用于定制产前护理的PATHFinder智能体
PATHFinder Agent for Tailored Prenatal Care
- University of Michigan（密歇根大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对产前护理，提出PATHFinder智能体这一端到端对话系统，通过结构化对话收集信息并制定个性化计划，展示社区资源。经评估前沿大语言模型，GPT-5.2平均分最高，还发现检测建议差距，将开展人体研究和随机对照试验验证。
AI中文摘要：
产前护理是一项旨在改善孕妇分娩结果的重要预防性服务。美国妇产科医师学会（ACOG）最近推出了倡导定制产前护理的指南，即PATH（定制医疗保健计划）。我们提出了PATHFinder智能体（适当定制医疗保健计划器），这是一个端到端的对话式智能系统，通过结构化对话收集患者健康和社会背景信息，精心制定符合PATH指南的个性化产前护理计划，并展示来自密歇根211的社区资源。该系统具有一个四阶段工作流程，涵盖患者接待、动态交互、计划合成和临床医生监督。我们在五个临床维度上根据专家策划的评分标准对前沿大语言模型（LLMs）进行评估，发现GPT-5.2获得了最高平均分（77.6%），同时也发现了产前检测建议中的关键差距。我们讨论了未来通过人体受试者研究和随机对照试验进行验证的问题。
英文摘要：
Prenatal care is an important preventive service designed to improve outcomes for pregnant individuals. The American College of Obstetricians and Gynecologists (ACOG) recently introduced guidelines advocating tailored prenatal care, called PATH (Plan for Tailored Healthcare). We present PATHFinder Agent(Planner for Appropriate Tailored Healthcare), an end-to-end conversational agentic system that gathers patient health and social context through structured dialogue, curates individualized prenatal care plans aligned with PATH guidelines, and surfaces community resources from Michigan 211. The system features a four-stage workflow spanning patient intake, dynamic interaction, plan synthesis, and clinician oversight. We evaluate frontier large language models (LLMs) on expert-curated rubrics across five clinical dimensions, finding that GPT-5.2 achieves the highest average score (77.6\%) while identifying key gaps in antenatal testing recommendations. We discuss future validation through human participant studies and randomized controlled trials.
