Health TrialsbyHealthPanel

Performance of Large Language Models for Structured Recognition and Refractive Prediction

ConditionCataract
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorJin Yang

About this trial

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 criteria

This trial does not accept healthy volunteers

Qualifiers

None

Disqualifiers

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.

Trial population

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

Trial design

Design model

Case-only

Time perspective

Retrospective

Treatments tested in this trial

Not listed

Trial groups

No trial groups listed

Trial outcomes

Primary outcomes

1

Refractive prediction error for sphere

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

Time frame
At index examination
2

Cohen's kappa with 95% CIs between model

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

Time frame
At index examination (single time point)

Secondary outcomes

1

Cylinder prediction error

Mean absolute error (MAE, diopters) of model-predicted Cylinder

Time frame
At index examination
2

Axis prediction error

Mean absolute error (MAE, diopters) of model-predicted Axis

Time frame
At index examination

Other outcomes

Sponsors and contacts

Click on the lead sponsor to view all of their trials.

Jin Yang

Lead sponsor

Eye & ENT Hospital of Fudan University

Sponsor institution

Source ClinicalTrials.gov
Apply now