Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning
This work addresses the need for auditable, personalized, and safe ventilator decision support in intensive care, but the evaluation is retrospective and lacks concrete performance numbers.
VDSS, a human-in-the-loop multi-agent framework for ventilator decision support, uses contextual bandit preference learning to adapt to clinician-specific tuning styles, achieving higher recommendation acceptability and fewer interaction rounds in retrospective ICU trajectory replay.
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.