Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning
Quick Take
The Ventilator Decision Support System (VDSS) enhances ventilator management by integrating human feedback with a contextual bandit approach, improving recommendation acceptability and reducing interaction rounds in ICU settings. This multi-agent framework allows for personalized decision-making while providing traceable evidence for clinician review.
Key Points
- VDSS uses a human-in-the-loop approach for personalized ventilator decision-making.
- Employs a contextual bandit for online adaptation of clinician preferences.
- Structured rejection feedback minimizes unproductive iterations during decision-making.
- Retrospective ICU trajectory analysis shows higher acceptability of recommendations.
- Facilitates improved human-AI collaboration in clinical environments.
Article Content
From source RSS / original summaryarXiv:2605. 23320v1 Announce Type: new Abstract: Ventilator decision support requires sequential decisions that track evolving physiology and disease trajectories while respecting safety boundaries and clinician specific tuning styles. Rule based approaches rarely generalize personalization, and end to end reinforcement learning or single large language model systems remain difficult to control and audit.
We propose the Ventilator Decision Support System (VDSS), a human in the loop multi agent framework that coordinates modular decision components through contract driven structured interfaces and produces traceable evidence for review. VDSS performs online preference adaptation with a contextual bandit, updating clinician specific preferences from the final accepted decision at each adjustment cycle and using them to guide subsequent recommendations.
Structured rejection feedback triggers targeted replanning to reduce unproductive iterations and improve interaction stability. Retrospective ICU trajectory replay with expert review indicates higher recommendation acceptability and fewer interaction rounds to reach an acceptable plan, supporting clinically deployable human AI collaboration.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Importance of Out-of-Band Metadata for Safe Autonomous Agents: The Redpanda Agentic Data Plane
The Redpanda Agentic Data Plane (ADP) introduces out-of-band metadata channels to enhance the safety of autonomous AI agents, ensuring secure data access and tamper-proof audit trails. This architecture mitigates risks associated with unpredictable AI behavior by enforcing governance throughout the agent lifecycle, demonstrated in a multi-agent trading system with strict data scoping and approval thresholds.
