Abstract: We are in the midst of an AI hypecycle. Large language models are everywhere you look – and they are increasingly being integrated into biomedical research and clinical care. The potential upside for AI is sky high and yet, haven’t we been here before? In this seminar, I will review why AI, and particularly machine learning, has become the technology du jour in biomedicine – again. I will provide illustrations of machine learning in support of novel biomedical discovery, including drug repurposing and automation in clinical phenotyping. At the same time, I will review how blind trust in AI can lead to numerous societal dilemmas, including violations of privacy, algorithmic unfairness, and an overall loss of trust. I will then show how these problems be represented in AI development and application lifecyle, so that problems can be spotted and addressed before they destroy our research ecosystems and clinical operations.
Bio: Bradley Malin, Ph.D. is the Accenture Professor of Biomedical Informatics, Biostatistics, and Computer Science at Vanderbilt University Medical Center. He co-founded and co-directs ADVANCE Center, which is focused on the development of foundational AI models, their translation into biomedical research and clinical practice, and continuous monitoring and surveillance. He is a principal investigator of the Instructure Core of the NIH AIM-AHEAD Program and the Ethical and Trustworthy AI Core of the NIH Bridge2AI Center. He is a member of the Board of Scientific Counselors of the National Center for Health Statistics (NCHS) of the U.S. Centers for Disease Control and Prevention (CDC), as well as the Technical Anonymisation Group (TAG) of the European Medicines Agency. Among various honors, he is an elected fellow of the National Academy of Medicine and was a recipient of the Presidential Early Career Award for Scientists and Engineers (PECASE)