Deep Learning Algorithm for the Diagnosis of Gastrointestinal Diseases Depending on Tongue Images

• Conditions: Gastrointestinal Disease

• Registration Number: NCT04811599
• Lead Sponsor: Shandong University

Brief Summary

The purpose of this study is to analysize the relationship between the characteristics of tongue image and the diagnosis of gastrointestinal diseases , then develop and validate a deep learning algorithm for the diagnosis of gastrointestinal diseases depending on tongue images, so as to improve the objectiveness and intelligence of tongue diagnosis. At the same time, gastrointestinal flora of common tongue images were analyzed in order to provide a microecological basis for understanding the relationship between tongue images and digestive tract diseases.

Detailed Description

Tongue diagnosis is an important part of traditional Chinese medicine.According to traditional Chinese medicine theory,health condition can assessed by observing tougue features,including color, gloss, shape and coating of the tongue, tongue features reflect gastric mucosal state, disease classification and prognosis. Recently, deep learning based on central neural networks (CNN) has shownTongue diagnosis is an important part of traditional Chinese medicine.According to traditional Chinese medicine theory,health condition can assessed by observing tougue features,including color, gloss, shape and coating of the tongue, tongue features reflect gastric mucosal state, disease classification and prognosis. Recently, deep learning based on central neural networks (CNN) has shown multiple potential in detecting and diagnosing gastrointestinal diseases. However, there is still a blank in recognition of gastrointestinal diseases .This study aims to develop and validate a deep learning algorithm for the diagnosis of digestive tract diseases depending on tongue images,and analyze gastrointestinal flora of common tongue images.

Study Timeline

• Status Verified: 2021-03
• Study First Submitted: 2021-03-20
• Study First Submitted QC: 2021-03-20
• Last Update Submitted: 2021-03-20
• Study Start: 2021-03-21
• Study First Posted: 2021-03-23
• Last Update Posted: 2021-03-23
• Primary Completion: 2022-06-01
• Study Completion: 2022-06-01

Recruitment & Eligibility

• Status: UNKNOWN
• Sex: All
• Target Recruitment: 2000

Inclusion Criteria

• Patients aged 18 - 80 years undergoing endoscopic examination;patients gave informed consent and signed informed consent.

Exclusion Criteria

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Primary Outcome Measures

Name	Time	Method
The diagnostic accuracy of gastrointestinal diseases with deep learning algorithm	1 month	The diagnostic accuracy of gastrointestinal diseases with deep learning algorithm.

Secondary Outcome Measures

Name	Time	Method
The diagnostic sensitivity of gastrointestinal diseases with deep learning algorithm	1 month	The diagnostic sensitivity of gastrointestinal diseases with deep learning algorithm.
The diagnostic negative predictive value of gastrointestinal diseases with deep learning algorithm	1 month	The diagnostic specificity of gastrointestinal diseases with deep learning algorithm
The diagnostic specificity of gastrointestinal diseases with deep learning algorithm	1 month	The diagnostic specificity of gastrointestinal diseases with deep learning algorithm
The diagnostic positive predictive value of gastrointestinal diseases with deep learning algorithm	1 month	The diagnostic specificity of gastrointestinal diseases with deep learning algorithm

Trial Locations

Locations (1)

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