CN116259410A - Liver cancer occurrence risk prediction model and construction method of network calculator thereof - Google Patents

Liver cancer occurrence risk prediction model and construction method of network calculator thereof Download PDF

Info

Publication number
CN116259410A
CN116259410A CN202310109670.6A CN202310109670A CN116259410A CN 116259410 A CN116259410 A CN 116259410A CN 202310109670 A CN202310109670 A CN 202310109670A CN 116259410 A CN116259410 A CN 116259410A
Authority
CN
China
Prior art keywords
liver cancer
prediction
prediction model
occurrence
risk
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
Application number
CN202310109670.6A
Other languages
Chinese (zh)
Inventor
严俊
聂国乐
钟林美
张宏龙
王海平
李汛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
First Hospital of Lanzhou University
Original Assignee
First Hospital of Lanzhou University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by First Hospital of Lanzhou University filed Critical First Hospital of Lanzhou University
Priority to CN202310109670.6A priority Critical patent/CN116259410A/en
Publication of CN116259410A publication Critical patent/CN116259410A/en
Pending legal-status Critical Current

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
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Evolutionary Biology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Operations Research (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Epidemiology (AREA)
  • Algebra (AREA)
  • Pathology (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention discloses a liver cancer occurrence risk prediction model and a construction method of a network calculator thereof, which comprises the following steps: s1, acquiring corresponding clinical and inspection data of a study object; s2, screening of independent prediction characteristics; s3, constructing a prediction model; s4, generating a network calculator; s5, calculating the prediction probability of liver cancer occurrence. The risk prediction model and the network calculator for the occurrence of the family aggregated hepatitis B-related liver cancer are integrated into the electronic case system, so that an electronic decision can be provided for a clinician, the clinician can be better helped to evaluate the risk of the family aggregated hepatitis B-related liver cancer, and accordingly, the high-risk liver cancer patients can be subjected to periodic follow-up detection, early identification and intervention can be performed on the occurrence of the liver cancer, and the prognosis of the patients can be improved.

