CN113782211A - Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients - Google Patents
Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients Download PDFInfo
- Publication number
- CN113782211A CN113782211A CN202111251137.0A CN202111251137A CN113782211A CN 113782211 A CN113782211 A CN 113782211A CN 202111251137 A CN202111251137 A CN 202111251137A CN 113782211 A CN113782211 A CN 113782211A
- Authority
- CN
- China
- Prior art keywords
- patients
- hepatitis
- cirrhosis
- chronic kidney
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a method for establishing a risk early warning model of chronic kidney diseases of hepatitis B cirrhosis patients, which comprises the following steps: determining candidate hepatitis B cirrhosis patients, and collecting clinical data indexes, laboratory indexes and liver image indexes of the candidate hepatitis B cirrhosis patients; counting the cumulative incidence rate of the chronic kidney diseases of the candidate hepatitis B cirrhosis patients in different counting periods, and determining index parameters related to the occurrence of the chronic kidney diseases; determining a regression coefficient of the index parameter by using a proportional risk regression model by taking the index parameter related to the occurrence of the chronic kidney disease as a variable; and establishing an early warning model according to the index parameters and the regression coefficients thereof. The invention also discloses a method for predicting the risk of the hepatitis B cirrhosis patients suffering from the chronic kidney diseases. By utilizing the scheme of the invention, the early prediction capability of the chronic kidney disease of the hepatitis B cirrhosis patients can be improved.
Description
Technical Field
The invention relates to the field of data processing, in particular to a method for establishing a risk early warning model of a hepatitis B cirrhosis patient suffering from chronic kidney diseases, and further relates to a method for predicting the risk of the hepatitis B cirrhosis patient suffering from chronic kidney diseases.
Background
Chronic Kidney Disease (CKD) is a clinical general term for most kidney diseases, is commonly seen in patients with liver cirrhosis, and is one of the important causes of end-stage renal failure and worsening of the condition of patients with liver cirrhosis. The reason for CKD in hepatitis B cirrhosis comes from various aspects, and researches show that hepatitis B virus has the damage capability on the kidney, mainly plays a role through immune mediation of circulating immune complexes and in-situ immune complexes, and has accelerated damage on the kidney with the increase of age. Antiviral drugs also cause impaired renal function and thus progression to CKD. When chronic hepatitis B progresses to a liver cirrhosis stage, portal hypertension caused by liver cirrhosis can cause blood flow change of the whole body, so that kidney damage is caused, portal pressure is further increased, a vicious circle is formed, HRS (hepatorenal syndrome) is finally caused, and once HRS and even acute and chronic renal failure occur, the short-term fatality rate of a liver cirrhosis patient can be increased by more than 10 times. The hepatitis B cirrhosis is complicated with the hidden CKD condition, and the prognosis and clinical outcome of the patient can be effectively improved by finding and preventing high-risk people as soon as possible.
Disclosure of Invention
The invention provides a method for establishing a risk early warning model of chronic kidney diseases of hepatitis B cirrhosis patients, so as to improve the early prediction capability of CKD of hepatitis B cirrhosis patients.
The invention also provides a method for predicting the risk of the chronic kidney disease of the hepatitis B cirrhosis patient, which can simply, quickly and effectively determine the risk of the chronic kidney disease of the hepatitis B cirrhosis patient, thereby performing targeted intervention as soon as possible and guiding the patient to further perfect related treatment so as to reduce the risk of the chronic kidney disease.
Therefore, the invention provides the following technical scheme:
a method for establishing a risk early warning model of a hepatitis B cirrhosis patient suffering from chronic kidney diseases, the method comprising the following steps:
determining candidate hepatitis B cirrhosis patients, and collecting clinical data indexes, laboratory indexes and liver image indexes of the candidate hepatitis B cirrhosis patients;
counting the cumulative incidence rate of the chronic kidney diseases of the candidate hepatitis B cirrhosis patients in different counting periods, and determining index parameters related to the occurrence of the chronic kidney diseases;
determining a regression coefficient of the index parameter by using a proportional risk regression model by taking the index parameter related to the occurrence of the chronic kidney disease as a variable;
and establishing an early warning model according to the index parameters and the regression coefficients thereof.
Optionally, the determining a candidate hepatitis b cirrhosis patient comprises:
determining patients with hepatitis B cirrhosis who follow-up to a set age limit;
and eliminating patients which do not meet the requirements to obtain candidate hepatitis B cirrhosis patients.
