Increasing Clinical Trial Enrollment: A Semi-Automated Patient Centered Approach

描述(由申请人提供)： 这项研究的长期目标是通过基于自然语言处理(NLP)的半自动、交互式和以患者为中心的信息学应用程序来增加美国患者的临床试验登记人数。研究设计为前瞻性观察性研究。范围仅限于癌症患者。这个项目有三个具体目标。第一个目标是确定电子病历(EMR)临床笔记和临床试验公告的免费文本之间重叠的概念。PI将使用这些概念来开发映射框架，将试验公告文本中的概念与医疗记录中的临床笔记中的概念联系起来。当他得到映射帧时，他将为应用程序构建NLP模块。在软件开发工作中，他将利用尽可能多的公开可用的软件组件。他将用UIMA、GATE、MetaMap、Stanford Parser、NegEx算法和其他软件进行实验。PI将围绕国家医学图书馆的统一医学语言系统知识库开发该工具。他将使用Java进行编程。第二个目标是创建一种算法，如果记录中没有或无法访问信息，则自动生成问题，以直接从患者那里请求信息。第三个目标是评估该应用程序的体外和实验室性能。出于绩效评估的目的，PI将招聘癌症护理专家，为研究患者生成合格临床试验的黄金标准清单。他将在授权期结束时公开发布开发的代码。这个K99/R00项目将为未来的R01拨款申请奠定基础。PI致力于成为临床研究信息学领域的教师，拥有生物医学NLP的专业知识。K99/R00拨款的支持将使他能够在计算语言学方面获得大量的正式培训，同时为临床研究信息学领域的知识体系做出贡献。五年的拨款支持将确保他的努力取得成功。这项拟议的工作意义重大，因为令人沮丧的临床试验应收率(全国范围内为2-4%)阻碍了新药的及时开发。此外，研究表明，医生在邀请老年和少数族裔患者参加临床试验时，在统计上存在显著的偏见。拟议的项目与以医生为中心的努力是协同的，但目标是直接向患者提供个性化的、基于EMR的临床试验建议。这项研究的结果将赋予患者权力，提升他们在决策过程中的作用。

DESCRIPTION (provided by applicant): The long-term objective of this research is to increase the clinical trial enrollment of US patients via a semi- automated, Natural Language Processing (NLP) based, interactive and patient-centered informatics application. The study design is prospective observational study. Scope is limited to cancer patients. There are three specific aims for this project. The first aim is to identify concepts that overlap between the electronic medical record's (EMR) clinical notes and the free text of clinical trial announcements. The PI will use the concepts to develop mapping frames that connect concepts in the text of trial announcements to those found in clinical notes in the medical record. When he has the mapping frames he will build the NLP module for the application. In the software development work he will utilize as many publicly available software components as possible. He will experiment with UIMA, GATE, MetaMap, Stanford Parser, NegEx algorithm and others. The PI will develop the tool around the National Library of Medicine's Unified Medical Language System knowledgebase. He will use Java for programming. The second aim is to create an algorithm that automatically generates questions to request information directly from the patient if the information is not available or accessible in the records. The third aim is to evaluate the in-vitro, laboratory performance of the application. For performance evaluation purposes the PI will recruit cancer care specialists to generate the gold standard lists of eligible clinical trials for study patients. He will publicly release the developed code at the end of the grant period. This K99/R00 project will serve the foundation for future R01 grant applications. The PI is fully committed to become faculty in the Clinical Research Informatics domain with a specialization in biomedical NLP. The support of the K99/R00 grant will enable him to acquire substantial formal training in Computational Linguistics while contributing to the body of knowledge of the Clinical Research Informatics field. The five-year grant support will ensure success in his endeavor. The proposed work is highly significant because the dismal clinical trial accrual rates (2-4 % nationally) hampers timely development of new drugs. In addition, studies show that physicians have statistically significant bias against elderly and minority patients to invite participation in clinical trials. The proposed project is synergistic with physician-centered efforts but the goal is to provide individualized, EMR based clinical trial recommendations directly to the patients. The results of this research will empower the patients and elevate their role in the decision making process.