Deep Learning Algorithm for the Diagnosis of Gastrointestinal Diseases

Development and Validation of a Deep Learning Algorithm for the Diagnosis of Gastrointestinal Diseases

The purpose of this study is to develop and validate a deep learning algorithm for the diagnosis of gastrointestinal diseases. Then, evaluate the accuracy this new artificial intelligence(AI) assisted recognition system in clinic practice.

Study Overview

• Status: Unknown
• Conditions: Gastrointestinal Disease
• Intervention / Treatment: Device: AI for the Diagnosis of Gastrointestinal Diseases

Detailed Description

Recently, deep learning algorithm based on central neural networks (CNN) has shown multiple potential in computer-aided detection and computer-aided diagnose of gastrointestinal lesions. However, there is still a blank in recognition of all gastrointestinal diseases. This study aim to develop and validate a deep learning algorithm for the diagnosis of gastrointestinal diseases. Then, evaluate the accuracy this new artificial intelligence(AI) assisted recognition system in clinic practice.

• Study Type: Interventional
• Enrollment (Anticipated): 100000
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Shandong
    • Jinan, Shandong, China, 250012
      • Recruiting
      • Qilu Hospital, Shandong University
      • Contact: Xiuli Zuo, PhD; Phone Number: 053188369277 15588818685; Email: zuoxiuli@sdu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Participants, aged 18 years or older, who had not had a previous endoscopy were retrieved from all participating hospitals.

Exclusion Criteria:

-

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Experimental: AI monitoring gastrointestinal endoscopy; After receiving standard preparation regimen, patients go through colonoscopy or gastroscopy under the AI monitoring device. The whole procedure is monitored by AI associated recognition system. Gastrointestinal diseases will be detect and diagnosis in which the AI device will automatically captured relevant images and report the site of each segment on the screen. Histology analysis is set as a golden standard. Then all the AI captured images will be reviewed by human group, which consists of three to five experienced endoscopic physicians.

Device: AI for the Diagnosis of Gastrointestinal Diseases; After receiving standard preparation regimen, patients go through colonoscopy or gastroscopy under the AI monitoring device. The whole procedure is monitored by AI associated recognition system. Gastrointestinal diseases will be detect and diagnosis in which the AI device will automatically captured relevant images and report the site of each segment on the screen. Histology analysis is set as a golden standard. Then all the AI captured images will be reviewed by human group, which consists of three to five experienced endoscopic physicians.

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.	1month

Collaborators and Investigators

• Sponsor: Shandong University

Study record dates

Study Major Dates

• Study Start (Actual): January 1, 2020
• Primary Completion (Anticipated): February 1, 2020
• Study Completion (Anticipated): February 1, 2020

Study Registration Dates

• First Submitted: January 7, 2020
• First Submitted That Met QC Criteria: January 7, 2020
• First Posted (Actual): January 10, 2020

Study Record Updates

• Last Update Posted (Actual): February 18, 2020
• Last Update Submitted That Met QC Criteria: February 14, 2020
• Last Verified: February 1, 2020

More Information

Terms related to this study

• Keywords: Endoscopy; Deep Learning; Central Neural Networks; Gastrointestinal Disease
• Additional Relevant MeSH Terms: Gastrointestinal Diseases; Digestive System Diseases
• Other Study ID Numbers: 2019-SDU-QILU-G710

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No