Decentralized AI agents share clinical reasoning to improve medical care
Beyond Federated Learning: Decentralized Agentic Systems for Self-Evolving Clinical Intelligence
Artificial Intelligence
Summary
Medical knowledge is spread across many doctors and hospitals, but current AI systems mostly focus on combining raw patient data or model details, which misses the richness of clinical experience. The paper suggests a new approach where AI agents at different healthcare institutions exchange the steps taken during diagnosis—like observations and hypotheses—rather than just raw data. This could help AI systems learn from diverse medical experiences while protecting patient privacy. The authors discuss how this idea could be built, governed, and the challenges it faces.
What this means in practice
- •For hospital data teams: Combine diagnostic reasoning patterns from multiple healthcare sites to adapt AI tools that support patient treatment over time.
- •For medical software developers: Design decentralized AI systems that exchange clinical decision-making sequences instead of raw data or model weights to improve medical tools.
A position paper. It proposes an approach and reports no results.
Authors
Haoyuan Li, Mathias Funk, Aaqib Saeed
Abstract
Clinical expertise is inherently distributed: it resides not in any single dataset or institution but in the accumulated reasoning experiences of thousands of clinicians navigating diverse patient populations, resource constraints, and evolving treatment protocols. Yet current approaches to scaling medical AI, from centralized large language models to federated learning, remain anchored to a data-centric paradigm that treats knowledge as static parameters to be aggregated. In this Perspective, we argue for a fundamental shift from data aggregation to experience aggregation. We propose Decentralized Agentic Systems (DAS), a framework in which distributed AI agents operating across healthcare institutions synthesize collective clinical intelligence by sharing abstracted reasoning trajectories rather than raw data or model parameters. Unlike federated learning, which averages numerical gradients across homogeneous model architectures, DAS exchanges structured records of clinical reasoning, specifically the sequence of observations, hypotheses, tool invocations, and outcome feedback that constitute diagnostic experience. We examine the architectural principles, deployment considerations, governance requirements, and critical open challenges of this framework, laying the groundwork for a collaborative medical AI ecosystem where distributed expertise autonomously adapts to the complexities of longitudinal patient care.