AI reading of IOLMaster 700 reports to recommend toric lenses and refractive targets
Official title: Head-to-Head Evaluation of ChatGPT 4o, GPT-5, and DeepSeek for Structured Extraction, Toric IOL Recommendation, and Refractive Prediction
Run by Eye & ENT Hospital of Fudan University · NCT07183891 · Data updated 2026-11-12
This project tests whether large language models can read de-identified IOLMaster 700 report images to pull out eye measurements, recommend toric intraocular lenses, and predict postoperative refractions for people with cataract.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 100 (estimated) |
| Sponsor | Eye & ENT Hospital of Fudan University Academic / other |
| Locations | 1 site (Shanghai, Shanghai Municipality) |
| Status | Recruiting |
| Started | August 1, 2025 |
| Main results expected | December 31, 2030 |
| Study ends | December 31, 2035 |
| Registry record updated | September 19, 2025 |
| Trial ID | NCT07183891 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal candidates are people with cataract who have complete IOLMaster 700 biometric reports and who had uncomplicated surgery with good early postoperative visual acuity and rotational stability per the protocol.
✕Probably not a fit
Patients with incomplete or unreadable biometric reports, prior ocular surgery or trauma, intraoperative or significant postoperative complications, or atypical anatomy are unlikely to benefit from the model outputs.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This was a single-center, retrospective observational analysis using de-identified IOLMaster 700 report images from 54 participants (162 eyes). Three large language models (ChatGPT 4o, GPT-5, and DeepSeek) were supplied native, unprocessed raster images and prompted to (i) extract structured biometric parameters, (ii) give a binary toric candidacy decision and an institutional T-code, and (iii) provide refractive recommendations (sphere, cylinder, axis). Each model produced three independent outputs per exam; primary outcomes were parameter-level agreement and refractive error metrics, and secondary outcomes included decision-support performance for toric IOL selection and T-code agreement. No clinical interventions were performed, and the work proceeded under IRB oversight with de-identification and a waiver of consent.
Why it matters
Potential benefit: If successful, this approach could speed and standardize biometric extraction and provide automated decision support for toric IOL selection and refractive planning, reducing manual review time.
How similar studies have gone: Previous AI and machine-learning efforts have shown promise for extracting biometry and improving IOL calculations, but using large language models directly on raw report images for toric decision support is relatively novel and less validated.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: -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 Exclusion Criteria: * 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.
Where it's running
-
Eye and ENT hospital of Fudan University
Shanghai, Shanghai Municipality, China Recruiting
Study contacts
- Study coordinator: Xuanqiao Lin
- Email: 1532483480@qq.com
- Phone: +8615088920668
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Rotational Stability of the Acunex Vario Toric
This study tests whether the Acunex Vario toric extended-depth-of-focus intraocular lens stays stable in rotation and effectively reduces astigmatism for people undergoing cataract surgery.
-
Anterior segment anatomy assessment with swept-source OCT in eye surgery patients
This study tests whether swept-source OCT can detail front-eye anatomy in patients undergoing anterior segment eye surgery.
-
MiLOOP-assisted cataract surgery for dense cataracts
In people with dense cataracts, this study tests whether using the miLOOP device during cataract surgery can protect corneal cells and reduce ultrasound energy, compared with standard surgery.
-
Visual adaptation and quality of life after different IOL implantation options
This study follows adults who have cataracts and receive bilateral multifocal or mixed IOLs to see how their vision and daily life improve over 6 months.
-
Corneal Biomechanics and Surgical Astigmatism after Cataract Surgery in Pseudoexfoliation
This study tests how the cornea's biomechanical properties before cataract surgery relate to the amount of blinking surgically induced astigmatism, comparing people with pseudoexfoliation to those without.
-
Neuroplastic pain education and guided breathing during awake cataract surgery
This trial tests whether the STEIN Protocol, a non-drug approach with pain education, guided imagery, and paced breathing, helps adults having cataract surgery require less pain medicine and feel less anxious.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.