Effect of AI Monitoring Blind Spots of EGD on the Inspection Time and Lesion Dection Rate

Wuhan University

Status: Not yet enrolling

Conditions: Upper Gastrointestinal Symptoms

Treatments: Device: Endoangle

Study type: Interventional

Funder types: Other

Identifiers

NCT05832411

EA-23-005

Details and patient eligibility

About

The goal of this clinic trial is to learn about the effect of AI monitoring blind spots on the inspection time to EGD. Patients are randomly assigned to undergo an EGD with or without the assistance of AI. In the AI group, except for the original videos, there is additional information presented to endoscopists:(1)the virtual stomach model monitoring;(2)time;(3)scoring. Researchers will compare intervention group to see if it have a shorter inspection time compared with the control group.

Full description

The goal of this clinic trial is to evaluate the effect of real-time artificial intelligence for monitoring blind spots on the inspection time of EGD. Patients are randomly assigned to undergo an EGD with or without the assistance of AI. In the AI group, except for the original videos, there is additional information presented to endoscopists:(1)the virtual stomach model monitoring;(2)time;(3)scoring. Researchers will compare intervention group to see if it have a shorter inspection time in the case of non-inferior detection rate of gastric neoplastic lesions.

Enrollment: 1,672 estimated patients

Sex: All

Ages: 18+ years old

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

1. patients aged 18 years or older
2. patients able to give informed consent
3. American Society of Anesthesiology risk class 1,2 or 3

Exclusion criteria

1. patients with absolute contraindications to EGD examination
2. patients with a history of previous gastrectomy
3. patients with a serious underlying disease
4. pregnant patients
5. researchers believe that the patient is not suitable to participate in the trial

Trial design

Primary purpose: Other

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: Single Blind

---

1,672 participants in 2 patient groups

AI group

Experimental group

Description:

In the AI group, except for the original videos, there is additional information presented to endoscopists:（1）the virtual stomach model monitoring;（2）time;（3）scoring. Endoscopists will complete EGD examination without blind spots.

Treatment:

Device: Endoangle

Routine group

No Intervention group

Description:

In the Routine group, only the original videos and there is no additional information, and inspection time will be no less than 7 minutes.