Tongue Images-based AI Deep Learning Model for the Prediction of Esophageall Varies in Liver Cirrhosis

Active, not recruiting

• Conditions: Esophageal and Gastric Varices
• Interventions: Diagnostic Test: tongue diagnosis

• Registration Number: NCT05979935
• Lead Sponsor: Qilu Hospital of Shandong University

Brief Summary

The goal of this observational study is to compare the tongue images of liver cirrhosis patients with high-risk and low-risk esophageal varies.

The main question of this study is to explore whether there exists a relationship between the degree of esophageal varices and tongue bioinformatics in liver cirrhosis. it aims to answer 2 questions as below:

question 1: If these is a significant difference in tongue images between patients in liver cirrhosis with high-risk and low-risk esophageal varices.

Question 2; If tongue bioinformatics could be used as a diagnostic method for prediction of esophageal varices in liver cirrhosis.

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 group and low-risk 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 using AI deep learning model for information extraction.

Study Timeline

• Study Start: 2023-07-01
• Study First Submitted: 2023-07-30
• Study First Submitted QC: 2023-08-04
• Study First Posted: 2023-08-07
• Status Verified: 2024-08
• Last Update Submitted: 2024-09-28
• Last Update Posted: 2024-10-01
• Primary Completion: 2024-12-31
• Study Completion: 2025-01

Recruitment & Eligibility

• Status: ACTIVE_NOT_RECRUITING
• Sex: All
• Target Recruitment: 500

Inclusion Criteria

1. Patients who were diagnosed with liver cirrhosis;
2. Patients who received abdominal enhanced CT scans and upper endoscopic examination;
3. Patients who signed informed consent;

Exclusion Criteria

1. Patient who has previously received transjugular intrahepatic portosystemic shunt (TIPS), splenectomy, Hepatectomy, balloon occlusion of retrograde veins or liver transplantation;
2. Patient with liver cancer;

(4) Patients with hypertension, cor pulmnale, emphysema, heart failure and other severe systemic diseases;

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
patients with high-risk of esophageal varices in liver cirrhosis	tongue diagnosis	The maximum diameter of varices \>5mm or maximum diameter of varices \<5mm with positive red sign in patients with liver cirrhosis
patients with low-risk of esophageal varices in liver cirrhosis	tongue diagnosis	the maximum diameter of esophageal varices \<5mm without positive red sign in patients with liver cirrhosis.

Primary Outcome Measures

Name	Time	Method
Endoscopic examination is used to screen esophageal varices for liver cirrhosis patients.	6 months	Endoscopic examination is a standard method for the diagnosis of esophageal varices for liver cirrhosis patients. The degree of esophageal varices, including the diameter and red sign of varices veins can be detected details.
Tongue images analysis by AI deep learning model	6 months	Tongue images will be analyzed by AI deep learning model and information will be extracted and transformed to data for further analysis.

Secondary Outcome Measures

Name	Time	Method
Specific Characteristic in Tongue Bioinformatics	6 months	Artificial intelligence technology and statistic analysis will be used to study the specific difference in tongue bioinformatics between high-risk and low-risk group esophageal varices in patients with liver cirrhosis.

Trial Locations

Locations (1)

Qilu Hospital of Shdong University; 🇨🇳 Jinan, Shandong, China