CLAIRE：一种面向医疗行政表单填写的模式引导混合工作流
CLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion
浏览论文内容
中文总结 AI 辅助
CLAIRE提出一种模式引导的混合工作流，分离字段发现、映射与验证，在合成基准上实现100%成功率，显著提升医疗表单填写的准确性与效率。
中文摘要 AI 辅助
医疗行政人员将电子健康记录、转诊单、索赔系统、提供者名册和工作队列中的结构化信息转移到动态表单中。我们开发并评估了CLAIRE（临床语言与智能体推理及录入），一种混合工作流，它将字段状态发现、源到字段映射、确定性验证、受限修正、升级和审计追踪分离。我们测试了五个合成医疗行政模式、1000条源记录、四种界面变体、两个数据质量套件和六个比较器，产生了24000个基准情节。一项独立的严格输出审计评估了来自Qwen2.5-1.5B和Qwen2.5-7B的直接映射，以及一项覆盖6000个情节的基于追踪的操作模拟。在所评估的合成基准条件下，完整的CLAIRE在两个套件中均实现了1.000的情节成功率、字段准确率、必填字段完成率和依赖完成率；移除验证将压力套件的成功率降至0.500。在模拟中，100.0%的干净和验证压力情节达到了可员工审核的草稿，而升级挑战情节的这一比例为68.6%，不支持的情况被阻止。基于场景的节省为每例149.7-165.5秒，未观察到员工时间。研究结果支持基于模式、验证优先的医疗行政自动化，其中语言模型组件辅助映射，但不授权不支持或具有重大后果的操作。
英文摘要
Healthcare administrative staff transfer structured information from electronic health records, referrals, claims systems, provider rosters, and work queues into dynamic forms. We developed and evaluated CLAIRE (Clinical Language and Agentic Intelligence for Reasoning and Entry), a hybrid workflow that separates field-state discovery, source-to-field mapping, deterministic validation, bounded correction, escalation, and audit tracing. We tested five synthetic healthcare administrative schemas, 1,000 source records, four interface variants, two data-quality suites, and six comparators, yielding 24,000 benchmark episodes. A separate strict-output audit evaluated direct mappings from Qwen2.5-1.5B and Qwen2.5-7B, and a trace-derived operational simulation covered 6,000 episodes. Under the evaluated synthetic benchmark conditions, full CLAIRE achieved 1.000 episode success, field accuracy, required-field completion, and dependency completion in both suites; removing validation reduced stress-suite success to 0.500. In the simulation, 100.0% of clean and validation-stress episodes reached a staff-reviewable draft, compared with 68.6% of escalation challenge episodes, unsupported cases were blocked. Scenario-based savings were 149.7-165.5 seconds per case, not observed staff times. The findings support schema-grounded, validation-first healthcare administrative automation in which language-model components assist mapping but do not authorize unsupported or consequential actions.
