发表机构
MBZUAI; University of Oxford; Imperial College London（穆罕默德·本·扎耶德人工智能大学; 牛津大学; 伦敦帝国学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
CaseWeaver提出基于时间线锚定潜在临床病例图的多智能体框架，生成具有一致背景和连贯轨迹的多模态虚拟临床病例，在临床可推断性和多样性上优于基线。
AI 中文摘要
临床诊断依赖于在整个病程中从同一患者收集的一致多模态数据，然而由于采集成本、模态缺失、系统碎片化以及纵向随访等因素，此类数据难以大规模获取。现有的合成数据方法主要聚焦于单一模态或报告级别的视觉-语言双模态生成。目前鲜有研究在完整临床病例层面构建具有一致患者背景、连贯疾病轨迹以及相互关联的模态特异性证据的合成数据。我们提出了CaseWeaver，这是一个围绕时间线锚定的潜在临床病例图（LCCG）构建的多智能体框架。LCCG在共享的患者级表示中组织患者背景、潜在疾病状态、临床事件和预期观察结果。模态智能体利用受限的观察子图和临床协议生成包括临床记录、实验室结果、生理信号和医学图像在内的证据。我们使用校准的AgentClinic协议评估临床可推断性，并使用虚拟病例多样性（VCD）评分评估病例多样性。CaseWeaver在两项指标上均优于通用模型和智能体工作流基线，生成了更多样且更连贯的多模态虚拟临床病例。
英文摘要
Clinical diagnosis relies on consistent multimodal data collected from the same patient throughout the disease course, yet such data are difficult to acquire at scale because of collection costs, missing modalities, fragmented systems, and longitudinal follow-ups. Existing synthetic-data approaches largely focus on individual modalities or vision-language dual modalities at report-level generation. Little work has been done to construct synthetic data with consistent patient backgrounds, coherent disease trajectories, and interrelated modality-specific evidence at a complete clinical case level. We introduce CaseWeaver, a multi-agent framework built around a timeline-anchored Latent Clinical Case Graph (LCCG). The LCCG organizes patient context, latent disease states, clinical events, and expected observations in a shared patient-level representation. Modality-agents use scoped observation subgraphs and clinical protocols to generate evidence including clinical records, laboratory results, physiological signals, and medical images. We evaluate clinical inferability using a calibrated AgentClinic protocol and case diversity using Virtual Case Diversity (VCD) score. CaseWeaver outperformed general-model and agentic-workflow baselines on both metrics, producing more diverse and coherent multimodal virtual clinical cases.
