Artificial Intelligence, Endoscopy
Conditions
Brief summary
In this study, we proposed a prospective study about the effectiveness of artificial intelligence system for endoscopy report quality in endoscopists. The subjects would be divided into two groups. For the collected endoscopic videos, group A would complete the endoscopy report with the assistance of the artificial intelligence system. The artificial intelligence assistant system can automatically capture images, prompt abnormal lesions and the parts covered by the examination (the upper gastrointestinal tract is divided into 26 parts). Group B would complete the endoscopy report without special prompts. After a period of forgetting, the two groups switched, that is, group A without AI assistance and group B with AI assistance to complete the endoscopy report. Then, the completeness of the report lesion, the accuracy of the lesion location, the completeness of the lesion and the standard part in the captured images, and so on were compared with or without AI assistance.
Interventions
DIAGNOSTIC_TESTArtificial intelligence assistant system
The artificial intelligence assistant system can automatically capture images, prompt abnormal lesions and the parts covered by the examination (the stomach is divided into 26 parts).
Sponsors
Renmin Hospital of Wuhan University
Study design
Allocation
RANDOMIZED
Intervention model
CROSSOVER
Primary purpose
DEVICE_FEASIBILITY
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
18 Years to 70 Years
Healthy volunteers
Yes
Inclusion criteria
1. Males or females who are over 18 years old; 2. After qualified medical education and obtained the Certificate of Chinese medical practitioner;
Exclusion criteria
1. Doctors without qualified medical education and didn't obtaine the Certificate of Chinese medical practitioner; 2. The researcher believes that the subjects are not suitable for participating in clinical trials.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Integrity of report lesion | one month | Report lesion integrity with or without AI-assisted. Calculation method = number of report lesions / total number of lesions x 100% |
| Accuracy of lesion location | one month | Accuracy of lesion location with or without AI-assisted. Calculation method = number of lesion with correct location / total number of lesions x 100% |
| Integrity of lesion in captured images | one month | Lesion integrity in captured images with or without AI-assisted. Calculation method = number of lesions in captured images / total number of lesions x 100% |
| Integrity of standard part in captured images | one month | Lesion integrity in captured images with or without AI-assisted. Calculation method = number of standard parts in captured images / the actual number of standard parts covered by the examination x 100% |
Countries
China
Contacts
Primary ContactHonggang Yu, MD
Outcome results
None listed