Department of Pharmacology & Therapeutics, College of Medicine & Medical Sciences, Arabian Gulf University, Manama, Kingdom of Bahrain.
Speciality Dental Residency Program, Primary Health Care Centers, Manama, Kingdom of Bahrain.
Expert Rev Clin Pharmacol. 2024 Aug;17(8):731-741. doi: 10.1080/17512433.2024.2363840. Epub 2024 Jun 4.
The US Food and Drug Administration (USFDA) communicates new drug safety concerns through drug safety communications (DSCs) and medication guides (MGs), which often challenge patients with average reading abilities due to their complexity. This study assesses whether large language models (LLMs) can enhance the readability of these materials.
We analyzed the latest DSCs and MGs, using ChatGPT 4.0© and Gemini© to simplify them to a sixth-grade reading level. Outputs were evaluated for readability, technical accuracy, and content inclusiveness.
Original materials were difficult to read (DSCs grade level 13, MGs 22). LLMs significantly improved readability, reducing the grade levels to more accessible readings (Single prompt - DSCs: ChatGPT 4.0© 10.1, Gemini© 8; MGs: ChatGPT 4.0© 7.1, Gemini© 6.5. Multiple prompts - DSCs: ChatGPT 4.0© 10.3, Gemini© 7.5; MGs: ChatGPT 4.0© 8, Gemini© 6.8). LLM outputs retained technical accuracy and key messages.
LLMs can significantly simplify complex health-related information, making it more accessible to patients. Future research should extend these findings to other languages and patient groups in real-world settings.
美国食品和药物管理局（USFDA）通过药物安全通讯（DSC）和用药指南（MG）传达新的药物安全问题，由于其复杂性，这些信息往往令阅读能力一般的患者感到困惑。本研究评估大型语言模型（LLM）是否可以提高这些材料的可读性。
我们分析了最新的 DSC 和 MGs，使用 ChatGPT 4.0©和 Gemini©将其简化至六年级阅读水平。评估输出的可读性、技术准确性和内容完整性。
原始材料难以阅读（DSC 阅读水平 13，MG 阅读水平 22）。LLM 显著提高了可读性，将阅读水平降低至更易理解的程度（单一提示——DSC：ChatGPT 4.0©10.1，Gemini©8；MG：ChatGPT 4.0©7.1，Gemini©6.5。多次提示——DSC：ChatGPT 4.0©10.3，Gemini©7.5；MG：ChatGPT 4.0©8，Gemini©6.8）。LLM 输出保留了技术准确性和关键信息。
LLM 可以显著简化复杂的与健康相关的信息，使其更容易被患者理解。未来的研究应将这些发现扩展到其他语言和现实环境中的患者群体。