Description

Liver cancer occurrence risk prediction model and construction method of network calculator thereof
Technical Field
The invention relates to the technical field of medical informatics, in particular to a family aggregated hepatitis B related liver cancer occurrence risk prediction model and a construction method of a network calculator thereof.
Background
Liver cancer is one of the most common tumors worldwide, with mortality being the third leading cause of death. Hepatocellular carcinoma (HCC) is a major type of primary liver cancer, accounting for about 75% -85%. The early symptoms of HCC are not obvious, and most of them found clinically are patients with middle and late stages, with recurrence rates up to 70% 5 years after hepatectomy. Thus, early discovery of HCC is an important measure to improve HCC outcome. Currently, diagnosis of HCC is based mainly on imaging and laboratory examinations. Ultrasound is a common means of HCC screening with a sensitivity of 92% and a specificity of 74.2%. AFP is one of the usual indicators of HCC diagnosis, but its sensitivity is low (40-60%). However, when AFP is combined with ultrasonic examination, the sensitivity (99.2%) and specificity (68.3%) of ultrasonic examination can be further improved. Because of the high cost and equipment requirements of ultrasonic inspection, the ultrasonic inspection cannot be popularized and applied on a large scale.
Chronic hepatitis b is one of the important etiologies of HCC occurrence, with more than 50% of HCC patients worldwide suffering from active hepatitis b. Of these, 75-90% of HCC in the epidemic areas of hepatitis b is directly caused by hepatitis b. For patients who have been infected with HBV virus, effective HCC monitoring means may reduce the occurrence of adverse outcomes. HBV in-family transmission is associated with the phenomenon of family aggregation of HCC.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person of ordinary skill in the art.
Disclosure of Invention
The invention aims to provide a liver cancer occurrence risk prediction model and a construction method of a network calculator thereof, which are suitable for clinical patient liver cancer occurrence risk prediction by constructing a multivariate logistic regression model noman diagram by utilizing clinical test data of family aggregated hepatitis B patients and further constructing the network calculator based on the noman diagram.
In order to achieve the above object, the present invention provides a method for constructing a liver cancer occurrence risk prediction model and a network calculator thereof, comprising the following steps:
s1, acquiring corresponding clinical and inspection data of a study object;
s2, screening the independent prediction characteristics, namely establishing a univariate logistic regression model by using acquired clinical and test data to calculate the correlation between each clinical test index and the occurrence risk of the liver cancer by taking the liver cancer as a dependent variable, screening out the indexes related to the occurrence of the liver cancer, carrying out multivariate logistic regression on the screened indexes, and screening out the independent prediction characteristics of the occurrence of the liver cancer;
s3, constructing a prediction model, constructing a Norman diagram of liver cancer occurrence risk according to the weight coefficient of each independent prediction feature in the prediction model result;
s4, generating a network calculator, and further generating the network calculator based on the Norman diagram;
s5, calculating the prediction probability of liver cancer occurrence, collecting data information of independent prediction features of clinical patients, and inputting the data information into the network calculator to obtain the prediction probability of liver cancer occurrence.
Preferably, in step S1, the clinical and test data include: lymphocyte to monocyte ratio, hemoglobin content, neutrophil percentage, high density lipoprotein cholesterol, prothrombin time, blood glucose, glutamyl transpeptidase, alpha-2 microglobulin, ratio of aspartate aminotransferase to alanine aminotransferase, carcinoembryonic antigen, alpha-fetoprotein, hyaluronic acid, cirrhosis, portal hypertension and ascites, erythrocytes, leukocytes, platelets, neutrophil absolute, aspartate aminotransferase, total cholesterol, serum total protein, alkaline phosphatase, triglycerides, prothrombin activity, a-L fucosidase, a hydroxybutyrate dehydrogenase, albumin, globulin, lactate dehydrogenase, fibrinogen, ferritin, alpha 1 microglobulin, CA199, laminin, HBV DNA, and conjugated cholic acid.
Preferably, in step S1, the study object is randomly divided into a training set and a test set according to a ratio of 7:3, wherein the training set is used for exploring the independent prediction characteristics of liver cancer occurrence and constructing a prediction model, and the test set is used for internal verification of the prediction model.
Preferably, in step S2, the independent prediction feature includes: hemoglobin content, neutrophil percentage, serum total protein, glutamyl transpeptidase, a-L fucosidase, ratio of aspartate aminotransferase to alanine aminotransferase, and alpha fetoprotein.
