Comparing AI performance in reading TAP block ultrasound videos
Performance Comparison of Large Language Models in TAP Block Ultrasound Interpretation: A Double-Blind Prospective Study
This project will test whether two AI models, Gemini 2.5 Pro and ChatGPT-5.1, can accurately read TAP block ultrasound videos and match expert anesthesiologists.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 40 (estimated) |
| Ages | 18 Years to 85 Years |
| Sex | All |
| Sponsor | Kanuni Sultan Suleyman Training and Research Hospital Academic / other |
| Locations | 1 site (Istanbul, Istanbul) |
| Trial ID | NCT07261436 on ClinicalTrials.gov |
What this trial studies
This observational project compares how Gemini 2.5 Pro and ChatGPT-5.1 interpret ultrasound videos recorded during routine lateral TAP block procedures. All videos will be fully de-identified; Gemini will receive original video files while ChatGPT-5.1 will receive high-resolution GIF segments, and both models will answer the same eight structured clinical questions about anatomy, needle placement, local anesthetic spread, dermatomal effects, and safety concerns. Expert A will provide primary human reference answers and Expert B will blindly review anonymized responses from Expert A and both AIs. No extra procedures are performed and only patients undergoing routine TAP blocks who consent will be included.
Who should consider this trial
Good fit: Adults aged 18–85 with ASA physical status I–III who are undergoing elective surgery with a lateral TAP block recorded as part of routine anesthesia care and who can give written consent.
Not a fit: Patients not undergoing TAP blocks, those with unsuccessful or incomplete blocks, or people whose ultrasound recordings are low quality or missing are unlikely to benefit from the findings.
Why it matters
Potential benefit: If successful, this could help flag incorrect or incomplete TAP blocks, speed postprocedure review, and support clinicians in interpreting ultrasound videos.
How similar studies have performed: AI image-analysis tools have shown promise for ultrasound interpretation in other settings, but applying large language models to TAP block video interpretation is relatively novel and less tested.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Adults aged 18-85 years * ASA I-III physical status * Undergoing elective surgery with a lateral TAP block performed as part of routine anesthesia care * Complete ultrasound-guided block procedure recorded on video * Able to provide written informed consent Exclusion Criteria: * Unsuccessful or incomplete TAP block procedure * Poor-quality ultrasound video (needle tip or anesthetic spread not visible) * Missing demographic or clinical data * Withdrawal of consent at any time
Where this trial is running
Istanbul, Istanbul
- Health Science University İstanbul Kanuni Sultan Süleyman Education and Training Hospital — Istanbul, Istanbul, Turkey (Türkiye) (Recruiting)
Study contacts
- Study coordinator: Engin ihsan Turan, principal investigator
- Email: enginihsan@hotmail.com
- Phone: +905382431114
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.