Biomarkers and kits for diagnosis of liver fibrosis and cirrhosis and use method
A technology of biomarkers and diagnostic kits, applied in measurement devices, instruments, scientific instruments, etc., can solve problems affecting the early detection and treatment of liver fibrosis
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] Example 1: Screening of differential biomarkers
[0053] The design method of this experiment can be found in the appendix figure 1 . The test samples in the present invention were approved by the local ethics committee and informed consent was obtained from all subjects. The present invention enrolls 1374 subjects in total, which are divided into training set, test set and independent verification set. In the training set and test set, ultra-high performance liquid chromatography tandem mass spectrometry was used to detect fasting (12 hours) serum samples from 502 healthy people and 504 patients with different degrees of chronic liver disease caused by HBV infection confirmed by liver biopsy. The content of metabolites such as bile acid and amino acid, and the detection of corresponding clinical indicators. In an independent validation set, the content of bile acid and amino acid metabolites in fasting (12 hours) serum samples from 368 patients with chronic liver ...
Embodiment 2
[0120] Example 2 biomarker combination (elaidic acid (C18:2n6t), taurocholate (TCA), tyrosine (Tyrosine) and valine predictive power
[0121] Samples and data sources are the same as in Example 1.
[0122]The random forest model was used to evaluate candidate variables and establish a model to verify the combination of elaidic acid (C18:2n6t), taurocholate (TCA), tyrosine (Tyrosine) and valine in predicting the degree of liver fibrosis The prediction ability, the results are shown in Table 4. It can be seen from Table 4 that the combination of these four metabolites has better predictive ability compared with the existing test indicators.
[0123] The random forest model is carried out by using the LiveForest software of Shenzhen Huiyun Biotechnology Co., Ltd., the software copyright registration number is 2018SR227394, and the software name: a machine learning diagnosis system for chronic liver disease based on metabolomics V1.0.
[0124] Table 4
[0125]
[0126] ...
Embodiment 3
[0128] Example 3: Biomarker Combination Random Forest Model Differentiates Healthy and Chronic Liver Disease Groups
[0129] The selected biomarkers are: TCA (taurocholate), Tyrosine (tyrosine), and age, AST, ALT and platelets are as described in Example 1, and 363 patients with chronic liver disease and 371 healthy individuals were in the training set Humans, 141 patients with chronic liver disease and 131 healthy people in the test set, using the biomarker combination random forest model trained in the training set, the possibility of the above subjects suffering from chronic liver disease can be output, and through the ROC analysis Youden's optimal point finds the optimal cutoff value that assesses the model's overall ability to distinguish sick from healthy individuals. result( figure 2 ): The area under the ROC curve and the 95% confidence interval in the training set are 0.986 (0.979-0.991), the area under the PR curve and the 95% confidence interval are 0.988 (0.983...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com