Apply to trial NCT07183891

A few quick questions so the study team can decide if you might be a fit.

Recruiting

Performance of Large Language Models for Structured Recognition and Refractive Prediction

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.

How this works

Answer a few questions
About 5 to 10 minutes. Skip-friendly where possible.
We connect you with the study team
When a site picks up your application, we introduce you to their team directly — with you on the thread.
The team reaches out to schedule screening
Usually within a few business days, via the contact you give.

EmailWe save your progress under this email and copy you when we connect you with the study team.

I agree that Hipa.ai may share my application — my name, contact details, and my answers, including health information — with the official study team for this trial so they can review my responses and contact me.

By continuing, you agree to our terms of service.

Performance of Large Language Models for Structured Recognition and Refractive Prediction

How this works

Answer a few questions

We connect you with the study team

The team reaches out to schedule screening