Gastrointestinal Neoplasm, Mass Lesion
Conditions
Keywords
endoscopic ultrasound, solid mass lesion, artificial intelligence, fine needle biopsy
Brief summary
The aim of this study is to determine if the widely available artificial intelligence platform ChatGPT can accurately identify the abnormalities present on cytology specimens obtained at EUS-FNB of solid mass lesions in the gastrointestinal tract, in comparison with interpretation by cytopathologists as the gold standard.
Detailed description
The diagnostic accuracy of EUS-guided fine needle biopsy of lesions in the gastrointestinal tract is dependent on the availability of a cytopathologist to render a rapid on-site evaluation (ROSE), with studies showing that the presence of an on-site cytopathologist improves the diagnostic yield, decreases the number of inadequate or unsatisfactory samples, and limits the number of passes required to establish a diagnosis. However, the availability of ROSE is variable across centers and regions, with the availability of onsite cytopathology services limited to a handful of tertiary referral centers in the United States. ChatGPT is a universally available, generative artificial intelligence program developed by OpenAI. The aim of this study is to determine if this AI platform can accurately identify the abnormalities present on cytology specimens obtained at EUS-FNB of solid mass lesions in the gastrointestinal tract, in comparison with interpretation by cytopathologists as the gold standard.
Interventions
DIAGNOSTIC_TESTEUS-guided fine needle biopsy
EUS-guided fine needle biopsy of solid mass lesions in the gastrointestinal tract
Sponsors
Orlando Health, Inc.
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age 18 years old or greater * Patients undergoing EUS-guided fine needle biopsy of solid mass lesions in the gastrointestinal tract
Exclusion criteria
* Age less than 18 years * Patients not undergoing sampling of solid mass lesions at EUS * Patients with cystic lesions in the gastrointestinal tract
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic adequacy at rapid onsite evaluation | 1 day | The ability of the AI systems to interpret specimen adequacy on cytology images |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic accuracy at rapid onsite evaluation | 7 days | The ability of the AI systems to interpret and diagnose cytology images |
Countries
United States
Contacts
PRINCIPAL_INVESTIGATORJi Young Bang, MD MPH
Orlando Health
Outcome results
None listed