient Sub-distribution hazard (95% CI) p Albumin binding capacity, per 1% -0.0136 0.986(0.979-0.994) <0.001 Mean arterial pressure, per 1 mmHg -0.0210 0.979(0.962-0.997) 0.022 <![CDATA[White blood cell count, per 10 9 cells / L]]> 0.0767 1.080(1.049-1.111) <0.001 International normalized ratio, per 1 0.7374 2.091(1.656-2.639) <0.001

[0052] The regression coefficients of the screened independent risk factors were used to construct a prognostic prediction model. The model formula was: prognostic score = -0.0136*albumin binding capacity -0.0210*mean arterial pressure + 0.0767*white blood cell count + 0.7374*international normalized ratio. The cut-off value of the model obtained by the optimal Youden index was -1.48. The score ≥-1.48 was a high-risk group for death, and the score <-1.48 was a low-risk group for death. At the same time, the screened independent risk factors were used to create a dynamic nomogram as a convenient web prediction tool. By selecting the values ​​of these four parameters, the model score and the corresponding 1-year survival probability were automatically calculated, such as Figure 2 The figure shows the dynamic nomogram of the prognostic model of the test cohort. The AUC (Area Under Curve) of the nomogram is 0.80, which is significantly better than the MELD score. Figure 3 shown.

[0053] Verification of the predictive performance of the model: The validation cohort included 142 patients, including 132 patients with acute decompensation of cirrhosis and 10 patients with acute-on-chronic liver failure. At the one-year follow-up after admission, 110 patients survived, 27 patients died, and 5 patients underwent liver transplantation. The above model was brought into the validation cohort for analysis, and the AUC was 0.76. Figure 4 As shown in the figure, the model has a good ability to predict the expected survival outcome.

[0054] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A long-term prognosis prediction system for patients with liver disease, characterized in that: The prognosis prediction system is aimed at patients with decompensated liver cirrhosis and acute-on-chronic liver failure, and includes a data collection module, a model building module, and an evaluation and prediction module, wherein: The data collection module is used to collect clinical data of patients with acute decompensation of liver cirrhosis and acute-on-chronic liver failure, including anthropometric data, vital signs, laboratory data, and albumin binding capacity obtained by specific detection; the albumin binding capacity obtained by specific detection is evaluated by experimentally measuring the residual binding amount of albumin binding site II to the specific fluorescent marker dansylsarcosine; The model building module is used to build a prediction model for the death of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure one year after admission. The prediction model is built using a competing risk model, and a dynamic nomogram visualization prediction model is used to create a convenient prediction tool; The prediction evaluation module is used to evaluate the prediction performance of the model through the receiver operating curve.

2. A system for predicting long-term prognosis of patients with liver disease according to claim 1, characterized in that: The prognostic factors of the competing risk model for predicting long-term mortality in patients with acute decompensation of cirrhosis and acute-on-chronic liver failure include albumin binding capacity, mean arterial pressure, white blood cell count, and international normalized ratio.

3. The long-term prognosis prediction system for patients with liver disease according to claim 1, characterized in that: The method for predicting the long-term prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure is used to predict the 1-year survival rate.

4. The long-term prognosis prediction system for patients with liver disease according to claim 1, characterized in that: The prediction model formula is: Prognostic score = -0.0136*albumin binding capacity -0.0210*mean arterial pressure +0.0767*white blood cell count +0.7374*international normalized ratio The albumin binding capacity (%) = fluorescence in the ultrafiltrate of the standard / fluorescence in the ultrafiltrate of the sample × 100. If the prognostic score is ≥ -1.48, it is a high-risk group for death, and if the prognostic score is < -1.48, it is a low-risk group for death.

5. A method for predicting the long-term prognosis of a patient with liver disease, characterized in that: The prognosis prediction method is for patients with decompensated liver cirrhosis and acute-on-chronic liver failure, and comprises the following steps: Step S1, collecting clinical data of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure, including anthropometric data, vital signs, laboratory data, and albumin binding capacity obtained by specific detection; Step S2, constructing a competing risk model for predicting the death of patients with acute decompensation of liver cirrhosis and acute-on-chronic liver failure one year after hospitalization, wherein the prediction model is constructed using a competing risk model, and a dynamic nomogram visualization prediction model is used to produce a convenient prediction tool; Step S3, evaluating the prediction performance of the model through the receiver operating curve.

6. A method for predicting long-term prognosis of patients with liver disease according to claim 5, characterized in that: The albumin binding capacity obtained by the specific detection is evaluated by experimentally measuring the residual binding amount of albumin binding site II to the specific fluorescent marker dansylsarcosine.

7. The method for predicting long-term prognosis of a patient with liver disease according to claim 5, characterized in that: The prognostic factors of the competing risk model for predicting long-term mortality in patients with acute decompensation of cirrhosis and acute-on-chronic liver failure include albumin binding capacity, mean arterial pressure, white blood cell count, and international normalized ratio.

8. The method for predicting long-term prognosis of a patient with liver disease according to claim 5, characterized in that: The method for predicting the long-term prognosis of patients with acute decompensation of cirrhosis and acute-on-chronic liver failure is used to predict the 1-year survival rate.

9. The method for predicting long-term prognosis of a patient with liver disease according to claim 6, characterized in that: The prediction model formula is: Prognostic score = -0.0136*albumin binding capacity -0.0210*mean arterial pressure +0.0767*white blood cell count +0.7374*international normalized ratio The albumin binding capacity (%) = fluorescence in the ultrafiltrate of the standard / fluorescence in the ultrafiltrate of the sample × 100. If the prognostic score is ≥ -1.48, it is a high-risk group for death, and if the prognostic score is < -1.48, it is a low-risk group for death.

Images