Development and Validation of a Deep Learning Algorithm to Evaluate Endoscopic Disease Activity of Ulcerative Colitis.

Real-time Evaluation of Severity and Mucosal Healing in Patients With Ulcerative Colitis by a Deep Learning Algorithm: a Multi-center Prospective Study.

The purpose of this study is to develop an artificial intelligence(AI) assisted scoring system, which can evaluate the disease severity and mucosal healing stage in patients with ulcerative colitis. Then testify whether this new scoring system can help physicians to enhance the accuracy of disease severity assessments in a multi-center clinical practice.

Study Overview

• Status: Unknown
• Conditions: Ulcerative Colitis
• Intervention / Treatment: Device: Artificial inteligence associated ulcerative colitis severity scoring system; Device: Conventional human scoring

Detailed Description

Ulcerative colitis is a non-specific chronic inflammation of gut characterized by referral bloody stool, diarrhea and abdominal pain. Endoscopic features of the disease severity and mucosal healing stage are strongly associated with treatment response and prognosis in the future. Currently, the Mayo endoscopic sub-score (Mayo ES) and Ulcerative colitis endoscopic index of severity (UCEIS) are commonly recommended to guide therapeutic adjustments. However, the accuracy of these scales greatly relies on intra-observer and inter-observer consistency for lack of objective measurements. Recently, deep learning algorithm based on convolutional neural network (CNN) has shown multiple potential in computer-aided detection and computer-aided diagnose of gastrointestinal lesions. Up to now, no randomized controlled trials have been conducted to evaluate the performance of deep learning algorithm for assessing disease activity in ulcerative colitis. This study aims to train a deep learnig algorithm to assess severity and mucosal healing stage of ulcerative colitis using the Mayo ES and UCEIS scale, then testify whether the engagement of AI can improve the evaluation accuracy of physicians in a multi-center clinical practice.

• Study Type: Interventional
• Enrollment (Anticipated): 200
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Shandong
    • Jinan, Shandong, China, 257000
      • Qilu hosipital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 14 years to 66 years (Adult, Older Adult)
• Accepts Healthy Volunteers: No
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Patients with ulcerative colitis undergoing colonoscopy

Exclusion Criteria:

• Known or suspected bowel obstruction, stricture or perforation
• Compromised swallowing reflex or mental status
• Severe congestive heart failure (New York Heart Association class III or IV)
• Uncontrolled hypertension (systolic blood pressure > 170 mm Hg, diastolic blood pressure > 100 mm Hg)
• Pregnancy or lactation
• Hemodynamically unstable
• Colonic surgery history
• Bad bowel preparation (segmental BBPS<2)
• Unable to give informed consent

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Artificial Intelligence assisted Scoring Group; Patients in this group go through colonoscopy under the AI monitoring device.	Device: Artificial inteligence associated ulcerative colitis severity scoring system; Patients in this group go through a flexible colonoscopy under the AI monitoring device. During the withdrawal process, inflammatory lesions are detected by AI-associated scoring system. Pictures are automatically captured and analyzed by the computer. The Mayo ES and UCEIS sores will be calculated and presented on a second screen, providing a reference for the physician to evaluate the disease severity and mucosal healing stage of the patient. Biopsies will be taken from inflammatory region for histological examination. Videos will be recorded and re-evaluated by a group of experts to determine the final Mayo ES and UCEIS scores.
Active Comparator: Conventional Human Scoring Group; Patients in this group go through conventional colonoscopy without AI monitoring device.	Device: Conventional human scoring; Patients in this group go through a conventional colonoscopy without the AI monitoring device. During the withdrawal process, physician evaluates the disease severity and mucosal healing stage of the patient according to his personal experience. Biopsies will be taken from inflammatory region for histological examination. Videos will be recorded and re-evaluated by a group of experts to determine the final Mayo ES and UCEIS scores.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The scoring accuracy of Mayo ES in AI-associated group and conventional group.	The scoring accuracy of Mayo endoscopic sub-score (Mayo ES) in each group will be calculated using scores from expert group as reference standard. The Mayo ES is a 4-point scale, which classifies the endoscopic severity of ulcerative colitis into the following four categories: point 0 refers to normal or inactive disease, point 1 refers to mild disease with erythema, decreased vascular patterns and mild friability, point 2 refers to moderate disease with marked erythema, absence of vascular patterns, friability and erosions, point 3 refers to severe disease with spontaneous bleed and ulceration. The scoring accuracy of Mayo ES ranging from 0 to 3 point will be separately evaluated in both groups.	6 months
The scoring accuracy of UCEIS in AI-associated group and conventional group.	The scoring accuracy of Ulcerative colitis endoscopic index of severity (UCEIS) in each group will be separately calculated using scores from expert group as reference standard. The UCEIS is an 8-point scale consists of 3 parts: vascular pattern (point 0 refers to normal mucosa, point 1 refers to patchy obliteration of vascular pattern, point 2 refers to complete obliteration of vascular pattern), bleeding (point 0 refers to no visible blood, point 1 refers to some spots of coagulated blood, point 2 refers to free liquid, point 3 refers to frank blood in the lumen), erosions and ulcers (point 0 refers to normal mucosa, point 1 refers to erosions, point 2 refers to superficial ulcers, point 3 refers to deep ulcers. The total UCEIS score summarized by the above 3 parts will be analyzed. The scoring accuracy of UCEIS ranging from 0 to 8 point will be separately evaluated in both group.	6 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
The accuracy of mucosal healing judgements using Mayo ES in each group.	The accuracy of mucosal healing judgements using Mayo ES will be calculated in each group. Assessments from expert group will be used as reference standard. Complete mucosal healing is defined as point 0 in Mayo ES scale, which refers to normal or inactive disease.	6 months
The accuracy of mucosal healing judgements using UCEIS in each group.	The accuracy of mucosal healing judgements using UCEIS will also be calculated in each group. Assessments from expert group will be used as reference standard. Complete mucosal healing is defined as point 0 in UCEIS scale, which refers to normal vascular pattern without bleeding, erosions and ulceration.	6 months

Collaborators and Investigators

• Sponsor: Shandong University

Study record dates

Study Major Dates

• Study Start (Anticipated): June 1, 2019
• Primary Completion (Anticipated): December 31, 2019
• Study Completion (Anticipated): June 1, 2020

Study Registration Dates

• First Submitted: May 27, 2019
• First Submitted That Met QC Criteria: June 1, 2019
• First Posted (Actual): June 4, 2019

Study Record Updates

• Last Update Posted (Actual): June 4, 2019
• Last Update Submitted That Met QC Criteria: June 1, 2019
• Last Verified: June 1, 2019

More Information

Terms related to this study

• Keywords: Ulcerative Colitis; Deep Learning; Convolutional Neural Network
• Additional Relevant MeSH Terms: Digestive System Diseases; Pathologic Processes; Gastrointestinal Diseases; Gastroenteritis; Colonic Diseases; Intestinal Diseases; Inflammatory Bowel Diseases; Ulcer; Colitis; Colitis, Ulcerative
• Other Study ID Numbers: 2019-SDU-QILU-G002

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: Yes

Drug and device information, study documents

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