ArticleOphthalmology and therapy2025
Large Language Models: Pioneering New Educational Frontiers in Childhood Myopia.
Article in Ophthalmology and therapy, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 11 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
11 citing papers in PubMed.
- Ability of Large Language Models to Answer Patients' Questions and Generate Educational Materials for Uncommon Retinal Conditions.Journal of vitreoretinal diseases · 2026Article
- Large Language Model Simplification of Open Access Pediatric Strabismus Literature: Cross-Sectional Validation of Readability and Clinical Fidelity.JMIR formative research · 2026Article
- Comparative Performance of AI Models and Clinicians in Evidence-Based Cardiovascular Disease Management for People Living With HIV: Comparative Study.Journal of medical Internet research · 2026Article
- Artificial intelligence in pediatric myopia - a narrative review.Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie · 2026Review
- Performance of ChatGPT-4o in Providing Information on Pediatric Inborn Errors of Immunity: A Cross-Sectional Evaluation.Journal of clinical medicine · 2026Article
- Optimizing Large Language Model Responses to Medical Queries: a Cross-sectional Study On the Effective Use of Chatgpt for Cancer-related Questions.Journal of medical systems · 2026Article
- Assessing large language models as assistive tools in selecting first trial lens parameters for orthokeratology.Frontiers in medicine · 2026Article
- Evaluating large language models in specialized myopia knowledge and clinical reasoning.Frontiers in medicine · 2026Article
- Large Language Model-Generated Patient Education Materials in Pediatric Ophthalmology: A Scoping Review.Clinical ophthalmology (Auckland, N.Z.) · 2026Review
- Quality assessment of patient-facing urologic telesurgery content using validated tools.Journal of robotic surgery · 2025Article
- Digital technologies in enhancing hierarchical vision health management for the next 1000 days of children's life: multi-component economic evaluation.The Lancet regional health. Western Pacific · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
introductionThis study aimed to evaluate the performance of three large language models (LLMs), namely ChatGPT-3.5, ChatGPT-4o (o1 Preview), and Google Gemini, in producing patient education materials (PEMs) and improving the readability of online PEMs on childhood myopia.
methodsLLM-generated responses were assessed using three prompts. Prompt A requested to "Write educational material on childhood myopia." Prompt B added a modifier specifying "a sixth-grade reading level using the FKGL (Flesch-Kincaid Grade Level) readability formula." Prompt C aimed to rewrite existing PEMs to a sixth-grade level using FKGL. Reponses were assessed for quality (DISCERN tool), readability (FKGL, SMOG (Simple Measure of Gobbledygook)), Patient Education Materials Assessment Tool (PEMAT, understandability/actionability), and accuracy.
resultsChatGPT-4o (01) and ChatGPT-3.5 generated good-quality PEMs (DISCERN 52.8 and 52.7, respectively); however, quality declined from prompt A to prompt B (p = 0.001 and p = 0.013). Google Gemini produced fair-quality (DISCERN 43) but improved with prompt B (p = 0.02). All PEMs exceeded the 70% PEMAT understandability threshold but failed the 70% actionability threshold (40%). No misinformation was identified. Readability improved with prompt B; ChatGPT-4o (01) and ChatGPT-3.5 achieved a sixth-grade level or below (FGKL 6 ± 0.6 and 6.2 ± 0.3), while Google Gemini did not (FGKL 7 ± 0.6). ChatGPT-4o (01) outperformed Google Gemini in readability (p < 0.001) but was comparable to ChatGPT-3.5 (p = 0.846). Prompt C improved readability across all LLMs, with ChatGPT-4o (o1 Preview) showing the most significant gains (FKGL 5.8 ± 1.5; p < 0.001).
conclusionsChatGPT-4o (o1 Preview) demonstrates potential in producing accurate, good-quality, understandable PEMs, and in improving online PEMs on childhood myopia.
Indexed as
Identifiers
What Socratic holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the Socratic graph.