Performance of Large Language Models for Structured Recognition and Refractive Prediction

NCT07183891 | Recruiting

• 1 other identifier: Totic-2025-001
• Study Type: observational
• Target: 100
• Locations: 1 country
• Sites: 1

Brief 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.

Conditions

Cataract

Keywords

cataract; toric IOL; astigmatism

Outcome Measures

Primary Outcomes (2)

• Refractive prediction error for sphere

  Mean absolute error (MAE, diopters) of model-predicted sphere versus clinical reference

  At index examination

• Cohen's kappa with 95% CIs between model

  Cohen's kappa with 95% CIs between model outputs and clinician-validated reference for per-parameter

  At index examination (single time point)

Secondary Outcomes (2)

• Cylinder prediction error

  At index examination

• Axis prediction error

  At index examination

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

cataract patients who had undergone phacoemulsification and implantation of an AcrySof IQ Toric monofocal intraocular lens

You may qualify if:

• 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

You may not qualify if:

• incomplete biometric data on the examination report;
• a history of previous ocular surgery or ocular trauma
• the occurrence of intraoperative complications, such as an anterior capsular tear or posterior capsular rupture
• the development of significant postoperative complications, including but not limited to severe intraocular infection or inadequate pupillary dilation.

Sponsors & Collaborators

• Jin Yang: lead

Study Sites (1)

Eye and ENT hospital of Fudan University

Shanghai, Shanghai Municipality, 200000, China

RECRUITING

MeSH Terms

Conditions

Cataract; Astigmatism

Condition Hierarchy (Ancestors)

Lens Diseases; Eye Diseases; Refractive Errors

Central Study Contacts

Xuanqiao Lin

CONTACT

+8615088920668; 1532483480@qq.com

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Chief Physician

Study Record Dates

• First Submitted: September 14, 2025
• First Posted: September 19, 2025
• Study Start: August 1, 2025
• Primary Completion (Estimated): December 31, 2030
• Study Completion (Estimated): December 31, 2035
• Last Updated: September 19, 2025

Record last verified: 2025-09

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)