Enhancing readability of USFDA patient communications through large language models: a proof-of-concept study

ABSTRACT

Background

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.

Methods

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.

Results

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.

Conclusion

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.

KEYWORDS:

• Artificial intelligence
• ChatGPT
• gemini
• USFDA
• drug safety communications
• medication Guides

Declaration of interest

The authors have no relevant affiliations or financial involvement with any organization or entity with a financial interest in or financial conflict with the subject matter or materials discussed in the manuscript. This includes employment, consultancies, honoraria, stock ownership or options, expert testimony, grants, patents received or pending, or royalties.

Reviewer disclosures

Peer reviewers on this manuscript have no relevant financial or other relationships to disclose.

Author contributions statement

Conception of the study and design of the study: K Sridharan; Data acquisition: K Sridharan, G Sivaramakrishnan; Data analysis and interpretation: K Sridharan, G Sivaramakrishnan; Initial draft of the manuscript: K Sridharan; Revision and approval of the final draft of the manuscript: K Sridharan, G Sivaramakrishnan; Responsibility and be accountable for the contents of the article and to share responsibility to resolve any questions raised about the accuracy or integrity of the published work: K Sridharan.

Acknowledgement

We acknowledge the use of ChatGPT for correcting grammar in the manuscript.

Additional information

Funding

This paper was not funded.