PATHFinder Agent for Tailored Prenatal Care
PATHFinder Agent for Tailored Prenatal Care
PATHFinder：用于定制化产前护理的智能体
Abstract: 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).
摘要： 产前护理是一项重要的预防性服务，旨在改善孕妇的健康结果。美国妇产科医师学会（ACOG）最近发布了倡导定制化产前护理的指南，称为 PATH（定制化医疗计划）。
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.
我们提出了 PATHFinder Agent（适宜定制化医疗规划师），这是一个端到端的对话式智能体系统。它通过结构化对话收集患者的健康和社会背景信息，根据 PATH 指南制定个性化的产前护理计划，并提供来自 Michigan 211 的社区资源。
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.
该系统具有涵盖患者接诊、动态交互、计划综合和临床监督四个阶段的工作流程。我们在五个临床维度上，使用专家制定的评估标准对前沿大语言模型（LLMs）进行了评估，结果发现 GPT-5.2 获得了最高的平均分（77.6%），同时识别出了产前检查建议中的关键差距。
We discuss future validation through human participant studies and randomized controlled trials.
我们讨论了未来通过人类参与者研究和随机对照试验进行验证的可能性。
Paper Details:
- Authors: Vaibhav Balloli, Carissa Samuel, Samia Abdelnabi, Alex Peahl, Elizabeth Bondi-Kelly
- Date: 9 Jun 2026
- Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY); Emerging Technologies (cs.ET)
论文详情：
- 作者： Vaibhav Balloli, Carissa Samuel, Samia Abdelnabi, Alex Peahl, Elizabeth Bondi-Kelly
- 日期： 2026年6月9日
- 学科： 人工智能 (cs.AI)；计算与语言 (cs.CL)；计算机与社会 (cs.CY)；新兴技术 (cs.ET)