Further, step S3 further comprises
And evaluating the prediction performance of the prediction model, and evaluating the prediction performance of the prediction model by using the working characteristic curve, the standard curve and the clinical decision curve of the research object.
Preferably, in step S3, the critical division of the working characteristic curve of the study object is performed on patients with high risk and low risk of liver cancer, specifically:
calculating a critical value according to the about dengue index, wherein the about dengue index=sensitivity+specificity-1;
the threshold value calculated using the about log index is 0.266: the patients with high risk have liver cancer occurrence probability higher than 0.266, and the patients with low risk have liver cancer occurrence probability lower than 0.266.
Compared with the prior art, the liver cancer occurrence risk prediction model and the construction method of the network calculator thereof have the following beneficial effects:
the method has the advantages that the model for predicting the occurrence risk of the family aggregated hepatitis B-associated liver cancer is constructed, the network calculator is designed according to the model, and the model for predicting the occurrence risk of the family aggregated hepatitis B-associated liver cancer and the network calculator are integrated into the electronic case system, so that an electronic decision can be provided for a clinician, the clinician can be better helped to evaluate the risk of the family aggregated hepatitis B-associated liver cancer, and therefore, the high-risk liver cancer patients can be subjected to periodic follow-up detection so as to early identify and intervene in the occurrence of the liver cancer, and the prognosis of the patients can be improved.
Drawings
FIG. 1 is a schematic flow chart of a method for constructing a family aggregated hepatitis B related liver cancer risk prediction model and a network calculator according to an embodiment of the invention;
FIG. 2 is a Norman diagram of a predictive model constructed using multivariate logistic regression according to the present invention;
FIG. 3 is a graph of the subject's operational characteristics of the present invention;
FIG. 4 is a calibration graph of the present invention;
FIG. 5 is a decision graph of the present invention;
fig. 6 is a working interface of a network calculator constructed according to a liver cancer prediction model according to the present invention.
Detailed Description
The following detailed description of embodiments of the invention is, therefore, to be taken in conjunction with the accompanying drawings, and it is to be understood that the scope of the invention is not limited to the specific embodiments.
Throughout the specification and claims, unless explicitly stated otherwise, the term "comprise" or variations thereof such as "comprises" or "comprising", etc. will be understood to include the stated element or component without excluding other elements or components.
As shown in fig. 1, a method for constructing a liver cancer occurrence risk prediction model and a network calculator thereof according to a preferred embodiment of the present invention includes the following steps:
s1, acquiring corresponding clinical and inspection data of a study object
Collecting clinical test indicators corresponding to the patient, comprising: lymphocyte to monocyte ratio (LMR), hemoglobin content (Hb), neutrophil percentage (NEU), high density lipoprotein cholesterol (HDL-C), prothrombin Time (PT), blood Glucose (GLU), glutamyl transpeptidase (GGT), alpha-2 microglobulin, ratio of aspartate aminotransferase to Alanine Aminotransferase (AAR), carcinoembryonic antigen (CEA), alpha-fetoprotein (AFP), hyaluronic Acid (HA), cirrhosis, portal hypertension and ascites, erythrocytes, leukocytes, platelets, neutrophil absolute value, aspartate Aminotransferase (AST), total Cholesterol (CHOL), serum Total Protein (TP), alkaline phosphatase (ALP), triglycerides (TG), prothrombin activity (PTA), alpha-L fucosidase (AFU), alpha hydroxybutyrate dehydrogenase, albumin (ALB), globulin (GLB), lactate Dehydrogenase (LDH), fibrinogen (FIB), ferritin (SF), alpha 1 microglobulin, CA199, laminin (LN), DNA (PCR), binding (SCG), and the like.
Study subjects selection, retrospectively collecting first diagnosed familial aggregated hepatitis B patients from first college of Lanzhou university, 2010-12, 2019, were divided into a set-up and validation group according to a randomized 7:3 group approach.
Wherein the subject meets the following criteria:
(1) Inclusion criteria: (1) serological detection of hepatitis B surface antigen (HBsAg) positive, diagnosis of hepatitis B virus hepatitis (HBV, abbreviated as hepatitis B) ) Infection; (2) definition of familial aggregated hepatitis b: at least one of the parents in the family history is infected with HBV prior to birth; at least more than 2 HBsAg positive individuals in the family history of the genetic relatives; (3) the clinical medical record is complete.