Optionally, the excluding of the unsatisfactory patients comprises:
patients with hypertension or diabetes, patients with malignant tumor, patients with other viral hepatitis, patients with HIV, patients with autoimmune liver disease, patients with liver transplantation, patients with chronic kidney disease or other kidney diseases before existence, and patients with pregnancy are excluded.
Optionally, the clinical data indicator comprises any one or more of: sex, age, chronic liver disease course, liver cirrhosis degree, smoking history, drinking history, and complications;
the laboratory metrics include any one or more of: blood routine index, liver and kidney function index, blood coagulation function index and virology index;
the liver image index comprises any one or more of the following indexes: abdominal color ultrasound index, liver CT index or liver MRI index.
Optionally, the determining an index parameter associated with the occurrence of chronic kidney disease comprises:
index parameters related to the occurrence of chronic kidney disease are determined by single-factor and multi-factor analysis.
Optionally, the single-factor and multi-factor analyses include the following: the method comprises the following steps of single-factor proportional risk regression model Cox analysis, multi-factor Cox regression analysis, calculation of area under a working characteristic curve of a subject and Kaplan-Meier survival curve.
Optionally, the establishing an early warning model according to the index parameter and the regression coefficient thereof includes:
the early warning score model is 0.068 × age (year) +0.122 × ratio of neutrophil count to lymphocyte count-0.065 × albumin (g/L).
A method for predicting the risk of developing chronic kidney disease in a patient with hepatitis b cirrhosis, the method comprising:
acquiring index parameters related to chronic kidney diseases of patients with hepatitis B cirrhosis;
inputting the index parameters related to the chronic kidney disease of the patient with the hepatitis B cirrhosis into a pre-established early warning model, and calculating to obtain the risk of the chronic kidney disease of the patient with the hepatitis B cirrhosis.
Optionally, the index parameters related to the occurrence of chronic kidney disease include: age, ratio of neutrophil count to lymphocyte count, albumin.
According to the method for establishing the risk early warning model of the chronic kidney disease of the hepatitis B cirrhosis patients, provided by the embodiment of the invention, clinical data indexes, laboratory indexes and liver image indexes of candidate hepatitis B cirrhosis patients are acquired; counting the cumulative incidence rate of the chronic kidney diseases of the candidate hepatitis B cirrhosis patients in different counting periods, and determining index parameters related to the occurrence of the chronic kidney diseases; determining a regression coefficient of the index parameter by using a proportional risk regression model by taking the index parameter related to the occurrence of the chronic kidney disease as a variable; and establishing an early warning model according to the index parameters and the regression coefficients thereof, and improving the early prediction capability of the patients with hepatitis B cirrhosis on CKD. Furthermore, the risk of the chronic kidney disease of the hepatitis B cirrhosis patients can be simply, quickly and effectively determined by using the early warning model, so that targeted intervention can be performed as soon as possible, and the patients are guided to further perfect related treatment to reduce the risk of the chronic kidney disease.
Drawings
FIG. 1 is a flowchart of a method for establishing a risk early warning model of patients with hepatitis B cirrhosis suffering from chronic kidney diseases according to an embodiment of the present invention;
FIG. 2 is a comparison of the results of using the present invention protocol against existing MELD and CTP scores for a modeling cohort;
FIG. 3 is a comparison of the use of the present invention scheme against existing MELD and CTP scores for a validation queue;
FIG. 4 is a schematic diagram illustrating the prediction of the incidence of CKD in a high-risk group and a low-risk group by using a prediction model provided by an embodiment of the invention;
FIG. 5 is a schematic diagram of the prediction of the incidence of CKD in a high-risk group and a low-risk group for a validation cohort using a prediction model provided in an embodiment of the present invention;
FIG. 6 is a flowchart of a method for predicting the risk of developing chronic kidney disease in patients with hepatitis B cirrhosis according to an embodiment of the present invention.
