用对话智能生成个性化产前护理方案，匹配最新临床指南。
PATHFinder Agent for Tailored Prenatal Care
- 通过四阶段对话系统收集健康与社会信息，生成定制化产检计划。
- GPT-5.2在五大临床维度平均得分77.6%，但仍有产前检测建议遗漏。
- 适合产科医生、健康管理平台及需要精准产前服务的用户。
产前护理是改善孕产妇结局的重要预防性服务。美国妇产科医师学会（ACOG）最近提出个性化产前护理指南，称为PATH（Tailored Healthcare计划）。本文提出PATHFinder Agent（Appropriate Tailored Healthcare规划者），一个端到端的对话式智能体系统，通过结构化对话获取患者健康与社会背景信息，依据PATH指南生成个性化产前护理计划，并整合密歇根州211社区资源。系统包含四阶段流程：患者初筛、动态交互、计划合成与临床监督。我们在专家制定的评分标准下评估前沿大语言模型（LLMs），发现GPT-5.2在五个临床维度上取得最高平均分77.6%，但存在产前检测推荐缺失问题。未来需通过人类参与者研究和随机对照试验进一步验证。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。