Search AMIA.org

In this talk, James Zou, PhD explores how generative AI agents can enable drug discovery and development. He introduces the Virtual Lab—a collaborative team of AI scientist agents conducting in silico research meetings to tackle open-ended R&D projects.

This dynamic discussion will feature perspectives from academia, clinical practice, and industry, highlighting practical strategies for integrating AI solutions into healthcare settings. Panelists will share experiences, challenges, and lessons learned from implementation efforts, with a focus on governance, workflow integration, and impact assessment.

This talk shares insights from real-world use of text-based AI at the bedside—from opioid misuse screening via EHR notes to Ambient AI for automating documentation—highlighting both opportunities and risks, as well as approaches for evaluation and improvement.

Large language models (LLMs) have shown remarkable potential in the medical domain, with specialized medical LLMs developed and applied across a variety of tasks. However, their effectiveness in medicine remains uncertain, and practical guidance for their deployment in specific applications is still limited.

The deployment of text-based AI models at the point of care introduces new opportunities—and risks—for improving clinical documentation, communication, and decision support. In this talk, I will share lessons learned from the real-world bedside implementation of AI systems that use the EHR notes for screening opioid misuse to Ambient AI for automating clinical documentation, as well as methods for monitoring, evaluation, and continuous improvement.