用提示学习提升希伯来语肠炎报告的细粒度结构化数据提取效果。
Hierarchical Section Matching Prediction (HSMP) BERT for Fine-Grained Extraction of Structured Data from Hebrew Free-Text Radiology Reports in Crohn's Disease
- 基于提示的分层匹配预测模型，提升多器官病理识别能力。
- 在24种组合上平均F1达0.83，显著优于基线模型。
- 适合低资源语言医学文本分析，可支撑流行病学研究。
从放射科报告中提取结构化临床信息极具挑战，尤其在低资源语言中更为突出。本研究针对克罗恩病多器官表现稀疏的问题，开发了分层结构匹配预测BERT（HSMP-BERT），用于希伯来语放射科文本的结构化信息抽取。基于以色列医疗机构2010-2023年的9,683份克罗恩病患者影像报告，其中512份经放射科医生标注，涵盖六个胃肠道器官和15种病理类型，每例生成90个结构化标签。采用多标签分层划分（66%训练+验证；33%测试），保持标签分布。评估指标包括准确率、F1、Cohen's κ、AUC、PPV、NPV和召回率。在超过15个正例的24种器官-病灶组合上，HSMP-BERT平均F1为0.83±0.08，κ值为0.65±0.17，显著优于SMP零样本基线（F1 0.49±0.07，κ 0.06±0.07）和标准微调（F1 0.30±0.27，κ 0.27±0.34；配对t检验p < 10⁻⁷）。分层推理使推理时间减少5.1倍。模型应用于全部报告后，揭示了回肠壁增厚、狭窄与狭窄前扩张之间的关联，并发现炎症表现存在年龄与性别差异。该方法为放射科结构化数据提取提供可扩展方案，支持克罗恩病群体水平分析，展现人工智能在低资源环境中的潜力。
原文摘要 · Abstract (English)
Extracting structured clinical information from radiology reports is challenging, especially in low-resource languages. This is pronounced in Crohn's disease, with sparsely represented multi-organ findings. We developed Hierarchical Structured Matching Prediction BERT (HSMP-BERT), a prompt-based model for extraction from Hebrew radiology text. In an administrative database study, we analyzed 9,683 reports from Crohn's patients imaged 2010-2023 across Israeli providers. A subset of 512 reports was radiologist-annotated for findings across six gastrointestinal organs and 15 pathologies, yielding 90 structured labels per subject. Multilabel-stratified split (66% train+validation; 33% test), preserving label prevalence. Performance was evaluated with accuracy, F1, Cohen's $κ$, AUC, PPV, NPV, and recall. On 24 organ-finding combinations with $>$15 positives, HSMP-BERT achieved mean F1 0.83$\pm$0.08 and $κ$ 0.65$\pm$0.17, outperforming the SMP zero-shot baseline (F1 0.49$\pm$0.07, $κ$ 0.06$\pm$0.07) and standard fine-tuning (F1 0.30$\pm$0.27, $κ$ 0.27$\pm$0.34; paired t-test $p < 10^{-7}$). Hierarchical inference cuts runtime 5.1$\times$ vs. traditional inference. Applied to all reports, it revealed associations among ileal wall thickening, stenosis, and pre-stenotic dilatation, plus age- and sex-specific trends in inflammatory findings. HSMP-BERT offers a scalable solution for structured extraction in radiology, enabling population-level analysis of Crohn's disease and demonstrating AI's potential in low-resource settings.
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。