多智能体框架用于解释多变量生理时间序列
A Multi-Agent Framework for Interpreting Multivariate Physiological Time Series
AI总结：
本研究提出Vivaldi多智能体框架，通过对比不同模型表现，发现智能体系统在非思考模型中提升解释质量，但在思考模型中反而降低相关性，强调了计算外部化在医疗AI中的重要性。
摘要：
连续生理监测在急诊护理中至关重要，但部署可信赖的AI却具有挑战性。尽管大语言模型（LLMs）能够将复杂的生理信号转换为临床叙述，但不清楚智能体系统相对于零样本推理的表现如何。为了解决这些问题，我们提出了Vivaldi，一个角色结构化的多智能体系统，用于解释多变量生理时间序列。由于监管限制禁止现场部署，我们在一个受控的临床试点中实例化Vivaldi，针对一小群高度合格的急诊医学专家进行测试。其评估揭示了一幅依赖于上下文的图景，这与普遍认为智能体推理普遍提高性能的假设形成对比。我们的实验表明，智能体管道显著受益于非思考和医学微调的模型，提高了专家评分的解释合理性和相关性，分别提高了+6.9和+9.7分。相反，对于思考模型，智能体协调经常降低解释质量，包括相关性下降14分，同时提高诊断精度（ESI F1 +3.6）。我们还发现，显式工具基础计算对于可编码的临床指标至关重要，而主观目标，如疼痛评分和住院时间，显示出有限或不一致的变化。专家评估进一步表明，临床效用的提升取决于可视化惯例，医学专业模型在效用和清晰度之间的权衡最为有利。这些发现表明，智能体AI的价值在于选择性地外部化计算和结构，而不是最大推理复杂性，并突出了具体的设计权衡和学到的经验，广泛适用于安全关键的医疗保健环境中的可解释AI。
英文摘要：
Continuous physiological monitoring is central to emergency care, yet deploying trustworthy AI is challenging. While LLMs can translate complex physiological signals into clinical narratives, it is unclear how agentic systems perform relative to zero-shot inference. To address these questions, we present Vivaldi, a role-structured multi-agent system that explains multivariate physiological time series. Due to regulatory constraints that preclude live deployment, we instantiate Vivaldi in a controlled, clinical pilot to a small, highly qualified cohort of emergency medicine experts, whose evaluations reveal a context-dependent picture that contrasts with prevailing assumptions that agentic reasoning uniformly improves performance. Our experiments show that agentic pipelines substantially benefit non-thinking and medically fine-tuned models, improving expert-rated explanation justification and relevance by +6.9 and +9.7 points, respectively. Contrarily, for thinking models, agentic orchestration often degrades explanation quality, including a 14-point drop in relevance, while improving diagnostic precision (ESI F1 +3.6). We also find that explicit tool-based computation is decisive for codifiable clinical metrics, whereas subjective targets, such as pain scores and length of stay, show limited or inconsistent changes. Expert evaluation further indicates that gains in clinical utility depend on visualization conventions, with medically specialized models achieving the most favorable trade-offs between utility and clarity. Together, these findings show that the value of agentic AI lies in the selective externalization of computation and structure rather than in maximal reasoning complexity, and highlight concrete design trade-offs and learned lessons, broadly applicable to explainable AI in safety-critical healthcare settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
