PS43: Innovation in Motion: How Large Language Models Expedite Clinical Development

The expanded use of artificial intelligence (AI) and machine learning (ML) throughout the drug development cycle in recent years is not surprising, due to the capabilities in solving complex problems that may be too challenging with traditional methods. In May 2023, US FDA published a discussion paper on "Using AI & ML in the Development of Drug & Biological Products", which points out the current and potential use of AI/ML in different phases of drug development. Specifically, the clinical research section highlights the potential use in various aspects of clinical operations, clinical study design and analysis. In a podcast interview, Dr. Khair ElZarrad, Director of the Office of Medical Policy from FDA Center for Drug Evaluation and Research (CDER), commented that from 2016 to today (2024), approximately 300 submissions referenced AI use, encompassing aspects from discovery to clinical research, post-market safety surveillance, and manufacturing. With generative AI setting in motion upon the release of OpenAI's GPT3 in 2000 and ChatGPT in 2022, researchers from cross-disciplines have been actively seeking innovative applications of generative AI tools such as large language models (LLMs) across industries. Such exploratory efforts gradually propagate to clinical development applications, though wide applications in production are still relatively few. On the one hand, LLM research are blooming. For instance, Wang et al (2023) examined the proprietary and open-source LLMs in patient-trial matching for patient recruitment; Adam et al (2024) utilized LLM for numeric information extraction from unstructured clinical free-text notes to improve the quality of real-world data curation; Reason et al (2024) evaluate the application of LLM to automate health economic modeling. On the other hand, many clinical trialists are still seeking good use cases and jumping through hurdles to implement LLM tools in production environment. This session will invite speakers from regulatory agency, industry and academia to share examples and case studies as well as novel methodologies utilizing LLM, to address questions such as: - What areas of clinical development are most value-adding for LLM applications? - What are the practical challenges (operational, resource, legal, etc) for wide applications of LLM in clinical development? - How can LLM experts work with other functions to promote the use of novel methodologies? This session is intended for audiences who are interested in practical considerations and the recent advancement in methodologies of LLM in clinical development space.