Actively Recruiting
Performance of Large Language Models for Structured Recognition and Refractive Prediction
Led by Jin Yang · Updated on 2025-09-19
100
Participants Needed
1
Research Sites
543 weeks
Total Duration
On this page
AI-Summary
What this Trial Is About
We conducted a single-center, retrospective observational study to evaluate large language models (ChatGPT 4o, GPT-5, DeepSeek) for automated interpretation of de-identified IOLMaster 700 reports provided as raster images. Models produced structured biometric extraction, toric IOL recommendation, and refractive predictions (sphere, cylinder, axis). Primary outcomes included parameter-level agreement and refractive error metrics; secondary outcomes included decision-support performance for toric IOL selection and agreement on ordered T-codes. No clinical intervention was performed.
CONDITIONS
Official Title
Performance of Large Language Models for Structured Recognition and Refractive Prediction
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Postoperative corrected distance visual acuity (CDVA) of 0.10 logMAR or better
- Absolute intraocular lens (IOL) rotational stability less than 10 degrees at the 1-month follow-up examination
You will not qualify if you...
- Incomplete biometric data on the examination report
- History of previous ocular surgery or ocular trauma
- Occurrence of intraoperative complications such as anterior capsular tear or posterior capsular rupture
- Development of significant postoperative complications including severe intraocular infection or inadequate pupillary dilation
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Trial Site Locations
Total: 1 location
1
Eye and ENT hospital of Fudan University
Shanghai, Shanghai Municipality, China, 200000
Actively Recruiting
Research Team
X
Xuanqiao Lin
CONTACT
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
0
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here