用迁移学习为医疗问卷项自动匹配标准代码，提升电子审批效率。
Transfer Learning for FHIR Questionnaire Terminology Binding
- 将术语绑定转为文本检索问题，用预训练模型匹配医学代码。
- 生物医学语料冻结模型在18.5%准确率上表现最佳，微调后5项命中率达38.9%。
- 数据增广反而降低性能，适合医疗文本匹配的场景研究者必看。
电子先审流程需为FHIR问卷项绑定LOINC代码，但大多数HL7 Da Vinci CDS-Library中的项目缺乏此类绑定。本文将其视为检索任务：给定问卷项文本，在97,314个活跃代码中寻找正确对应代码。在涵盖自然提问、中等描述和简洁表达三种查询风格的54项评估集上，对比了六种方法（TF-IDF、冻结MiniLM、BioBERT、BioLORD、对比微调MiniLM、TF-IDF+GPT重排序器）。无单一方法在所有指标上胜出。未接触任务数据的BioLORD（基于生物医学本体定义预训练的冻结编码器）在顶排准确率上最优（R@1 = 0.185，MRR = 0.246）；而对原始LHC-Forms配对进行对比微调，获得R@5 = 0.389、R@10 = 0.426。分布偏移消融实验表明，添加GPT生成的改写句虽增加数据量，却使R@5从0.389降至0.296，因此增广联合训练在所有指标上均劣于仅用原始数据训练，仅在R@1上略优。性能在5000个训练样本时达峰值。对BioLORD R@1失败案例的分析显示，错误主要源于特定性错误与文本歧义，合计占59%。
原文摘要 · Abstract (English)
Electronic prior authorization workflows require FHIR Questionnaire items to carry LOINC codes, yet most items in the HL7 Da Vinci CDS-Library lack these bindings. We treat this as a retrieval problem: given a Questionnaire item's text, find the correct LOINC code in a pool of 97,314 active codes. We compare six methods (TF-IDF, frozen MiniLM, BioBERT, BioLORD, contrastively fine-tuned MiniLM, and a TF-IDF+GPT reranker) on a 54-item evaluation set spanning three query styles (natural question, medium, and terse). No single method wins on every metric. BioLORD, a frozen encoder pre-trained on biomedical ontology definitions, has the best top-rank accuracy (R@1 = 0.185, MRR = 0.246) despite seeing no task-specific data, while a contrastive fine-tune on raw LHC-Forms pairs takes R@5 (0.389) and R@10 (0.426). A distribution-shift ablation shows why the fine-tune in our main table is not the strongest one: adding GPT-generated paraphrases to the raw pairs drops R@5 from 0.389 to 0.296, so the augmented union underperforms raw-only training on every metric except R@1. Performance peaks at 5k training pairs. Error analysis on BioLORD's R@1 failures shows that wrong-specificity and ambiguous-text cases together account for 59% of errors.
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。