Scholarlink

Background <p>Ophthalmological reports are often written at a complexity level that exceeds the reading ability of many patients. Large language models (LLMs) may help simplify these texts, but their performance depends on prompt design and must preserve clinical fidelity. This study evaluated whether different prompting strategies improve the readability and safety of simplified ophthalmological reports.</p> Methods <p>We analyzed 443 de-identified reports from a tele-ophthalmology platform, including 280 retinal fundus and 163 ocular ultrasound reports. Each report was simplified by four LLMs (GPT-3.5, GPT-4.0, Gemini, and Copilot) using three prompts: a basic command, a patient-oriented prompt, and a targeted 7th-grade reading level prompt. Readability was measured with the average Readability Grade Level (aRGL). A representative eligible subset of the generated texts was independently evaluated by two third-year ophthalmology residents, and each selected response underwent independent review by both evaluators, with disagreements resolved by a board-certified retina ophthalmologist. Outcomes included factual accuracy, information completeness, and potential for harm.</p> Results <p>The original reports were highly complex, with a median aRGL of 13.8 overall, 11.6 for fundus reports, and 15.4 for ocular ultrasound reports. All LLMs improved readability scores to varying degrees. Prompt engineering was a major determinant of performance, and the targeted 7th-grade prompt produced the best results across models. Copilot, Gemini, and GPT-4.0 achieved median aRGL values closest to the recommended patient-facing reading level, while GPT-3.5 showed weaker performance in some comparisons. Clinical validation showed substantial agreement between raters (kappa range, 0.70–0.97). After adjudication, 91% of simplified texts were factually accurate, 86% retained all critical information, and 95% showed no potential for harm.</p> Conclusion <p>LLMs can simplify ophthalmological reports while preserving clinical fidelity, but performance depends strongly on prompt specificity. These tools show promise for patient-facing communication, although human oversight remains essential.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Large language model based simplification of ophthalmological clinical and ancillary results for patient readability

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月8日

查看全文
  • Alexandre Antônio Marques Rosa,
  • Francisco Vinícius Moraes de Souza,
  • José Leandro Nascimento da Silva,
  • Rafael Scherer,
  • Valberto Monteiro Nunes,
  • Leandro Cabral Zacharias,
  • Gustavo Barreto Melo,
  • Taurino dos Santos Rodrigues Neto

摘要

Background

Ophthalmological reports are often written at a complexity level that exceeds the reading ability of many patients. Large language models (LLMs) may help simplify these texts, but their performance depends on prompt design and must preserve clinical fidelity. This study evaluated whether different prompting strategies improve the readability and safety of simplified ophthalmological reports.

Methods

We analyzed 443 de-identified reports from a tele-ophthalmology platform, including 280 retinal fundus and 163 ocular ultrasound reports. Each report was simplified by four LLMs (GPT-3.5, GPT-4.0, Gemini, and Copilot) using three prompts: a basic command, a patient-oriented prompt, and a targeted 7th-grade reading level prompt. Readability was measured with the average Readability Grade Level (aRGL). A representative eligible subset of the generated texts was independently evaluated by two third-year ophthalmology residents, and each selected response underwent independent review by both evaluators, with disagreements resolved by a board-certified retina ophthalmologist. Outcomes included factual accuracy, information completeness, and potential for harm.

Results

The original reports were highly complex, with a median aRGL of 13.8 overall, 11.6 for fundus reports, and 15.4 for ocular ultrasound reports. All LLMs improved readability scores to varying degrees. Prompt engineering was a major determinant of performance, and the targeted 7th-grade prompt produced the best results across models. Copilot, Gemini, and GPT-4.0 achieved median aRGL values closest to the recommended patient-facing reading level, while GPT-3.5 showed weaker performance in some comparisons. Clinical validation showed substantial agreement between raters (kappa range, 0.70–0.97). After adjudication, 91% of simplified texts were factually accurate, 86% retained all critical information, and 95% showed no potential for harm.

Conclusion

LLMs can simplify ophthalmological reports while preserving clinical fidelity, but performance depends strongly on prompt specificity. These tools show promise for patient-facing communication, although human oversight remains essential.