Detailed Description
The international renal disease organization improvement for renal disease global prognosis working group (KDIGO) in 2012 defined the diagnostic criteria for CKD as: kidney injury (abnormal hematuria component, imaging or pathology examination) lasting 3 months or more, with or without GFR abnormality, with or without history of kidney transplantation; GFR (glomerular filtration rate) < 60ml/min/1.73m2For 3 months or more with or without evidence of kidney damage. CKD can be diagnosed if one of the above criteria is met. CKD is often functional in the early stages and if found in an early stage may reverse its course under drug action, and conversely may progress to hepatorenal syndrome and acute and chronic renal failure, which are life threatening. However, before obvious clinical symptoms appear in CKD patients, occult injuries often appear until the clinical symptoms appear, the disease condition approaches to the middle and late stages, the optimal treatment time of the patients is delayed, and the life quality is influenced. Therefore, a great deal of epidemiological research on CKD is actively carried out in all countries, but the current epidemiological research on CKD mainly takes the general population as a research object, and the clinical research on the CKD is lacked in patients with cirrhosis, especially hepatitis b cirrhosis patients and concurrent CKD. While several previous studies have suggested that age, sex, hypertension, diabetes and hypercholesterolemia are associated with the development of CKD, there is a lack of relevant studies for the development of CKD in patients with hepatitis b cirrhosis.
Therefore, the embodiment of the invention provides a method for establishing a risk early warning model of chronic kidney diseases of hepatitis B cirrhosis patients and a method for predicting the risk of chronic kidney diseases of hepatitis B cirrhosis patients, which predict the risk of CKD of hepatitis B cirrhosis patients, improve the early prediction capability of CKD of hepatitis B cirrhosis patients and perform targeted intervention, thereby achieving the purpose of delaying the disease progression. Specifically, the scheme of the invention utilizes the existing clinical test indexes which are easy to obtain to carry out analysis and comparison, establishes a risk early warning model for the hepatitis B cirrhosis patients to have chronic kidney diseases, simply, quickly and effectively determines the risk of the hepatitis B cirrhosis patients to have chronic kidney diseases, and guides the patients to further perfect the related treatment so as to reduce the risk of the chronic kidney diseases.
Fig. 1 is a flowchart of a method for establishing a risk early warning model of a patient with hepatitis b cirrhosis who has chronic kidney disease according to an embodiment of the present invention, including the following steps:
Specifically, persons with hepatitis B cirrhosis who follow up to a set age (such as 3 years or more) are determined, and then unsatisfactory patients are excluded to obtain candidate hepatitis B cirrhosis patients. For example, patients with hypertension or diabetes, patients with malignant tumor, patients with other viral hepatitis, patients with HIV, patients with autoimmune liver disease, patients with liver transplantation, patients with CKD or other kidney disease, patients with pregnancy, etc. are excluded.
In the scheme, 5546 patients with hepatitis b cirrhosis who were treated between 8 months and 2014 1 months in 2008 were specifically analyzed, 1190 patients with hypertension or diabetes were excluded, 1854 patients with malignant tumor, 321 patients with other viral hepatitis, 42 patients with HIV were excluded, 208 patients with autoimmune liver disease, 22 patients with liver transplantation, 158 patients with CKD or other kidney disease before, 74 patients with pregnancy and 817 patients with follow-up visit less than 3 years, and finally 436 patients met the grouping criteria for modeling, and 380 patients between 4 months and 2016 12 months in 2014 were subjected to prospective study for verification.
Wherein the clinical data indicators may include any one or more of: sex, age, chronic liver disease course, liver cirrhosis degree, smoking history, drinking history, and complications.
Wherein the laboratory index may include any one or more of: blood routine index, liver and kidney function index, blood coagulation function index and virology index; the blood general index consists of leucocytes, neutrophil count, lymphocyte count, the ratio of the neutrophil count to the lymphocyte count and platelets, the liver and kidney function index consists of glutamic-pyruvic transaminase, glutamic-oxalacetic transaminase, total bilirubin, albumin, glutamyltransferase, alkaline phosphatase, blood creatinine and blood urea nitrogen, the blood coagulation function index consists of prothrombin time and an international standardized ratio, and the virology index consists of five hepatitis B virus and hepatitis B virus quantification.
The liver image index may include any one or more of the following: abdominal color Doppler, liver CT (Computed Tomography) or liver MRI (Magnetic Resonance Imaging).
For the patients with the above statistics, 816 hepatitis B cirrhosis patients were enrolled, which included 436 patients in a retrospective modeling cohort and 380 patients in a prospective validation cohort. Of 816 patients with hepatitis B and liver cirrhosis, the majority were male (71.6% of the total) and decompensated (73.4% of the total). Patients in the modeled group had higher ratios of alkaline phosphatase, prothrombin time levels, and ascites, smoking history, and drinking history than patients in the validated group.
