The U.S. Food and Drug Administration (FDA) is exploring the application of generative AI to enhance the efficiency, accuracy, and reliability of extracting pertinent information from drug labeling documents.

“Regulatory agencies consistently deal with extensive document reviews, ranging from product submissions to both internal and external communications. Large Language Models (LLMs) like ChatGPT can be invaluable tools for these tasks, however present several challenges, particularly the proprietary information, combining customized function with specific review needs, and transparency and explainability of the model’s output,” researchers said in a recently released paper.

To address challenges, FDA has developed askFDALabel, a framework for FDA drug labeling documents, vital in drug review. It operates securely, featuring a semantic search and Q&A/text-generation modules offering a cost-effective regulatory solution.

However, the researchers acknowledge in their study that while AskFDALabel marks significant progress in analyzing drug labeling documents, it also underscores important areas for future research and development.