EMSDialog: 通过多LLM代理从电子患者护理报告生成合成多人紧急医疗服务体系对话
EMSDialog: Synthetic Multi-person Emergency Medical Service Dialogue Generation from Electronic Patient Care Reports via Multi-LLM Agents
AI总结：
本文提出基于ePCR的多代理生成流程，生成4414个合成多说话者EMS对话数据集，提升EMS对话诊断预测的准确性、及时性和稳定性。
摘要：
对话诊断预测需要模型跟踪流式临床对话中的演变证据并决定何时提交诊断。现有医疗对话语料库大多为二元关系或缺乏多方工作流和注释。我们引入基于ePCR的、基于话题流的多代理生成流程，该流程通过规则基础的事实和话题流检查迭代规划、生成和自我优化对话。该流程生成EMSDialog，一个基于真实世界ePCR数据集的4414个合成多说话者EMS对话数据集，标注有43种诊断、说话者角色和回合级话题。人类和LLM评估证实EMSDialog的高质量和现实性，使用句级和对话级指标。结果表明，使用EMSDialog增强的训练提高了EMS对话诊断预测的准确性、及时性和稳定性。我们的数据集和代码在https://uva-dsa.github.io/EMSDialog公开可用。
英文摘要：
Conversational diagnosis prediction requires models to track evolving evidence in streaming clinical conversations and decide when to commit to a diagnosis. Existing medical dialogue corpora are largely dyadic or lack the multi-party workflow and annotations needed for this setting. We introduce an ePCR-grounded, topic-flow-based multi-agent generation pipeline that iteratively plans, generates, and self-refines dialogues with rule-based factual and topic flow checks. The pipeline yields EMSDialog, a dataset of 4,414 synthetic multi-speaker EMS conversations based on a real-world ePCR dataset, annotated with 43 diagnoses, speaker roles, and turn-level topics. Human and LLM evaluations confirm high quality and realism of EMSDialog using both utterance- and conversation-level metrics. Results show that EMSDialog-augmented training improves accuracy, timeliness, and stability of EMS conversational diagnosis prediction. Our datasets and code are publicly available at https://uva-dsa.github.io/EMSDialog
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。