For the above patients, in the follow-up period of 3 years, 35 (8.0% of the total number of the modeling group) patients in the modeling group were confirmed to be diagnosed as CKD, and 28 (7.4% of the total number of the verification group) patients in the verification group were confirmed to be diagnosed as CKD. The cumulative incidence of CKD at 1, 2 and 3 years was 0.5%, 4.4% and 8.0% in the building group and 1.6%, 5.0% and 7.4% in the validation group, respectively.
In embodiments of the invention, the indicator parameter associated with the occurrence of CKD may be determined by single factor analysis.
By one-way analysis, it can be determined that age, albumin, lymphocyte count, the ratio of neutrophil count to lymphocyte count and eGFR (glomerular filtration rate) are significantly correlated with the occurrence of CKD.
It should be noted that the single-factor analysis method specifically adopts single-factor Cox (proportional risk regression model) regression analysis, and the embodiment of the present invention is not limited thereto.
And 103, determining a regression coefficient of the index parameter by using the index parameter related to the occurrence of the chronic kidney disease as a variable and using a proportional risk regression model.
That is, the index parameters determined by the single factor analysis are taken as variables and incorporated into the multi-factor Cox regression analysis, and finally, the indexes related to the occurrence of CKD in patients with hepatitis b cirrhosis are determined, and the regression coefficients of the index parameters are calculated. Specifically, the age (HR (hazard ratio) of 1.073, 95% CI (confidence interval): 1.036-1.109; P <0.001), albumin (HR ═ 0.918, 95% CI: 0.865-0.975; P ═ 0.005) and the ratio of the neutrophil count to the lymphocyte count (HR ═ 1.142, 95% CI: 1.036-1.259; P ═ 0.007) were finally determined by inputting the above variables into the multifactorial Cox regression analysis, and the regression coefficients of the respective index parameters were obtained.
And 104, establishing an early warning model according to the index parameters and the regression coefficients thereof.
Through the regression analysis, the following early warning models can be obtained:
the early warning score model (named ANA-CKD model) was 0.068 × age (year) +0.122 × ratio of neutrophil count to lymphocyte count-0.065 × albumin (g/L).
Wherein the age value can be calculated from the date of birth in the patient medical record.
Wherein the ratio of the neutrophil count to the lymphocyte count, wherein the neutrophil count and the lymphocyte count are both definitions commonly used in clinical blood routine tests and can be determined by means commonly used in clinical blood routine tests.
Wherein, albumin is the definition commonly used in clinical biochemical test, and can be measured by the common mode in clinical biochemical test, and the unit is g/L.
The higher the early warning score is, the higher the risk of the hepatitis B cirrhosis patients to develop chronic kidney diseases is.
Figures 2 and 3 show the results of a comparison of the MELD and CTP scores using the protocol of the present invention with those of the prior art. The horizontal axis in fig. 2 and 3 represents the follow-up time and the vertical axis represents the cumulative incidence of CKD.
CTP (Child-Turcotte-Pugh) score and a model for end-stage liver disease (MELD) are models which are widely applied to the evaluation of liver reserve function of a liver cirrhosis patient at present, but whether the model can be used for predicting the occurrence risk of CKD is not clear.
Wherein, CTP score is calculated by hepatic encephalopathy, ascites, total bilirubin, albumin and prothrombin time, and each index is divided into 1, 2 and 3 according to the disease degree. Wherein, the grade A is 5 to 6, the grade B is 7 to 9, and the grade C is 10 to 15. The evaluation model has been applied clinically for more than 40 years, and is the most classical model for evaluating the liver reserve function, and evaluating the illness state and prognosis of patients with cirrhosis at home and abroad at present.
The MELD scoring model is used for evaluating whether a cirrhosis patient needs to undergo jugular portal-body shunt, and the research finds that serum total bilirubin, creatinine and an international standardized ratio are independent factors influencing the prognosis of the patient and establishes a calculation formula: r ═ 9.6 xln (creatinine mg/dl) +3.8 xln (total bilirubin mg/dl) +11.2 xln (international normalized ratio) +6.4 × cause (cholestasis or alcohol 0, others are 1), the higher the R value, the lower the survival rate.
FIG. 2 shows the accuracy of predicting CKD in 3 years in patients with hepatitis B cirrhosis by AUROC (Area under the curve of the working characteristics of the subject) comparing different models (ANA-CKD, CTP, MELD). AUROC represents accuracy, and the larger the area under the curve represents the higher the accuracy of the model.
