Multi-Agentic AI Workflows in Healthcare
Artificial intelligence in healthcare is rapidly moving beyond single models toward multi-agent systems—coordinated workflows in which multiple AI agents collaborate to perform complex clinical tasks such as triage, diagnostics, patient stratification, and decision support. While these systems promise greater flexibility and performance, they also introduce new challenges related to trust, safety, governance, and real-world deployment.
This course provides a structured, practitioner-focused introduction to multi-agent AI workflows in healthcare, designed for engineers, data scientists, product leaders, and healthcare technologists who want to move from isolated AI pilots to reliable, scalable, and clinically responsible systems. Rather than focusing on model internals alone, the course emphasizes system-level design, including agent coordination, uncertainty handling, human-in-the-loop decision-making, and failure-mode mitigation.
Through real healthcare case studies—including radiology pipelines, oncology decision support, and emergency department triage—participants will learn how different agent roles (classifiers, planners, explainers, and watchdogs) interact, where risks emerge, and how trust and safety can be engineered into AI workflows from the outset. The course introduces practical frameworks for evaluating readiness, managing risk, and assessing return on investment when deploying agentic AI in clinical environments.
By the end of the course, participants will be equipped with the conceptual tools and evaluation frameworks needed to critically assess multi-agent AI systems, design safer human-AI collaborations, and make informed decisions about adopting agent-based workflows in healthcare settings.
Instructor
Arvind Rao
Arvind Rao is a Professor in the Department of Computational Medicine and Bioinformatics at the University of Michigan. His group uses image analysis and machine learning methods to link image-derived phenotypes with structured datasets, across biological scale. Arvind received his PhD in Electrical Engineering and Bioinformatics from the University of Michigan, specializing in transcriptional genomics, and was a Lane Postdoctoral Fellow at Carnegie Mellon University, specializing in bioimage informatics. He is a Fellow of American Medical Informatics Association (AMIA), The Royal College of Pathology (RCPath) in the UK (by published works) and American Association for Advancement in Science (AAAS). He is also a senior member of the IEEE.
Publication Year: 2026