MedTRACE：面向证据支撑决策的工具增强多模态临床推理智能体
MedTRACE: Tool-Augmented Multimodal Clinical Reasoning Agents for Evidence-Grounded Decision-Making
- Vanderbilt University（范德堡大学）
- Wichita State University（威奇托州立大学）
- University of Florida（佛罗里达大学）
- Wyze Inc.（Wyze公司）
- Northeastern University（东北大学）
- City University of New York（纽约城市大学）
- Southwest University（西南大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MedTRACE提出一种工具增强的多模态临床推理智能体，通过迭代假设形成、工具调用与证据验证，在多个基准上显著提升诊断准确率与可靠性。
AI中文摘要：
多模态临床决策需要对来自电子健康记录、医学图像和生理信号等异构证据进行可靠推理。现有模型通常将这些输入直接映射到诊断结果，而未明确评估证据充分性、工具使用需求或诊断不确定性。本文提出MedTRACE，一种用于证据支撑决策的工具增强多模态临床推理智能体。MedTRACE使用模态特定编码器构建统一的患者状态表示，并执行假设形成、工具感知 deliberation 和证据验证的迭代循环。它动态调用视觉定位、证据检索和结构化解析工具，以定位与诊断相关的区域、检索临床知识和相似病例，并提取结构化发现。获取的证据进入证据记忆，其中一致性验证器确认或修正当前假设。MedTRACE输出诊断结果及支持证据、可审计的推理轨迹和校准后的置信度。在多个多模态临床诊断基准上的实验表明，MedTRACE相比最强基线将诊断准确率提高5.4%，AUROC提高4.7个百分点。它还将证据选择F1提高8.2个百分点，视觉定位IoU提高6.5个百分点，将期望校准误差降低31.6%，并将无证据支持的诊断错误减少27.8%。这些结果表明，主动的证据获取和验证提高了多模态临床决策的准确性、可解释性和可靠性。
英文摘要：
Multimodal clinical decision-making requires reliable reasoning over heterogeneous evidence from electronic health records, medical images, and physiological signals. Existing models typically map these inputs directly to diagnoses without explicitly assessing evidence sufficiency, tool-use requirements, or diagnostic uncertainty. This paper presents MedTRACE, a tool-augmented multimodal clinical reasoning agent for evidence-grounded decision-making. MedTRACE uses modality-specific encoders to construct a unified patient-state representation and performs an iterative loop of hypothesis formation, toolaware deliberation, and evidence verification. It dynamically invokes visual grounding, evidence retrieval, and structured parsing tools to locate diagnosis-relevant regions, retrieve clinical knowledge and similar cases, and extract structured findings. The acquired evidence enters an evidence memory, where a consistency verifier confirms or revises the current hypothesis. MedTRACE outputs a diagnosis together with supporting evidence, an auditable reasoning trace, and calibrated confidence. Experiments on multiple multimodal clinical diagnosis benchmarks show that MedTRACE improves diagnostic accuracy by 5.4% and AUROC by 4.7 percentage points over the strongest baseline. It also improves evidenceselection F1 by 8.2 percentage points and visual-grounding IoU by 6.5 percentage points, reduces expected calibration error by 31.6%, and decreases unsupported diagnostic errors by 27.8%. These results demonstrate that active evidence acquisition and verification improve the accuracy, interpretability, and reliability of multimodal clinical decisionmaking.
