Clinical Research Directory
Browse clinical research sites, groups, and studies.
Expert-Validated ChatGPT Support for Arterial Blood Gas Interpretation
Sponsor: Izmir Katip Celebi University
Summary
This randomized controlled study evaluated whether expert-validated ChatGPT support improved arterial blood gas (ABG) interpretation performance among early-career non-specialist physicians. Participants completed a baseline assessment consisting of 11 standardized clinical scenarios covering five domains of ABG interpretation. Eligible participants who entered the reassessment phase were randomly assigned to either an AI-supported group or a control group. One week after baseline assessment, participants completed a posttest using the same clinical scenarios. The AI-supported group received expert-validated ChatGPT responses before answering each case, whereas the control group completed the assessment without AI support. The primary outcome was posttest total ABG interpretation accuracy across 55 scored items, compared between groups after adjustment for baseline accuracy. Secondary outcomes included changes in total accuracy, domain-specific accuracy, case-level performance, and item-level accuracy.
Official title: Expert-Validated Generative AI Support for Arterial Blood Gas Interpretation in Early-Career Non-Specialist Physicians: A Randomized Controlled Study
Key Details
Gender
All
Age Range
Any - Any
Study Type
INTERVENTIONAL
Enrollment
161
Start Date
2026-05-20
Completion Date
2026-06-05
Last Updated
2026-09-30
Healthy Volunteers
Yes
Conditions
Interventions
Expert-Validated ChatGPT Support
Before each of the 11 arterial blood gas (ABG) cases, participants viewed a standardized ChatGPT response that had been independently validated against the expert reference key by three physician experts. The response addressed five scored domains and included a brief rationale. Participants then provided their own answers to each case.
Locations (1)
Gaziantep City Hospital
Gaziantep, Gaziantep, Turkey (Türkiye)