大模型能写出临床合格的医保审批信，但缺关键行政细节。
AI-Generated Prior Authorization Letters: Strong Clinical Content, Weak Administrative Scaffolding
- 用三款商用大模型在45个医学场景测试审批信生成能力。
- 临床内容准确，但普遍遗漏编码、时长请求等行政要素。
- 适合关注AI医疗流程落地的医生与系统设计者参考。
医保前置审批是美国医疗体系中最繁重的行政流程之一，每年耗费数十亿美元和数千小时医生时间。尽管大语言模型在临床文本任务中表现优异，但其生成可提交审批信的能力尚未得到充分评估，现有研究仅限于单案例演示，缺乏多场景结构化评测。我们评估了三种商用大模型（GPT-4o、Claude Sonnet 4.5、Gemini 2.5 Pro），覆盖风湿科、精神科、肿瘤科、心血管科和骨科共45个由医生验证的合成场景。所有模型生成的信件临床内容均表现良好：诊断准确、医疗必要性论证合理、阶梯治疗记录完整。然而，对真实行政要求的二次分析显示，存在持续性缺失：缺少收费代码、未提出授权时长、随访计划不充分。这些发现重新定义了问题：临床部署的挑战并非模型能否写好临床内容，而是围绕模型构建的系统能否提供支付方流程所需的行政精确性。
原文摘要 · Abstract (English)
Prior authorization remains one of the most burdensome administrative processes in U.S. healthcare, consuming billions of dollars and thousands of physician hours each year. While large language models have shown promise across clinical text tasks, their ability to produce submission-ready prior authorization letters has received only limited attention, with existing work confined to single-case demonstrations rather than structured multi-scenario evaluation. We assessed three commercially available LLMs (GPT-4o, Claude Sonnet 4.5, and Gemini 2.5 Pro) across 45 physician-validated synthetic scenarios spanning rheumatology, psychiatry, oncology, cardiology, and orthopedics. All three models generated letters with strong clinical content: accurate diagnoses, well-structured medical necessity arguments, and thorough step therapy documentation. However, a secondary analysis of real-world administrative requirements revealed consistent gaps that clinical scoring alone did not capture, including absent billing codes, missing authorization duration requests, and inadequate follow-up plans. These findings reframe the question: the challenge for clinical deployment is not whether LLMs can write clinically adequate letters, but whether the systems built around them can supply the administrative precision that payer workflows require.
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。