Frontlight ResearchEarly access
Taking peopleNo phase
Performance of Large Language Models for Structured Recognition and Refractive Prediction
Key facts
- Who runs it
- Jin Yang
- Where
- China1 site in 1 countryChoose a country to see its sites
- Trial code
- Status
- Recruiting
- People taking part
- 100 people, planned
- Started
- 1 Aug 2025
- Expected to end
- 31 Dec 2035
- Type of study
- Observational
- Record updated
- 19 September 2025
Who can take part
- Age
- 18 years and older
- Sex
- Women and men
- Healthy volunteers
- Cannot take part
The registry criteria, word for word
Show all 5 criteriaShow less
Who can take part
- -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
Who cannot take part
- a history of previous ocular surgery or ocular trauma
- the development of significant postoperative complications, including but not limited to severe intraocular infection or inadequate pupillary dilation
- incomplete biometric data on the examination report
- the occurrence of intraoperative complications, such as an anterior capsular tear or posterior capsular rupture
This trial is currently available in China.
It has sites in one country. Choose a country to see its sites.
About the trial
What the trial wants to find out
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.
Questions to ask the study team
- How often do I need to come in, and for how long each time?
- Are travel costs paid?
- Can I keep my own doctor?
- What happens if I want to stop?
Contact the study team: see the registry record → Contacts and Locations
Print a page for my doctorData and sources
- Registry record
- Listed on ClinicalTrials.gov.How to verify a trial in the registry
- Official title
- Head-to-Head Evaluation of ChatGPT 4o, GPT-5, and DeepSeek for Structured Extraction, Toric IOL Recommendation, and Refractive Prediction
- Record updated
- 19 September 2025