Responsible Natural Language Processing for Researchers, Clinicians, and Patients

Language is embedded across medicine, from clinical notes to medical literature to patient communication. Natural language processing, and particularly large language models, can help us to reimagine how we process and communicate this clinical text, which could have transformative effects for the practice of medicine.

This talk will discuss open challenges, opportunities and solutions for NLP to accelerate clinical discovery for researchers, streamline workflows at the point-of-care for physicians, and improve the accessibility of health information for patients. First, I will discuss scalable techniques for clinical information extraction that leverage large language models. Next, I will describe a paradigm for smarter electronic health records that decreases documentation burden, incentivizes the creation of high-quality data at the point-of-care, and aids in proactive information retrieval. This will include a discussion of the difficulties of evaluating generative AI deployments in medicine. Finally, I will discuss our work studying how patients may be using large language models to access health information and advice, and the opportunities and pitfalls of doing so.