(2) Exclusion criteria: excluding Hepatitis C (HCV), hepatitis A (HAV), hepatitis E (HEV), human Immunodeficiency Virus (HIV) infection, autoimmune liver disease, liver metastasis, genetic metabolism type liver disease, alcoholic liver disease, schistosome liver disease, and liver disease of unknown etiology.
S2, screening of independent prediction features
Establishing univariate and multivariate regression models by using acquired clinical and test data to screen independent prediction characteristics of liver cancer occurrence by taking whether liver cancer occurs as dependent variables, specifically calculating correlation between each clinical test index and liver cancer occurrence risk by using the acquired clinical and test data through univariate logistic regression model of glm () function in R software to screen out indexes related to liver cancer occurrence; performing multivariate logistic regression on the screened indexes to screen out independent prediction characteristics of the occurrence of liver cancer related to hepatitis B; determining whether the research object has liver cancer by using medical equipment according to whether the dependent variable is liver cancer, and dividing the research object into a liver cancer group and a liver cancer group which does not have liver cancer according to a determination result; the medical device includes computed tomography and magnetic resonance imaging.
Retrospective study, in which study subjects were patients meeting the group-entering standard, were randomly divided into a training set and a test set (see table 1) according to a 7:3 ratio, the training set was used to explore independent risk factors of the occurrence of familial hepatitis b-related liver cancer and to construct a predictive model, and the test set was used for internal verification of the predictive model. Statistical analysis was performed using R version 4.1.2 using the packets rms, survivinal, rmda, pROC, dynNom, etc. P <0.05 is considered statistically significant. First, the optimum cut-off value of each continuity variable is analyzed by pROC package in R software, and the continuity variable is divided into two kinds of variables. Single-factor and multi-factor analysis was performed using Logistic regression model to screen risk factors for the development of familial aggregated hepatitis b-associated liver cancer (see table 2). And subsequently, using an R language rms package to construct a Norman diagram based on a multi-factor logistic regression screening result, and further constructing a network calculator according to the DynNom package.
Table 1 training set and test set clinical features
Figure BDA0004076288730000061
TABLE 2 Single-and Multi-factor Logistic results
Figure BDA0004076288730000062
Figure BDA0004076288730000071
Obtaining independent prediction characteristics of liver cancer occurrence specifically comprises: hemoglobin content (Hb), percent Neutrophil (NEU), total serum protein (TP), glutamyl transpeptidase (GGT), a-L fucosidase (AFU), ratio of aspartate aminotransferase to Alanine Aminotransferase (AAR), alpha Fetoprotein (AFP).
The method takes whether liver cancer occurs as a dependent variable and specifically comprises the following steps: determining whether the research object has liver cancer by using medical equipment, dividing the research object into a liver cancer generation group and a liver cancer non-generation group according to a determination result, wherein the medical equipment comprises computed tomography, magnetic resonance imaging and the like.
S3, constructing and evaluating a prediction model
According to the obtained independent prediction characteristics, a prediction model is constructed, according to the single-factor and multi-factor analysis results, hemoglobin (Hb), neutrophil percentage (NEU), alpha Fetoprotein (AFP), serum Total Protein (TP), alpha-L fucosidase (AFU), glutamyl transpeptidase (GGT), ratio of aspartate aminotransferase to Alanine Aminotransferase (AAR) are all independent risk factors for the occurrence of family aggregated hepatitis B-related liver cancer, and based on the screened independent prediction characteristics, a Norman map of liver cancer occurrence risk is constructed by utilizing R version 4.1.2 (shown in figure 2).
After the predictive model nomann diagram is established, the predictive performance of the predictive model is evaluated by analyzing the working characteristic curve (shown in fig. 3), the calibration curve (shown in fig. 4) and the clinical decision curve (shown in fig. 5) of the subject.
Critical division of liver cancer occurrence in high-risk and low-risk patients using the subject working profile (as shown in fig. 3) is specifically:
calculating a critical value according to the about dengue index, wherein the about dengue index=sensitivity+specificity-1;
above the critical value is a high risk patient for liver cancer, and below the critical value is a low risk patient for liver cancer.
The threshold value calculated using the about log index is 0.266: the patients with high risk have liver cancer occurrence probability higher than 0.266, and the patients with low risk have liver cancer occurrence probability lower than 0.266.