The ANA-CKD model has an AUROC of 0.756 (95% CI: 0.673-0.839), significantly higher than the MELD score (0.615, 95% CI: 0.568-0.662; P ═ 0.012) and the CTP score (0.570, 95% CI: 0.520-0.615; P ═ 0.002). This indicates that the ANA-CKD model is superior to the MELD and CTP scores in predicting the CKD occurrence risk of hepatitis B cirrhosis patients.
Further, to verify the predictive power of the constructed model: the early warning models established above were substituted into the validation cohort analysis AUROC, which was 0.766 (95% CI: 0.719-0.808) for the ANA-CKD model, still significantly higher than the MELD score (0.554, 95% CI: 0.503-0.605; P ═ 0.003) and the CTP score (0.643, 95% CI: 0.597-0.696; P ═ 0.031), as shown in fig. 3.
As can be seen from the comparison, the early warning model constructed by the scheme of the invention, namely the early warning scoring model, has higher capability of predicting CKD of hepatitis B cirrhosis patients.
In addition, the cut-off value of the ANA-CKD model is 1.2 according to the ROC curve. Patients were divided into two groups according to cut-off values: low risk group (score <1.2) and high risk group (score ≧ 1.2). Cumulative probability of CKD for 3 years for patients in the low risk group (score <1.2) and high risk group (score ≧ 1.2) was 3.1% and 15.2% on the modeling cohort (P <0.0001), as shown in fig. 4, and 2.2% and 11.9% on the validation cohort (P ═ 0.0003), as shown in fig. 5. Therefore, patients with hepatitis B cirrhosis with score no less than 1.2 have a higher risk of developing CKD within 3 years, and need to pay attention to the change of renal function and intervene as early as possible. In fig. 4 and 5, the horizontal axis represents the follow-up time and the vertical axis represents the cumulative incidence of CKD.
Accordingly, an embodiment of the present invention further provides a method for predicting the risk of developing chronic kidney disease in a patient with hepatitis b cirrhosis, as shown in fig. 6, which is a flowchart of the method, and includes the following steps:
The index parameters related to the occurrence of cirrhosis include: age, ratio of neutrophil count to lymphocyte count, albumin.
The method for establishing the early warning model has been described in detail in the foregoing, and is not described herein again.
By utilizing the early warning model, the risk of the chronic kidney disease of the hepatitis B cirrhosis patients is simply, conveniently, quickly and effectively determined, so that targeted intervention can be performed as soon as possible, and the patients are guided to further perfect related treatment to reduce the risk of the chronic kidney disease.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. Furthermore, the above-described system embodiments are merely illustrative, wherein modules and units illustrated as separate components may or may not be physically separate, i.e., may be located on one network element, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.
Accordingly, an embodiment of the present invention further provides an apparatus for a method for predicting a risk of a patient with hepatitis b cirrhosis suffering from chronic kidney disease, where the apparatus is an electronic device, and the apparatus may be, for example, a mobile terminal, a computer, a tablet device, a personal digital assistant, and the like. The electronic device may include one or more processors, memory; wherein the memory is used for storing computer executable instructions and the processor is used for executing the computer executable instructions to realize the method of the previous embodiments.
The present invention has been described in detail with reference to the embodiments, and the description of the embodiments is provided to facilitate the understanding of the method and apparatus of the present invention, and is intended to be a part of the embodiments of the present invention rather than the whole embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present invention without any creative effort shall fall within the protection scope of the present invention, and the content of the present description shall not be construed as limiting the present invention. Therefore, any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A method for establishing a risk early warning model of a hepatitis B cirrhosis patient suffering from chronic kidney disease is characterized by comprising the following steps:
determining candidate hepatitis B cirrhosis patients, and collecting clinical data indexes, laboratory indexes and liver image indexes of the candidate hepatitis B cirrhosis patients;
counting the cumulative incidence rate of the chronic kidney diseases of the candidate hepatitis B cirrhosis patients in different counting periods, and determining index parameters related to the occurrence of the chronic kidney diseases;
determining a regression coefficient of the index parameter by using a proportional risk regression model by taking the index parameter related to the occurrence of the chronic kidney disease as a variable;
and establishing an early warning model according to the index parameters and the regression coefficients thereof.
