Retrograde Cholangiopancreatography AI Assisted System Validation on Effectiveness and Safety

Artificial Intelligence Clinical Trial

Official title:

A Multicentric Validation Study on the Effectiveness and Safety of Artificial Intelligence Assisted System in Clinical Application of Retrograde Cholangiopancreatography

Clinical Trial Details — Status: Enrolling by invitation

Administrative data

• NCT number: NCT04719117
• Other study ID #: EA-19-006-08
• Status: Enrolling by invitation
• Start date: September 1, 2020
• Est. completion date: December 31, 2021

Study information

• Verified date: January 2021
• Source: Renmin Hospital of Wuhan University
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

In this study, the investigators proposed a prospective study about the effectiveness of artificial intelligence system for Retrograde cholangiopancreatography. The subjects would be include in an analyses groups. The AI-assisted system helps endoscopic physicians estimate the difficulty of Endoscopic retrograde cholangiopancreatography for choledocholithiasis and make recommendations based on guidelines and difficulty scores. The investigators used the stone removal times, success rate of stone extraction and Operating time to reflect the difficulty of the operation, and evaluated whether the results of the AI system were correct.

Description:

Endoscopy is a routine and reliable method for the diagnosis of digestive tract diseases.Common endoscopy are gastroscopy, colonoscopy, capsule endoscopy and enteroscopy, ultrasonic gastroscopy, after ercp and other related technology, can be used in early gastric cancer and peptic ulcer, esophageal varices, the stomach before lesion, intestinal polyps and adenomas and colorectal lesions, inflammatory bowel disease, pancreas disease, biliary tract disease diagnosis and follow-up.At present, digestive endoscopy almost covers the diagnosis of the vast majority of diseases of the digestive tract, and diseases of the digestive system that cannot be directly seen by endoscopy can also be realized through endoscopic-based technologies such as endoscopy and ERCP (here the investigators collectively refer to endoscopy), so as to achieve the coverage of the whole digestive system.It can be seen that digestive endoscopy is of great significance for the diagnosis of digestive diseases and the development of digestive field. With the popularization of these related technologies, the number of endoscopy increased rapidly, which further increased the workload of endoscopists. The operation of endoscopy by high-load endoscopists would reduce the quality of endoscopy, which is prone to problems such as incomplete examination coverage and incomplete detection of lesions.In digestive endoscopy, there are some problems in China, such as lack of endoscopic physicians and uneven distribution, and the quality of endoscopy is not up to standard. These problems need to be solved urgently in order to relieve the pain of patients, save medical resources, save the time and money of patients, and ensure the quality of patients' medical treatment. In 2015, the proposal of deep learning brought great changes to the field of artificial intelligence, which made the development of artificial intelligence leap to a new level.Computer vision is a science that studies how to make machines "see". Through deep learning, camera and computer can replace human eyes to carry out machine vision such as target recognition, tracking and measurement.Interdisciplinary cooperation in the field of medical imaging and computer vision is also one of the research hotspots in recent years. At present, it is mainly applied to the automatic identification and detection of lesions and quality control, and has achieved good results. It can assist doctors to find lesions, make disease diagnosis and standardize doctors' operations, so as to improve the quality of doctors' operations.With mature technical support, it has a good prospect and application value to develop endoscopic operating system for lesion detection and quality control based on artificial intelligence methods such as deep learning. In this study, the investigators proposed a prospective study about the effectiveness of artificial intelligence system for Retrograde cholangiopancreatography. The subjects would be include in an analyses groups. The AI-assisted system helps endoscopic physicians estimate the difficulty of Endoscopic retrograde cholangiopancreatography for choledocholithiasis and make recommendations based on guidelines and difficulty scores. The investigators used the stone removal times, success rate of stone extraction and Operating time to reflect the difficulty of the operation, and evaluated whether the results of the AI system were correct.

Recruitment information / eligibility

• Status: Enrolling by invitation
• Enrollment: 150
• Est. completion date: December 31, 2021
• Est. primary completion date: July 1, 2021
• Accepts healthy volunteers: No
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Who needs ERCP and its related tests are needed to further define the characteristics of digestive tract diseases
• Able to read, understand and sign informed consent
• The investigator believes that the subject can understand the process of the clinical study, is willing and able to complete all the study procedures and follow-up visits, and cooperate with the study procedures
• Patients with a natural duodenal papilla

Exclusion Criteria:

• Has participated in other clinical trials, signed informed consent and is in the follow-up period of other clinical trials
• Has drug or alcohol abuse or mental disorder in the last 5 years
• Women who are pregnant or lactating
• Subjects with previous biliary sphincterotomy
• The investigator determined that subjects were not suitable for ERCP and related tests
• A high-risk disease or other special condition that the investigator considers inappropriate for the subject to participate in a clinical trial
• Patients with known more severe pancreatic head carcinoma
• Patients with acute pancreatitis within 3 days
• Biliary stent replacement or removal did not occur after pancreatic angiography as expected
• Acute cardiovascular and cerebrovascular diseases

Related Conditions & MeSH terms

• Artificial Intelligence
• Cholangiopancreatography, Endoscopic Retrograde
• Digestive System Diseases
• Endoscopy
• Gastrointestinal Disease
• Gastrointestinal Diseases

Locations

Country	Name	City	State
China	Changhai Hospital	Shanghai	Shanghai
China	People's Hospital	Shanghai	Shanghai
China	Renmin hospital	Wuhan	Hubei

Sponsors (1)

Lead Sponsor	Collaborator
Renmin Hospital of Wuhan University

Country where clinical trial is conducted

China, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Number of stone removal operations	The number of times that the stoning balloon and the stoning net were pulled out of the lumen during the stoning process.	A year
Secondary	the accuracy of the measurement	The diameter of the stone (or the width of the lower end of the bile duct) measured by the machine is consistent with the doctor's degree.Accurate DuDu = | machine measurement results - the doctor gold standard measurement results | / doctor gold standard measurements.	A year
Secondary	Stone clearance success rate	Whether the stones have been removed successfully	A year
Secondary	the sensitivity of the prediction of the stone	That is, the sensitivity of the machine to predict the number of stones.Sensitivity = the number of calculi correctly predicted by the machine/the number of actual calculi.	A year
Secondary	the operate time	Refers to the time from the successful intubation of the duodenal papilla guide wire to the beginning of endoscopic withdrawal.	During surgery
Secondary	the removal stone time	Refers to the time from the successful intubation of the duodenal papilla guide wire to the beginning of endoscopic withdrawal.	During surgery