As shown in fig. 3, the AUC (area under ROC curve) of the nomogram is 0.772 (95% CI: 0.7252-0.8182), which indicates that the accuracy of the prediction result of the nomogram is high; as shown in fig. 4, in the correction curve of the noman chart, a gray line (Ideal) at 45 degrees represents the actual probability of liver cancer occurrence, in addition, 2 lines (application and Bias-corrected) represent the prediction performance of the noman chart, and the 2 lines have similar trend with the Ideal line, further, the noman chart accurately estimates the probability of liver cancer occurrence of the study population, as shown in fig. 5, a clinical decision curve, and the None line represents that all patients do not receive intervention, and the net benefit is 0; ALL lines represent the benefit of ALL patient interventions and Nomogram lines represent nomann plots, indicating that the model has good clinical application value.
S4, generation of network calculator
Constructing and obtaining a liver cancer prediction nomann diagram according to weight coefficients of each independent prediction feature in a prediction model result, and further generating a network calculator based on DynNom packets in R according to the noman diagram;
and a visual network calculator is constructed, so that a clinician can conveniently make a decision and evaluate the occurrence risk of the familial aggregated hepatitis B related liver cancer.
S5, calculating the probability of liver cancer
And collecting key data information of clinical patients, and inputting the key data information into a network calculator to obtain the prediction probability of liver cancer occurrence.
The key data information of clinical patients is collected, specifically: hb, NEU, TP, GGT, AFU, AAR, AFP.
Such as Hb of a familial aggregated hepatitis B patient: 120g/L; NEU:50%; TP:68U/L; AFU:20U/L; AAR:1, a step of; AFP: when 380ng/ml is input into the network calculator, the occurrence probability of liver cancer and 95% CI of the patient are as follows: 0.042 (0.024-0.071).
As shown in fig. 6, the embodiment of the present invention further provides a network calculator for occurrence of a family aggregated hepatitis b related liver cancer, which mainly includes two modules: the module 1 is a clinical data input interface, and the module 2 is a result display interface.
In step S2, whether liver cancer occurs is taken as a final variable, whether liver cancer exists in the study object is determined by using medical equipment, and the study object is divided into liver cancer occurrence groups and non-liver cancer occurrence groups according to a determination result; the medical apparatus includes computed tomography and magnetic resonance imaging. Obtaining clinical indexes related to the occurrence risk of liver cancer by utilizing a univariate logistic regression model analysis; the multivariable logistic regression model is used and clinical reference values of all indexes are combined, independent prediction characteristics are screened out to construct a prediction model of occurrence of the family aggregated hepatitis B related liver cancer, and the independent prediction factors specifically comprise: hb, NEU, TP, GGT, AFU, AAR, AFP.
Of course, other algorithms, such as machine learning algorithms, may also be used to learn the clinical test data and construct the predictive model as desired.
The network calculator in the present embodiment is applicable to various electronic devices including, but not limited to, mobile terminal devices such as mobile phones, notebook computers, and the like.
In summary, the method for constructing the family aggregated hepatitis B-associated liver cancer occurrence prediction model and the network calculator thereof provided by the invention has the advantages that the establishment of the prediction model can predict the occurrence probability of the hepatitis B-associated liver cancer, the network calculator is generated according to the model, and the prediction tool is integrated into a medical electronic system, so that a decision basis can be provided for clinical management of clinicians and family aggregated hepatitis B patients; the prediction index of the model only needs 7 clinical examination indexes of Hb, NEU, TP, GGT, AFU, AAR and AFP, and the 7 indexes are all derived from laboratory examination, so that a clinician can obtain the clinical examination index conveniently and quickly, and meanwhile, the extra economic burden of a clinical patient can not be increased.
The foregoing descriptions of specific exemplary embodiments of the present invention are presented for purposes of illustration and description. It is not intended to limit the invention to the precise form disclosed, and obviously many modifications and variations are possible in light of the above teaching. The exemplary embodiments were chosen and described in order to explain the specific principles of the invention and its practical application to thereby enable one skilled in the art to make and utilize the invention in various exemplary embodiments and with various modifications as are suited to the particular use contemplated. It is intended that the scope of the invention be defined by the claims and their equivalents.

