Esophageal Varices, Liver Cirrhosis, Portal Hypertension, Sublingual Varices
Conditions
Keywords
Esophagogastroduodenal Varices, Liver cirrhosis, Sublingual vein, Portal hypertension
Brief summary
The aim of this observational study is to establish an AI deep learning model that can dianosie high-risk varices for patients with cirrhosis effeciently. The main question of this study is to esplore: question 1: Developing a digital tongue diagnosis model, specifically a deep learning model to diagnose high-risk esophageal and gastric varices (HRV) associated with cirrhosis using sublingual vein images. Answering the question of whether the new tongue diagnosis method can accurately diagnose. Question 2: Compare the diagnostic efficacy digital tongue diagnosis model with diagnostic models constructed using other biochemical indicators for HRV in cirrhosis, and answer the question of how to use it optimally. Question 3: Exploring the correlation between sublingual vein characteristics and Hepatic venous pressure gradient (HVPG). Question 4: Compared with endoscopic examination results, validate the diagnostic performance of the model (AUC ≥ 0.90) and screen for key parameters of sublingual vein characteristics (such as sublingual vein varicosity diameter, vein length, color, etc.). Question 5: Follow-up tongue examination images of patients with cirrhosis who underwent treatment (e.g., endoscopy, splenic embolization, TIPS, etc.) at 1, 2, and 3 years post-treatment were evaluated to assess the efficacy of digital tongue examination models in predicting high-risk esophageal and gastric variceal bleeding at 1, 2, and 3 years post-treatment, as well as the efficacy in predicting endoscopic treatment failure rates and patient mortality associated with bleeding.
Detailed description
Firstly, participants will be divided into two groups according to their degree of esophageal varices from endoscopic examination and CT report, including high-risk varices (HRV) group and low-risk varices (LRV) group. Secondly, participants will be asked to show their tongue, including the surface and sublingual veins of tongue, and the tongue images of each participants will be collected by researchers via camera. After finishing tongue image collection, participants will receive a professional tongue diagnosis report in Traditional Chinese Medicine and health suggestion. Finally, tongue images will be analyzed by AI deep learning model and some specifialized information will be estracted exactly. Besides, 60 patietns will be selected to eplore whtether sublingual vein characteristics is assoicated with HVPG. Finally, patietns will be followed up during 3 years, and gastric variceal bleeding, endoscopic treatment failure rates, and patient mortality risks related to bleeding will be analyzed.
Interventions
DIAGNOSTIC_TESTtongue diagnosis
The tongue image of participants will be collected via camera, and tongue images will be used for AI deep model learning analysis.
Sponsors
Shanghai Changzheng Hospital
Shanghai East Hospital of Tongji University
Eighth Affiliated Hospital, Sun Yat-sen University
Meng Chao Hepatobiliary Hospital of Fujian Medical University
Tianjin Medical University General Hospital
Army Medical Center of PLA
Shandong Provincial Hospital
Qianfoshan Hospital
Shandong Public Health Clinical Center
The 960th Hospital of the PLA Joint Logistics Support Force
Jinan Central Hospital
Weifang People's Hospital
Liaocheng People's Hospital
The Second Affiliated Hospital of Shandong First Medical University
Jining First People's Hospital
Qilu Hospital of Shandong University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 75 Years
Healthy volunteers
No
Inclusion criteria
1. Age 18-75 years (including both age limits), no gender restrictions; 2. Diagnosed with cirrhosis based on clinical presentation, laboratory tests, imaging studies, and/or histopathological examination; 3. Undergone upper gastrointestinal endoscopy within the past 3 months prior to enrollment and have complete endoscopic imaging records; 4. Undergone enhanced CT or MRI scan of the upper abdomen within the past month prior to enrollment; 5. Patients who consent to enrollment and have signed an informed consent form.
Exclusion criteria
1. Patients who have previously undergone endoscopic treatment for esophageal or gastric varices, transjugular intrahepatic portosystemic shunt (TIPS), splenectomy, hepatectomy, balloon occlusion of the portal vein, or liver transplantation; 2. Patients with grade 2-3 ascites or overt hepatic encephalopathy; 3. Patients with a history of portal venous system thrombosis (including the portal vein, splenic vein, superior mesenteric vein, etc.) or portal venous cavernous transformation, and who have been diagnosed with thrombosis within the past two weeks; 4. Patients diagnosed with or suspected of having primary liver cancer or other advanced malignant tumors; 5. Patients with chronic obstructive pulmonary disease and right heart failure; 6. Male and female patients with moderate anemia (hemoglobin \<70 g/L); 7. Patients with poorly controlled diabetes or microvascular complications; 8. Patients with poorly controlled hypertension; 9. Patients with hematological disorders such as polycythemia vera; 10. Patients with local oral lesions affecting sublingual venous blood flow, such as Ludwig's angina, Lemierre syndrome, or complications following certain oral surgeries (e.g., scar contracture or hematoma after tongue or floor of mouth surgery); 11. Patients with sublingual venous varicosities; 12. Patients who have experienced other severe systemic infections within the past 2 weeks prior to enrollment; 13. Pregnant women and peripartum women; 14. Patients with mental disorders; 15. Patients with incomplete medical records; 16. Patients unable to cooperate in completing the clinical study; 17. Other reasons deemed unsuitable for participation by the investigator.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| AUC of tongue diagnostic model | through study completion, up to 3 years | Using endoscopic diagnostic criteria as the gold standard, we calculated the area under the ROC curve (AUC), sensitivity, specificity, positive predictive value, and negative predictive value of the VIT-based digital tongue diagnosis model to evaluate its diagnostic performance in diagnosing HRV in cirrhosis. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| ROC of biochemical characteristic | through study completion, up to 3 years | Calculate the AUC valthe digital tongue diagnosis model.ue, sensitivity, specificity, positive predictive value, negative predictive value, and other relevant parameters of the ROC curve for the HRV diagnostic model for cirrhosis constructed based on biochemical indicators, and compare them with |
| Association between HVPG and sublingual vein | through study completion, up to 3 years | The association between sublingual vein and HVPG |
| Characteristic of sublingual vein | through studyy completion, up to 3 years | Key parameters for screening sublingual vein characteristics (such as sublingual vein varicosity diameter, vein length, color, etc.). |
| The rate of esophageal variceal bleeding, endoscopic treatment failure, and patient mortality | through study completion, up to 3 years | The incidence of esophageal variceal bleeding, endoscopic treatment failure rate, and patient mortality related to bleeding in patients with cirrhosis 1, 2, and 3 years after diagnosis. |
Countries
China
Outcome results
None listed