Using NLP to Extract Clinically Important Recommendations from Radiology Reports

使用 NLP 从放射学报告中提取临床上重要的建议

• 批准号: 8635902
• 负责人: Meliha Yetisgen
• 金额: $ 25.73万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-03-01 至 2016-02-29
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8635902
• 关键词: Academic Medical Centers; Address; Adopted; Characteristics; Clinical; Communication; Communities; Computerized Medical Record; Data Set; Dependency; Diagnostic; Diagnostic radiologic examination; Ensure; Funding; Future; Goals; Gold; Growth; Guidelines; Hand; Health; Image; Imaging technology; Incidental Findings; Institution; Intervention; Investigation; Knowledge; Life; Lung nodule; Magnetic Resonance Imaging; Malignant Neoplasms; Measures; Medical center; Methods; Modality; Natural Language Processing; Outcome; Output; Patient Care; Patients; Persons; Process; Provider; Quality of Care; Radiology Specialty; Recommendation; Reporting; Research; Research Infrastructure; Research Project Grants; Risk; Safety; Semantics; Shapes; Societies; Specific qualifier value; Speech; System; Telephone; Test Result; Testing; Text; Time; Training; Trauma; Ultrasonography; Unified Medical Language System; Washington; Writing; X-Ray Computed Tomography; biomedical informatics; cancer care; care delivery; design; falls; follow-up; health care delivery; imaging modality; improved; innovation; novel; open source; phrases; public health relevance; radiologist; screening; syntax; tool

Abstract Communication of clinically important follow-up recommendations when abnormalities are identified on imaging studies is prone to error. The absence of an automated system to identify and track radiology follow-up recommendations is an important barrier to ensuring timely follow-up of patients, especially for non-acute but potentially life threatening and unexpected findings. The primary goal of this proposal is to develop a Natural Language Processing (NLP) system to extract clinically important recommendation information from free-text radiology reports. Each radiology report will be preprocessed at the structural, syntactic, and semantic level to generate features that will be used to extract the boundaries of sentences that include recommendation information as well as the details of reason for recommendation, requested imaging test, and recommendation time frame. We will use a large corpus of free-text radiology reports represented by a mixture of modalities (e.g., radiography, computed tomography, ultrasound, and magnetic resonance imaging (MRI)) from three different institutions. Using this dataset we will perform the following specific aims: Aim 1. Create a multi- institutional radiology report corpus annotated for clinically important recommendation information; Aim 2. Develop a novel NLP system to extract clinically important recommendations in radiology reports. The proposed research is innovative because it will generate a new text processing approach that can be used to flag reports visually and electronically so that separate workflow processes can be initiated to reduce the chance that necessary investigations or interventions suggested in the report are missed by clinicians. The proposed set of tools will be disseminated to the biomedical informatics community as open source tools.

抽象的 当发现异常时传达临床上重要的后续建议 影像学研究很容易出错。缺乏识别和跟踪放射学随访的自动化系统 建议是确保患者及时随访的重要障碍，特别是对于非急性但 可能危及生命和意外的发现。该提案的主要目标是开发一种自然的 语言处理 (NLP) 系统可从自由文本中提取临床上重要的推荐信息 放射学报告。每份放射学报告都将在结构、句法和语义层面进行预处理，以 生成将用于提取包含推荐的句子边界的特征 信息以及推荐理由、要求的影像检查和推荐的详细信息 大体时间。我们将使用由混合模式表示的大量自由文本放射学报告语料库 （例如放射线照相、计算机断层扫描、超声波和磁共振成像 (MRI)） 不同的机构。使用此数据集，我们将实现以下具体目标： 目标 1. 创建一个多 机构放射学报告语料库，注释有临床重要的推荐信息；目标2。 开发一种新颖的 NLP 系统，以提取放射学报告中的临床重要建议。这 拟议的研究具有创新性，因为它将产生一种新的文本处理方法，可用于标记 以可视化和电子方式报告，以便可以启动单独的工作流程以减少机会 临床医生错过了报告中建议的必要调查或干预措施。拟议的 一套工具将作为开源工具传播到生物医学信息学界。