A diagnostic test of an explainable artificial intelligence model based micro-probe endoscopic ultrasonography for gastrointestinal stromal tumors

Development and validation of an Intelligent diagnosis model for submucosal tumors in the digestive tract based on multimodal endoscopic data

Status

Active, not recruiting

Phases

Early Phase 1

Study type

Observational

Source

ChiCTR

Registry ID

ChiCTR2400080928

Enrollment

Unknown

Registered

2024-02-18

Start date

2023-06-29

Completion date

Unknown

Last updated

2024-02-19

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

Conditions

submucosal tumors of the digestive tract

Interventions

Gold Standard:Pathological diagnosis is the gold standard for the diagnosis

Index test:An multimodal artificial intelligence assisted endoscopic ultrasound diagnosis system

Eligibility

Sex/Gender

All

Age

18 Years to 100 Years

Inclusion criteria

Inclusion criteria: 1.Patients with clearly pathological diagnosed of SMTs. 2.Patients with complete imaging and diagnostic reports of white light endoscopy and EUS. 3.Patients with willingness to participate. For prospectively enrolled patients, informed consent was obtained and signed by the patients. Informed consent was not required for retrospective cases.

Exclusion criteria

Exclusion criteria: 1. Unqualified WLE, EUS images, including images of poor quality, repeated or obscured by measuring lines. 2. Patients without definite pathological diagnosis.

Design outcomes

Primary

Measure	Time frame
accuracy;AUC;	—

Secondary

Measure	Time frame
sensitivity;specificity;	—

Countries

China

Contacts

Public ContactLi Jiao

The Third People's Hospital of Chengdu

cylijiao@163.com+86 136 5805 3888

Outcome results

None listed

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