2. The method of claim 1, wherein the determining the candidate hepatitis b cirrhosis patient comprises:
determining patients with hepatitis B cirrhosis who follow-up to a set age limit;
and eliminating patients which do not meet the requirements to obtain candidate hepatitis B cirrhosis patients.
3. The method of claim 2, wherein the excluding of unsatisfactory patients comprises:
patients with hypertension or diabetes, patients with malignant tumor, patients with other viral hepatitis, patients with HIV, patients with autoimmune liver disease, patients with liver transplantation, patients with chronic kidney disease or other kidney diseases before existence, and patients with pregnancy are excluded.
4. The method of claim 1,
the clinical data indicators include any one or more of: sex, age, chronic liver disease course, liver cirrhosis degree, smoking history, drinking history, and complications;
the laboratory metrics include any one or more of: blood routine index, liver and kidney function index, blood coagulation function index and virology index;
the liver image index comprises any one or more of the following indexes: abdominal color ultrasound index, liver CT index or liver MRI index.
5. The method of claim 4, wherein determining an indicator parameter associated with the occurrence of chronic kidney disease comprises:
index parameters related to the occurrence of chronic kidney disease are determined by single-factor and multi-factor analysis.
6. The method of claim 5, wherein the single-factor and multi-factor analysis comprises the following: the method comprises the following steps of single-factor proportional risk regression model Cox analysis, multi-factor Cox regression analysis, calculation of area under a working characteristic curve of a subject and Kaplan-Meier survival curve.
7. The method of claim 1, wherein the building an early warning model according to the index parameters and regression coefficients thereof comprises:
the early warning score model is 0.068 × age (year) +0.122 × ratio of neutrophil count to lymphocyte count-0.065 × albumin (g/L).
8. A method for predicting the risk of developing chronic kidney disease in a patient with hepatitis b cirrhosis, the method comprising:
acquiring index parameters related to chronic kidney diseases of patients with hepatitis B cirrhosis;
inputting the index parameters related to the chronic kidney disease of the patient with the hepatitis B cirrhosis into a pre-established early warning model, and calculating to obtain the risk of the chronic kidney disease of the patient with the hepatitis B cirrhosis.
9. The method of claim 8, wherein the index parameters associated with the occurrence of chronic kidney disease comprise: age, ratio of neutrophil count to lymphocyte count, albumin.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111251137.0A CN113782211A (en) | 2021-10-27 | 2021-10-27 | Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111251137.0A CN113782211A (en) | 2021-10-27 | 2021-10-27 | Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113782211A true CN113782211A (en) | 2021-12-10 |
Family
ID=78956698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111251137.0A Pending CN113782211A (en) | 2021-10-27 | 2021-10-27 | Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113782211A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118471518A (en) * | 2024-07-11 | 2024-08-09 | 杭州生奥信息技术有限公司 | ACLF occurrence prediction method and software product |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108417267A (en) * | 2018-03-19 | 2018-08-17 | 首都医科大学附属北京地坛医院 | A kind of system of the determining short-term prognosis of hepatorenal syndrome in liver cirrhosis patient |
| CN111951966A (en) * | 2020-08-05 | 2020-11-17 | 宁波市奉化区人民医院医共体 | Method for predicting postoperative complications of osteoporotic fracture based on possum scoring system |
| CN112002427A (en) * | 2020-10-09 | 2020-11-27 | 重庆医科大学 | Construction method of model for predicting risk of decompensated liver cirrhosis combined infection |
| CN112017783A (en) * | 2020-09-14 | 2020-12-01 | 华中科技大学同济医学院附属协和医院 | Prediction model for pulmonary infection after heart operation and construction method thereof |
| CN112420196A (en) * | 2020-11-20 | 2021-02-26 | 长沙市弘源心血管健康研究院 | Prediction method and system for survival rate of acute myocardial infarction patient within 5 years |
| CN112837819A (en) * | 2021-01-20 | 2021-05-25 | 尹丽君 | Method for establishing acute kidney injury prediction model after coronary artery bypass grafting |
| CN113421640A (en) * | 2021-06-24 | 2021-09-21 | 复旦大学附属中山医院 | Modeling method of postoperative complication prediction model based on early heart rate change |
-
2021
