Polepalli Ramesh Balaji, Houston Thomas, Brandt Cynthia, Fang Hua, Yu Hong
Biomedical and Health Informatics, University of Wisconsin Milwaukee, Milwaukee, WI, USA.
Stud Health Technol Inform. 2013;192:714-8.
Allowing patients direct access to their electronic health record (EHR) notes has been shown to enhance medical understanding and may improve healthcare management and outcome. However, EHR notes contain medical terms, shortened forms, complex disease and medication names, and other domain specific jargon that make them difficult for patients to fathom. In this paper, we present a BioNLP system, NoteAid, that automatically recognizes medical concepts and links these concepts with consumer oriented, simplified definitions from external resources. We conducted a pilot evaluation for linking EHR notes through NoteAid to three external knowledge resources: MedlinePlus, the Unified Medical Language System (UMLS), and Wikipedia. Our results show that Wikipedia significantly improves EHR note readability. Preliminary analyses show that MedlinePlus and the UMLS need to improve both content readability and content coverage for consumer health information. A demonstration version of fully functional NoteAid is available at http://clinicalnotesaid.org.
允许患者直接访问其电子健康记录（EHR）笔记已被证明能增强医疗理解，并可能改善医疗保健管理及结果。然而，EHR笔记包含医学术语、缩写形式、复杂的疾病和药物名称以及其他特定领域的行话，这使得患者难以理解。在本文中，我们展示了一个生物自然语言处理系统NoteAid，它能自动识别医学概念，并将这些概念与来自外部资源的面向消费者的简化定义相链接。我们通过NoteAid对将EHR笔记链接到三个外部知识资源进行了试点评估：医学主题词表（MedlinePlus）、统一医学语言系统（UMLS）和维基百科。我们的结果表明，维基百科显著提高了EHR笔记的可读性。初步分析表明，医学主题词表和统一医学语言系统需要在消费者健康信息的内容可读性和内容覆盖方面加以改进。功能齐全的NoteAid演示版本可在http://clinicalnotesaid.org获取。
