Skip to content

An artificial intelligence-assisted diagnostic system for endoscopic recognition and grading of esophageal leisons: a multi-center retrospective study

An artificial intelligence-assisted diagnostic system for endoscopic recognition and grading of esophageal leisons: a multi-center retrospective study

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2400082630
Enrollment
Unknown
Registered
2024-04-02
Start date
2024-04-20
Completion date
Unknown
Last updated
2024-04-08

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

esophageal lesion

Interventions

Gold Standard:Pathological diagnosis after surgical or endoscopic resection is the gold standard. The depth of invasion of esophageal intraepithelial neoplasia/early cancer was further classified as M
Index test:An AI-assisted endoscopic recognition and hierarchical diagnosis system for esophageal lesions applicable to the actual clinical environment

Sponsors

The First Medical Center of the PLA General Hospital
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 85 Years

Inclusion criteria

Inclusion criteria: Patients undergoing upper gastrointestinal endoscopy from January 1, 2013 to September 1, 2023; Age 18-85 years old, gender is not limited; Complete clinical, endoscopic and pathological information was obtained.

Exclusion criteria

Exclusion criteria: A history of upper gastrointestinal surgery, esophageal chemotherapy or radiotherapy before endoscopy; Patients diagnosed with esophageal cancer/precancerous lesions by endoscopy, but without the pathological diagnosis after surgical or endoscopic resection in our hospital, or without the depth of tumor invasion marked by pathology; The nature of esophageal lesions is unknown.

Design outcomes

Primary

MeasureTime frame
accuracy;sensibility;specificity;positive predictive value;negative predictive value;

Secondary

MeasureTime frame
The auxiliary efficiency of AI model for endoscopists;

Countries

China

Contacts

Public ContactNingli Chai

The First Medical Center of the PLA General Hospital

chainingli@vip.163.com+86 150 1136 2982

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026