用大模型生成符合FHIR标准的患者数字孪生，提升医疗数据可用性。
Schema-Grounded LLM Extraction for FHIR Patient Digital Twins
- 基于FHIR结构约束和医学术语检索增强提示，生成合规数据。
- 在MIMIC-IV和n2c2数据集上，生成数据有效性显著优于基线。
- 适合医疗信息提取、电子病历标准化及临床决策支持研究者。
我们重新审视从非结构化电子健康记录构建可互操作患者数字孪生的问题，认为该任务不应视为多个抽取模块的级联，而应作为生成有效FHIR Bundle的受约束生成过程。提出SG-LLM，一种基于模式的大语言模型抽取器：(i) 使用SapBERT索引检索候选SNOMED-CT、RxNorm和LOINC代码增强提示；(ii) 在直接从FHIR R4 StructureDefinitions导出的JSON Schema约束下解码；(iii) 引入验证器闭环修复阶段，将诊断信息反馈为结构化错误消息。我们主张以数字孪生的实际临床效用而非仅跨度级F1作为评估目标，并通过临床效用实验测量基于SG-LLM生成的FHIR包与专家标注数据训练分类器在30天再入院预测的AUROC差距。在MIMIC-IV和n2c2 2018 Track 2基准上，SG-LLM达到或超越强联合抽取和原始大模型基线，且生成的包有效性显著更高。消融实验分离了检索、模式约束和修复环的贡献。所有代码、提示和模式均已公开。
原文摘要 · Abstract (English)
We revisit the problem of constructing interoperable patient digital twins from unstructured electronic health records (EHRs) and argue that the task is better cast not as a cascade of extraction modules but as constrained generation of a valid FHIR bundle. We introduce SG-LLM, a schema-grounded LLM extractor that (i) augments the prompt with candidate SNOMED-CT, RxNorm, and LOINC codes retrieved through a SapBERT index, (ii) decodes under a JSON Schema derived directly from FHIR R4 StructureDefinitions, and (iii) closes a validator-in-the-loop repair stage whose diagnostics are fed back as structured error messages. We argue that the twin's usefulness, not only span-level F1, is the right object of evaluation, and operationalize this with a clinical-utility experiment that measures the gap in 30-day readmission AUROC between classifiers trained on SG-LLM-generated FHIR bundles versus expert-curated ones. On MIMIC-IV and n2c2 2018 Track 2 benchmarks, SG-LLM matches or exceeds strong joint-extraction and vanilla-LLM baselines while producing substantially more valid bundles. Ablations isolate the contributions of retrieval, schema constraint, and the repair loop. All code, prompts, and schemas are released.
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。