Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators

• URL: http://arxiv.org/abs/2603.24986v1
• Date: Thu, 26 Mar 2026 03:27:13 GMT
• Title: Rethinking Health Agents: From Siloed AI to Collaborative Decision Mediators
• Abstract summary: We show that AI systems in healthcare operate in siloed configurations, supporting individual users rather than the multi-stakeholder relationships central to healthcare.<n>We propose a conceptual framework for designing AI collaborators that surface contextual information, reconcile mental models, and scaffold shared understanding.
• Score: 12.746145837575709
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Clinical Reasoning in the Age of AI: Longitudinal Cognition and Human-AI Collaboration [0.7588418803784354]
  Understanding how doctors reason through clinical problems in real-world settings is critical for design of effective AI reasoning systems.<n>This study offers a unified framework for understanding clinical reasoning as a context-sensitive, temporally extended process.
  arXiv  Detail & Related papers  (2026-06-07T03:51:15Z)
• A longitudinal health agent framework [3.679030425488578]
  We propose a multi-layer framework and corresponding agent architecture that operationalizes adaptation, coherence, continuity, and agency across repeated interactions.<n>We demonstrate how longitudinal agents can maintain meaningful engagement, adapt to evolving goals, and support safe, personalized decision-making over time.
  arXiv  Detail & Related papers  (2026-04-13T20:03:53Z)
• Dyadic Partnership(DP): A Missing Link Towards Full Autonomy in Medical Robotics [49.546007696964146]
  We introduce the concept of Dyadic Partnership, a new paradigm in which robots and clinicians engage in intelligent, expert interaction and collaboration.<n>This article outlines the foundational components needed to enable such systems, including foundation models for clinical intelligence, multi-modal intent recognition, co-learning frameworks, advanced visualization, and explainable, trust-aware interaction.
  arXiv  Detail & Related papers  (2026-04-13T13:05:14Z)
• Augmenting Clinical Decision-Making with an Interactive and Interpretable AI Copilot: A Real-World User Study with Clinicians in Nephrology and Obstetrics [36.981753143345664]
  We present AICare, an interactive and interpretable AI copilot for collaborative clinical decision-making.<n>By analyzing longitudinal electronic health records, AICare grounds dynamic risk predictions in scrutable visualizations.
  arXiv  Detail & Related papers  (2026-01-31T13:41:32Z)
• Designing AI Tools for Clinical Care Teams to Support Serious Illness Conversations with Older Adults in the Emergency Department [53.52248484568777]
  The work contributes empirical understanding of ED-based serious illness conversations and provides design considerations for AI in high-stakes clinical environments.<n>We conducted interviews with two domain experts and nine ED clinical care team members.<n>We characterized a four-phase serious illness conversation workflow (identification, preparation, conduction, documentation) and identified key needs and challenges at each stage.<n>We present design guidelines for AI tools supporting SIC that fit within existing clinical practices.
  arXiv  Detail & Related papers  (2025-05-30T21:15:57Z)
• Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios [46.729092855387165]
  We study the choice of the backbone LLM for medical AI agents, which is the foundation for the agent's overall reasoning and action generation.<n>Our findings demonstrate o1's ability to enhance diagnostic accuracy and consistency, paving the way for smarter, more responsive AI tools.
  arXiv  Detail & Related papers  (2024-11-16T18:19:53Z)
• MedAide: Information Fusion and Anatomy of Medical Intents via LLM-based Agent Collaboration [19.951977369610983]
  MedAide is a medical multi-agent collaboration framework designed to enable intent-aware information fusion and coordinated reasoning.<n>We introduce a regularization-guided module that combines syntactic constraints with retrieval augmented generation to decompose complex queries.<n>We also propose a dynamic intent prototype matching module to achieve adaptive recognition and updating of the agent's intent.
  arXiv  Detail & Related papers  (2024-10-16T13:10:27Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• Understanding how the use of AI decision support tools affect critical thinking and over-reliance on technology by drug dispensers in Tanzania [0.0]
  Drug shop dispensers were on AI-powered technologies when determining a differential diagnosis for a presented clinical case vignette. We found that dispensers relied on the decision made by the AI 25 percent of the time, even when the AI provided no explanation for its decision.
  arXiv  Detail & Related papers  (2023-02-19T05:59:06Z)
• What Do End-Users Really Want? Investigation of Human-Centered XAI for Mobile Health Apps [69.53730499849023]
  We present a user-centered persona concept to evaluate explainable AI (XAI) Results show that users' demographics and personality, as well as the type of explanation, impact explanation preferences. Our insights bring an interactive, human-centered XAI closer to practical application.
  arXiv  Detail & Related papers  (2022-10-07T12:51:27Z)
• Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users [51.644376281196394]
  When using medical images for diagnosis, it is important that the images are of high quality.<n>In telemedicine, a common problem is that the quality issue is only flagged once the patient has left the clinic, meaning they must return in order to have the exam redone.<n>This paper reports on the development of an AI system for flagging and explaining low-quality medical images in real-time.
  arXiv  Detail & Related papers  (2022-07-06T14:53:26Z)
• IAC: A Framework for Enabling Patient Agency in the Use of AI-Enabled Healthcare [1.0878040851638]
  We present IAC (Informing, Assessment, and Consent), a framework for evaluating patient response to the introduction of AI-enabled digital technologies in healthcare settings. The framework is composed of three core principles that guide how healthcare practitioners can inform patients about the use of AI in their healthcare. We propose that the principles composing this framework can be translated into guidelines that improve practitioner-patient relationships and, concurrently, patient agency regarding the use of AI in healthcare.
  arXiv  Detail & Related papers  (2021-10-29T16:13:15Z)
• The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation [81.72197368690031]
  We present a new benchmarking suite designed specifically for medical sequential decision making. The Medkit-Learn(ing) Environment is a publicly available Python package providing simple and easy access to high-fidelity synthetic medical data.
  arXiv  Detail & Related papers  (2021-06-08T10:38:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.