Claims (6)

1. The method for constructing the liver cancer occurrence risk prediction model and the network calculator thereof is characterized by comprising the following steps:
s1, acquiring corresponding clinical and inspection data of a study object;
s2, screening the independent prediction characteristics, namely establishing a univariate logistic regression model by using acquired clinical and test data to calculate the correlation between each clinical test index and the occurrence risk of the liver cancer by taking the liver cancer as a dependent variable, screening out the indexes related to the occurrence of the liver cancer, carrying out multivariate logistic regression on the screened indexes, and screening out the independent prediction characteristics of the occurrence of the liver cancer;
s3, constructing a prediction model, constructing a Norman diagram of liver cancer occurrence risk according to the weight coefficient of each independent prediction feature in the prediction model result;
s4, generating a network calculator, and further generating the network calculator based on the Norman diagram;
s5, calculating the prediction probability of liver cancer occurrence, collecting data information of independent prediction features of clinical patients, and inputting the data information into the network calculator to obtain the prediction probability of liver cancer occurrence.
2. The method for constructing a liver cancer occurrence risk prediction model and its network calculator according to claim 1, wherein in step S1, the clinical and test data includes: lymphocyte to monocyte ratio, hemoglobin content, neutrophil percentage, high density lipoprotein cholesterol, prothrombin time, blood glucose, glutamyl transpeptidase, alpha-2 microglobulin, ratio of aspartate aminotransferase to alanine aminotransferase, carcinoembryonic antigen, alpha-fetoprotein, hyaluronic acid, cirrhosis, portal hypertension and ascites, erythrocytes, leukocytes, platelets, neutrophil absolute, aspartate aminotransferase, total cholesterol, serum total protein, alkaline phosphatase, triglycerides, prothrombin activity, a-L fucosidase, a hydroxybutyrate dehydrogenase, albumin, globulin, lactate dehydrogenase, fibrinogen, ferritin, alpha 1 microglobulin, CA199, laminin, HBV DNA, and conjugated cholic acid.
3. The method according to claim 1, wherein in step S1, the study object is randomly divided into a training set and a test set according to a ratio of 7:3, the training set is used for exploring the construction of the independent prediction feature and the prediction model of liver cancer occurrence, and the test set is used for internal verification of the prediction model.
4. The method for constructing a liver cancer occurrence risk prediction model and its network calculator according to claim 1, wherein in step S2, the independent prediction features include: hemoglobin content, neutrophil percentage, serum total protein, glutamyl transpeptidase, a-L fucosidase, ratio of aspartate aminotransferase to alanine aminotransferase, and alpha fetoprotein.
5. The method for constructing liver cancer occurrence risk prediction model and its network calculator according to claim 1, wherein step S3 further comprises
And evaluating the prediction performance of the prediction model, and evaluating the prediction performance of the prediction model by using the working characteristic curve, the standard curve and the clinical decision curve of the research object.
6. The method for constructing a liver cancer occurrence risk prediction model and a network calculator thereof according to claim 5, wherein the critical division of the working characteristic curve of the study object in step S3 is performed on patients with high risk and low risk of liver cancer occurrence, specifically:
calculating a critical value according to the about dengue index, wherein the about dengue index=sensitivity+specificity-1;
the threshold value calculated using the about log index is 0.266: the patients with high risk have liver cancer occurrence probability higher than 0.266, and the patients with low risk have liver cancer occurrence probability lower than 0.266.
CN202310109670.6A 2023-02-13 2023-02-13 Liver cancer occurrence risk prediction model and construction method of network calculator thereof Pending CN116259410A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310109670.6A CN116259410A (en) 2023-02-13 2023-02-13 Liver cancer occurrence risk prediction model and construction method of network calculator thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310109670.6A CN116259410A (en) 2023-02-13 2023-02-13 Liver cancer occurrence risk prediction model and construction method of network calculator thereof

