Supporting Responsible Deployment of AI in Healthcare with Sustainable and Generalizable Learning Prediction Systems

Abstract:

Successfully deploying impactful clinical AI tools is no small feat. Not only must we navigate clinical, technical, sociotechnical, and ethical challenges, but most critically, we ask patients and providers to trust and rely on these tools when making important health decisions. Such efforts compel us to be responsible stewards and ensure AI tools consistently perform as promised—overall, over time, across settings, and for all demographic, clinical, and geographic populations.

Learning prediction systems, an extension of the learning health system paradigm, can enable generalizable and sustainable predictive AI tools and minimize disruptions resulting from deploying these tools across evolving clinical environments. We will explore novel approaches to localization and post-deployment maintenance of clinical prediction tools, including challenges and opportunities to fostering health and equity through model sustainability.

About the Speaker:

Sharon Davis is an Assistant Professor of Biomedical Informatics and the Associate Director of the Center for Improving the Public’s Health through Informatics at Vanderbilt University Medical Center. She is a biomedical informatician with a background in public health and statistics. Her current research emphasizes clinical predictive analytics, post-marketing surveillance, algorithmic vigilance, and responsible stewardship of artificial intelligence in healthcare. She is particularly interested in addressing the practical challenges of applied learning prediction systems, focusing on methods supporting the implementation of reliable, impactful, fair, and sustainable clinical AI models underlying tools for decision support and population management. The arc of Dr. Davis’ career and her current focus on methods promoting practical clinical prediction are guided by a commitment to leveraging health and data sciences to advance tools that empower individuals, promote healthy communities, and reduce health inequities.