- 2021-10-27 CN CN202111251137.0A patent/CN113782211A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108417267A (en) * | 2018-03-19 | 2018-08-17 | 首都医科大学附属北京地坛医院 | A kind of system of the determining short-term prognosis of hepatorenal syndrome in liver cirrhosis patient |
| CN111951966A (en) * | 2020-08-05 | 2020-11-17 | 宁波市奉化区人民医院医共体 | Method for predicting postoperative complications of osteoporotic fracture based on possum scoring system |
| CN112017783A (en) * | 2020-09-14 | 2020-12-01 | 华中科技大学同济医学院附属协和医院 | Prediction model for pulmonary infection after heart operation and construction method thereof |
| CN112002427A (en) * | 2020-10-09 | 2020-11-27 | 重庆医科大学 | Construction method of model for predicting risk of decompensated liver cirrhosis combined infection |
| CN112420196A (en) * | 2020-11-20 | 2021-02-26 | 长沙市弘源心血管健康研究院 | Prediction method and system for survival rate of acute myocardial infarction patient within 5 years |
| CN112837819A (en) * | 2021-01-20 | 2021-05-25 | 尹丽君 | Method for establishing acute kidney injury prediction model after coronary artery bypass grafting |
| CN113421640A (en) * | 2021-06-24 | 2021-09-21 | 复旦大学附属中山医院 | Modeling method of postoperative complication prediction model based on early heart rate change |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118471518A (en) * | 2024-07-11 | 2024-08-09 | 杭州生奥信息技术有限公司 | ACLF occurrence prediction method and software product |
| CN118471518B (en) * | 2024-07-11 | 2024-10-15 | 杭州生奥信息技术有限公司 | ACLF occurrence prediction method and software product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Somsouk et al. | Moderate ascites identifies patients with low model for end‐stage liver disease scores awaiting liver transplantation who have a high mortality risk | |
| EP2844131B1 (en) | Methods and systems of evaluating a risk of a gastrointestinal cancer | |
| Bazeley et al. | C-reactive protein and prediction of 1-year mortality in prevalent hemodialysis patients | |
| Demirjian et al. | Predictive models for acute kidney injury following cardiac surgery | |
| Neill et al. | Epidemiology of acute kidney injury in Canadian critical care units: a prospective cohort study | |
| CN114121285A (en) | Kidney injury risk data prediction system, kidney injury risk data prediction method, computer device, and medium | |
| CN114220540A (en) | Construction method and application of diabetic nephropathy risk prediction model | |
| Jiang et al. | Incidence, risk factors, and biomarkers predicting ischemic or hemorrhagic stroke associated acute kidney injury and outcome: a retrospective study in a general intensive care unit | |
| CN113782211A (en) | Establishment method and prediction method of risk early warning model for chronic kidney disease of hepatitis B cirrhosis patients | |
| CN116259410A (en) | Liver cancer occurrence risk prediction model and construction method of network calculator thereof | |
| Çelik et al. | Evaluation of the diagnostic validity of noninvasive tests for predicting liver fibrosis stage in chronic hepatitis B patients | |
| De Almeida et al. | Kidney failure detection using machine learning techniques | |
| CN117976213A (en) | Sepsis acute liver injury risk prediction method, device, equipment and storage medium | |
| CN113160980A (en) | Modeling method and prediction device of thrombus risk prediction model of ovarian malignant tumor patient | |
| CN111768862A (en) | Autoimmune hepatitis risk prediction model and construction method thereof | |
| CN111341452A (en) | Multi-system atrophy and disability prediction method, model building method, device and equipment | |
| CN108417267B (en) | System for determining short-term prognosis of patient with liver cirrhosis hepatorenal syndrome | |
| Cui et al. | Establishment and evaluation of a model for predicting 3-month mortality in Chinese patients with hepatic encephalopathy | |
| CN114300135A (en) | Method and device for constructing early recurrence prediction model after liver cancer operation | |
| CN118471518B (en) | ACLF occurrence prediction method and software product | |
| CN118039137B (en) | Postoperative inflammatory response prediction system | |
| Wang et al. | Evaluating short-term and long-term liver fibrosis improvement in hepatitis C patients after DAA treatment | |
| Dash et al. | Enhancing Disease Diagnosis: Statistical Analysis of Haematological Parameters in Sickle Cell Patients, Integrating Predictive Analytics | |
| CN117976214A (en) | Method, device, equipment and storage medium for predicting 28-day death risk of senile sepsis | |
| Wang et al. | The Renal Prognosis Prediction Model of Diabetes Nephropathy Based on Machine Learning: TH-PO014 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20211210 |