Publications (1)

Publication Number Publication Date
CN116259410A true CN116259410A (en) 2023-06-13

Family

ID=86678826

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310109670.6A Pending CN116259410A (en) 2023-02-13 2023-02-13 Liver cancer occurrence risk prediction model and construction method of network calculator thereof

Country Status (1)

Country Link
CN (1) CN116259410A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116999092A (en) * 2023-08-18 2023-11-07 上海交通大学医学院附属第九人民医院 Difficult airway assessment method and device based on ultrasonic image recognition technology
CN117131468A (en) * 2023-09-12 2023-11-28 中山大学孙逸仙纪念医院 Intrahepatic cholangiocellular carcinoma screening index and analysis and evaluation method of prognosis factors thereof

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116999092A (en) * 2023-08-18 2023-11-07 上海交通大学医学院附属第九人民医院 Difficult airway assessment method and device based on ultrasonic image recognition technology
CN117131468A (en) * 2023-09-12 2023-11-28 中山大学孙逸仙纪念医院 Intrahepatic cholangiocellular carcinoma screening index and analysis and evaluation method of prognosis factors thereof
CN117131468B (en) * 2023-09-12 2024-01-23 中山大学孙逸仙纪念医院 Intrahepatic cholangiocellular carcinoma screening index and analysis and evaluation method of prognosis factors thereof

Similar Documents

Publication Publication Date Title
Liu et al. CT quantification of pneumonia lesions in early days predicts progression to severe illness in a cohort of COVID-19 patients
Younossi et al. Role of noninvasive tests in clinical gastroenterology practices to identify patients with nonalcoholic steatohepatitis at high risk of adverse outcomes: expert panel recommendations
Khwannimit et al. Comparison of the accuracy of three early warning scores with SOFA score for predicting mortality in adult sepsis and septic shock patients admitted to intensive care unit
CN116259410A (en) Liver cancer occurrence risk prediction model and construction method of network calculator thereof
Parkes et al. Enhanced Liver Fibrosis (ELF) test accurately identifies liver fibrosis in patients with chronic hepatitis C
Halfon et al. FibroTest-ActiTest as a non-invasive marker of liver fibrosis
Miyake et al. Body mass index is the most useful predictive factor for the onset of nonalcoholic fatty liver disease: a community-based retrospective longitudinal cohort study
Cen et al. Development and validation of a clinical and laboratory-based nomogram to predict nonalcoholic fatty liver disease
CN114724716A (en) Method, model training and apparatus for risk prediction of progression to type 2 diabetes
CN112017791A (en) System for determining prognosis condition of liver cancer patient based on artificial neural network model
Kim et al. Quick Sepsis-related Organ Failure Assessment score is not sensitive enough to predict 28-day mortality in emergency department patients with sepsis: a retrospective review
Macpherson et al. Intelligent liver function testing: working smarter to improve patient outcomes in liver disease
Mak et al. Serum Mac-2 binding protein glycosylation isomer level predicts hepatocellular carcinoma development in E-negative chronic hepatitis B patients
Zhang et al. Red cell distribution width-to-lymphocyte ratio: A novel predictor for HBV-related liver cirrhosis
KR20060009861A (en) Method of creating disease prognosis model, method of predicting disease prognosis using the model, device for predicting disease prognosis using the model, its program, and recording medium
Liang et al. Serum fibrosis index-based risk score predicts hepatocellular carcinoma in untreated patients with chronic hepatitis B
Lu et al. Evaluation and comparison of the diagnostic performance of routine blood tests in predicting liver fibrosis in chronic hepatitis B infection
CN111710423A (en) Method for determining mood disorder morbidity risk probability based on regression model
Stawinski et al. Model of end-stage liver disease (MELD) score as a predictor of in-hospital mortality in patients with COVID-19: a novel approach to a classic scoring system
Son et al. The quick sepsis-related organ failure score has limited value for predicting adverse outcomes in sepsis patients with liver cirrhosis
WO2022025069A1 (en) Disease risk evaluation method, disease risk evaluation device, and disease risk evaluation program
Yu et al. Clinical prediction models for hepatitis B virus-related acute-on-chronic liver failure: a technical report
Shao et al. Discrepancies between nonalcoholic and metabolic-associated fatty liver disease by multiple steatosis assessment
Wang et al. Retrospective evaluation of non-invasive assessment based on routine laboratory markers for assessing advanced liver fibrosis in chronic hepatitis B patients
Innes et al. Comparing Predicted Probability of Hepatocellular Carcinoma in Patients With Cirrhosis With the General Population: An Opportunity to Improve Risk Communication?

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