Head-to-Head Evaluation of ChatGPT 4o, GPT-5, and DeepSeek for Structured Extraction, Toric IOL Recommendation, and Refractive Prediction

Status: Recruiting
Location: See location...
Study Type: Observational
SUMMARY

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.

Eligibility
Participation Requirements
Sex: All
Minimum Age: 18
Healthy Volunteers: f
View:

• postoperative corrected distance visual acuity (CDVA) of 0.10 logMAR or better -an absolute IOL rotational stability of less than 10∘ at the 1-month follow-up examination

Locations
Other Locations
China
Eye and ENT hospital of Fudan University
RECRUITING
Shanghai
Contact Information
Primary
Xuanqiao Lin
1532483480@qq.com
+8615088920668
Time Frame
Start Date: 2025-08-01
Estimated Completion Date: 2035-12-31
Participants
Target number of participants: 100
Related Therapeutic Areas
Sponsors
Leads: Jin Yang

This content was sourced from clinicaltrials.gov