用BERT模型提升心脏病文本中多语言疾病与药物识别效果。
Multilingual Clinical NER for Diseases and Medications Recognition in Cardiology Texts using BERT Embeddings
- 基于多语言BERT模型，针对英文、西班牙语和意大利语病历文本进行实体识别。
- 在西班牙语疾病识别上达77.88%的F1分数，优于平均值69.61%。
- 为低资源语言临床文本分析提供有效解决方案，适合医疗NLP研究者参考。
电子健康记录（EHR）数据量激增，亟需从非结构化临床文本中提取生物医学知识，以支持数据驱动的临床系统，如患者诊断、疾病进展监测、治疗效果评估及未来临床事件预测。尽管上下文语言模型在英语语料上的命名实体识别（NER）任务中表现优异，但针对低资源语言的临床文本研究仍匮乏。为此，本研究参与BioASQ MultiCardioNER共享任务，旨在构建多种深度上下文嵌入模型，提升心脏病领域临床文本中的疾病与药物识别性能。我们评估了多种基于通用领域文本训练的单语和多语言BERT模型，在英文、西班牙语和意大利语的病例报告中提取疾病与药物实体。结果显示：西班牙语疾病识别（SDR）F1得分为77.88%，西班牙语药物识别（SMR）为92.09%，英文药物识别（EMR）为91.74%，意大利语药物识别（IMR）为88.9%。所有结果均超过测试排行榜的均值与中位数（分别为SDR: 69.61%/75.66%，SMR: 81.22%/90.18%，EMR: 89.2%/88.96%，IMR: 82.8%/87.76%）。
原文摘要 · Abstract (English)
The rapidly increasing volume of electronic health record (EHR) data underscores a pressing need to unlock biomedical knowledge from unstructured clinical texts to support advancements in data-driven clinical systems, including patient diagnosis, disease progression monitoring, treatment effects assessment, prediction of future clinical events, etc. While contextualized language models have demonstrated impressive performance improvements for named entity recognition (NER) systems in English corpora, there remains a scarcity of research focused on clinical texts in low-resource languages. To bridge this gap, our study aims to develop multiple deep contextual embedding models to enhance clinical NER in the cardiology domain, as part of the BioASQ MultiCardioNER shared task. We explore the effectiveness of different monolingual and multilingual BERT-based models, trained on general domain text, for extracting disease and medication mentions from clinical case reports written in English, Spanish, and Italian. We achieved an F1-score of 77.88% on Spanish Diseases Recognition (SDR), 92.09% on Spanish Medications Recognition (SMR), 91.74% on English Medications Recognition (EMR), and 88.9% on Italian Medications Recognition (IMR). These results outperform the mean and median F1 scores in the test leaderboard across all subtasks, with the mean/median values being: 69.61%/75.66% for SDR, 81.22%/90.18% for SMR, 89.2%/88.96% for EMR, and 82.8%/87.76% for IMR.
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。