ScholarDeck

AI / informaticsFrontiers in digital health · 2026

Assessing retina-specific ophthalmic counseling generated by an early public large language model across different levels of clinical urgency.

Dominic M Choo, Tyler A Durham, Kishan G Patel

OphthalmologyAI / informatics

Medical terminology was a common reason for difficulty understanding large language model counseling.

Assessing retina-specific ophthalmic counseling generated by an early public large language model across different levels of clinical urgency.

Dominic M Choo et al. · Frontiers in digital health · 2026

Purpose

To evaluate how the quality of retina-specific ophthalmology counseling provided by an early publicly available large language model (LLM) differs when advising patients with varying clinical characteristics and risk factors.

Methods

Prospective, cross-sectional study.

49%

Results

nearly half of reasons for difficulty understanding counseling were due to medical words

More results

Counseling accuracy differed across levels of clinical urgency ( p = 0.002) but remained consistent between high- and low-urgency vignettes of AMD ( p = 0.081) and DR ( p = 0.5), albeit not for RD ( P < 0.001).

More results

Counseling urgency did not differ significantly from clinical urgency of all vignettes, except for the high-urgency AMD ( p = 0.013) and high-urgency RD ( p < 0.001).

While counseling urgency did not significantly differ between high- and low-urgency vignettes of AMD ( p = 0.055) and RD ( p = 0.3), it did differ for the DR vignettes ( p < 0.001).

“

Conclusion · 1 of 2

The evaluated LLM-generated counseling outputs were largely similar across the sampled retinal vignettes with differing clinical urgency.

Conclusion · 2 of 2

Future studies should investigate the optimization of LLM prompting needed to garner counseling of consistent/appropriate accuracy, readability, empathy, and communication of urgency for specific conditions.

Post

Assessing retina-specific ophthalmic counseling generated by an early public large language model across different levels of clinical urgency.

Medical terminology was a common reason for difficulty understanding large language model counseling.

Related papers