Multi-Artificial Intelligence Agents for Enhancing Clinical Decision Support

This session highlights how multi-AI agents can be used to address persistent workflow challenges in clinical decision support, drawing from our real-world experience improving a clinical decision support system (CDSS) for end-of-life care planning. We demonstrate how Large Language model (LLM)-enhanced, self-reflecting and tool-enhanced agents can automate high-risk patient selection, reduce manual workload and improve care coordination. Attendees will gain actionable strategies for how to tackle common pain points in clinical decision support with AI-agent solutions. Results from our CDSS integrations illustrate improved efficiency, accuracy and continuity of care. We posit that these multi-AI agent approaches, validated in end-of-life care CDSS, can be adapted to diverse healthcare settings to solve common operational and clinical challenges.