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

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.

Study Overview

• Status: Unknown
• Conditions: Gastrointestinal Disease

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 Type: Observational
• Enrollment (Anticipated): 2000

Contacts and Locations

Study Locations

• China
  • Shandong
    • Jinan, Shandong, China, 250012
      • Qilu Hospital, Shandong University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years to 80 years (Adult, Older Adult)
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients aged 18 - 80 years undergoing endoscopic examination

Description

Inclusion Criteria:

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

Exclusion Criteria:

-

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

deep learning algorithm group; Before patients going through colonoscopy or gastroscopy ,taking them tongue images and collecting basic information by mobile phone with Anymed.After examination,endoscopic report and histology analysis is collected .Categorizing the images by gastrointestinal diseases，developing and validating a deep learning algorithm for the diagnosis of digestive tract diseases depending on tongue images.Extracting tougue coating,gastric mucosa and stool DNA by high-throughput sequencing,and analyzing their composation,adundance and diversity.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The diagnostic accuracy of gastrointestinal diseases with deep learning algorithm	The diagnostic accuracy of gastrointestinal diseases with deep learning algorithm.	1 month

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The diagnostic sensitivity of gastrointestinal diseases with deep learning algorithm	The diagnostic sensitivity 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 positive predictive value of gastrointestinal diseases with deep learning algorithm	The diagnostic specificity of gastrointestinal diseases with deep learning algorithm	1 month
The diagnostic negative predictive value of gastrointestinal diseases with deep learning algorithm	The diagnostic specificity of gastrointestinal diseases with deep learning algorithm	1 month

Collaborators and Investigators

• Sponsor: Shandong University
• Investigators: Study Chair: Xiuli Zuo, MD,PhD, Study Principal Investigator

Study record dates

Study Major Dates

• Study Start (Actual): March 21, 2021
• Primary Completion (Anticipated): June 1, 2022
• Study Completion (Anticipated): June 1, 2022

Study Registration Dates

• First Submitted: March 20, 2021
• First Submitted That Met QC Criteria: March 20, 2021
• First Posted (Actual): March 23, 2021

Study Record Updates

• Last Update Posted (Actual): March 23, 2021
• Last Update Submitted That Met QC Criteria: March 20, 2021
• Last Verified: March 1, 2021

More Information

Terms related to this study

• Keywords: artificial intelligence; Gastrointestinal Disease; deep learning; tongue image; gastrointestinal flora
• Additional Relevant MeSH Terms: Gastrointestinal Diseases; Digestive System Diseases
• Other Study ID Numbers: 2020-SDU-QILU-G056

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No