Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators

TL;DR

This paper advocates for rethinking health AI agents as collaborative mediators within multi-stakeholder healthcare interactions, emphasizing shared understanding and contextual awareness to improve decision-making.

Contribution

It introduces a conceptual framework for designing AI health collaborators that enhance multi-party communication and address fragmentation in healthcare settings.

Findings

Fragmented situational awareness causes adherence issues.

Siloed AI tools fail to improve multi-stakeholder collaboration.

Proposed framework supports shared understanding and goal alignment.

Abstract

Large language model based health agents are increasingly used by health consumers and clinicians to interpret health information and guide health decisions. However, most AI systems in healthcare operate in siloed configurations, supporting individual users rather than the multi-stakeholder relationships central to healthcare. Such use can fragment understanding and exacerbate misalignment among patients, caregivers, and clinicians. We reframe AI not as a standalone assistant, but as a collaborator embedded within multi-party care interactions. Through a clinically validated fictional pediatric chronic kidney disease case study, we show that breakdowns in adherence stem from fragmented situational awareness and misaligned goals, and that siloed use of general-purpose AI tools does little to address these collaboration gaps. We propose a conceptual framework for designing AI collaborators that surface contextual information, reconcile mental models, and scaffold shared understanding while preserving human decision authority.