在百万级患者数据上实现秒级临床文本语义搜索，成本可控且符合医疗合规要求。
Health System Scale Semantic Search Across Unstructured Clinical Notes
- 采用指令微调的qwen3嵌入模型与优化分块策略，实现高效语义表示。
- 系统支持百万级患者1.68亿条病历检索，查询延迟低于1秒，月成本约4000美元。
- 临床应用中显著提升病历提取效率，基因病患者识别率从75%提升至98%。
语义搜索通过概念相似性而非关键词检索临床信息，具有显著优势。然而，在包含数亿条临床笔记的医院系统中部署语义搜索面临工程、成本和治理上的巨大挑战，限制了其广泛应用。本研究在一家大型儿童医院部署了语义搜索系统，索引了16600万条临床笔记（4.84亿个嵌入向量），覆盖168万名患者。系统采用指令微调的qwen3-embedding-0.6B嵌入模型，使用存储优化的索引方式，将全文元数据存于低延迟键值存储中，并在符合HIPAA的治理框架下运行。通过医生撰写的基准测试优化模型与分块策略，评估了系统全规模性能（成本、延迟、检索质量），并以病历抽象效率和ICD-10队列生成对比来验证临床实用性。结果显示，系统实现亚秒级查询延迟，月运营成本约4000美元；300词分块下qwen3嵌入模型在基准测试中准确率达94.6%。在三项病历抽象任务中，相比传统查阅方式，时间减少24%至89%，同时保持可评估的评分者一致性。在全院范围检索中，语义搜索识别出98%的分子确诊遗传病患者，而诊断编码最多仅能识别75%。结论：健康系统规模的语义搜索在技术和运营上均具备可行性，为交互式检索、队列构建及下游大模型临床应用提供了无需专业信息学背景的机构级基础设施。
原文摘要 · Abstract (English)
Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval of clinical information. However, deploying semantic search across health systems, comprising hundreds of millions of clinical notes, presents formidable engineering, cost, and governance challenges that have prevented institutional adoption. Methods: We deployed a semantic search system at a large children's hospital indexing 166 million clinical notes (484 million embedding vectors) from 1.68 million patients. The system uses instruction-tuned qwen3-embedding-0.6B embeddings, stores vectors with storage-optimized indexing, maintains full-text metadata in a low-latency key-value store, and operates within a HIPAA-compliant governance framework. We evaluated the system by optimizing the model and chunking strategy using a physician-authored benchmark, characterizing full-scale performance (cost, latency, retrieval quality), and assessing clinical utility via chart abstraction efficiency and comparison to ICD-10 cohort generation. Results: The system delivers sub-second query latency with monthly operational costs of ~USD 4,000. Qwen3 embeddings with 300-token chunk size achieved 94.6% accuracy on the benchmark. In clinical utility evaluation across three abstraction tasks, semantic search reduced time-to-completion by 24 to 89% versus chart review while maintaining inter-rater agreement where assessable. During system-wide retrieval, semantic search recovered 98% of patients with molecularly confirmed genetic diseases, versus at most 75% by diagnosis codes. Conclusion: Health-system-scale semantic search is technically and operationally feasible. The system provides institutional infrastructure supporting interactive search, cohort generation, and downstream LLM-powered clinical applications without requiring specialized informatics expertise.
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。