Mining FDA drug labels for medical conditions
Mining FDA drug labels for medical conditions
复制标题
DOI：
10.1186/1472-6947-13-53
复制
发表时间：
2013-04-24
影响因子：
3.5
通讯作者：
Solti, Imre
中科院分区：
文献类型：
--
作者：
Li, Qi;Deleger, Louise;Solti, Imre
背景：辛辛那提儿童医院医学中心(CCHMC)建立了最初的自然语言处理(NLP)组件，将具有相应医疗条件(适应症、禁忌症、过量用药和不良反应)的药物提取为与药物相关的信息([(1)药物名称]-[(2)医疗条件]-[(3)LOINC部分标题])的三元组，用于智能数据库系统，以提高患者的安全和医疗质量。以美国食品药品监督管理局(FDA)的药品标签为例，论证了建立三元组作为智能数据库系统任务的可行性。方法：讨论了一个混合式NLP系统，称为AutoMCExtractor，用于从FDA发布的药品标签中收集医疗状况(包括疾病/障碍和体征/症状)。共有6,611种医疗条件被用于系统评估，其中包括手动注释的黄金标准。预处理步骤从XML文件中提取纯文本，并检测出八个相关的LOINC部分(如不良反应、警告和注意事项)用于医疗条件提取。然后使用条件随机场(CRF)分类器对表征、语言和语义特征进行训练，用于医疗条件提取。最后，基于字典的后处理修正了CRF步骤中的边界检测误差。结果：对于跨度级精确匹配，其准确率、召回率和F-MEASURE分别为0.90、0.81和0.85；对于令牌级评估，准确率、召回率和F-MEASURE分别为0.92、0.73和0.82。结论：(1)可以高性能地从FDA药品标签中提取医疗条件；(2)开发一个智能数据库系统框架是可行的。
Background: Cincinnati Children's Hospital Medical Center (CCHMC) has built the initial Natural Language Processing (NLP) component to extract medications with their corresponding medical conditions (Indications, Contraindications, Overdosage, and Adverse Reactions) as triples of medication-related information ([(1) drug name]-[(2) medical condition]-[(3) LOINC section header]) for an intelligent database system, in order to improve patient safety and the quality of health care. The Food and Drug Administration's (FDA) drug labels are used to demonstrate the feasibility of building the triples as an intelligent database system task.Methods: This paper discusses a hybrid NLP system, called AutoMCExtractor, to collect medical conditions (including disease/disorder and sign/symptom) from drug labels published by the FDA. Altogether, 6,611 medical conditions in a manually-annotated gold standard were used for the system evaluation. The pre-processing step extracted the plain text from XML file and detected eight related LOINC sections (e.g. Adverse Reactions, Warnings and Precautions) for medical condition extraction. Conditional Random Fields (CRF) classifiers, trained on token, linguistic, and semantic features, were then used for medical condition extraction. Lastly, dictionary-based post-processing corrected boundary-detection errors of the CRF step. We evaluated the AutoMCExtractor on manually-annotated FDA drug labels and report the results on both token and span levels.Results: Precision, recall, and F-measure were 0.90, 0.81, and 0.85, respectively, for the span level exact match; for the token-level evaluation, precision, recall, and F-measure were 0.92, 0.73, and 0.82, respectively.Conclusions: The results demonstrate that (1) medical conditions can be extracted from FDA drug labels with high performance; and (2) it is feasible to develop a framework for an intelligent database system.