Open Health Natural Language Processing Collaboratory

开放健康自然语言处理合作实验室

• 批准号: 9385056
• 负责人: Xiaoqian Jiang
• 金额: $ 158.96万
• 依托单位: MAYO CLINIC ROCHESTER
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2022-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9385056
• 关键词: Address; Algorithms; Attention; Award; Biological Preservation; Clinic; Clinical; Clinical Data; Clinical Research; Clinical Sciences; Clinical Trials; Collaborations; Collection; Communities; Competence; Custom; Data; Data Analyses; Data Collection; Data Science; Detection; Disease; Electronic Health Record; Ensure; Familial Hypercholesterolemia; Frequencies; Health; Hepatolenticular Degeneration; Individual; Informatics; Information Distribution; Institution; Kidney Calculi; Knowledge; Leadership; Learning; Measures; Medical; Meta-Analysis; Minnesota; Modeling; Monitor; Morphologic artifacts; Natural Language Processing; Observational Study; Patients; Phenotype; Play; Precision Medicine Initiative; Privacy; Process; Rare Diseases; Recruitment Activity; Research; Research Infrastructure; Research Personnel; Rest; Risk; Role; Sampling; Security; Semantics; Site; Source; Structure; System; Talents; Techniques; Testing; Text; Time; Training; Translational Research; Universities; Work; base; citizen science; cohort; collaboratory; data registry; empowered; health data; improved; indexing; individual patient; informatics infrastructure; innovation; interest; novel; phenotypic data; phrases; portability; statistics; tool; usability; virtual; Address; Algorithms; Attention; Award; Biological Preservation; Clinic; Clinical; Clinical Data; Clinical Research; Clinical Sciences; Clinical Trials; Collaborations; Collection; Communities; Competence; Custom; Data; Data Analyses; Data Collection; Data Science; Detection; Disease; Electronic Health Record; Ensure; Familial Hypercholesterolemia; Frequencies; Health; Hepatolenticular Degeneration; Individual; Informatics; Information Distribution; Institution; Kidney Calculi; Knowledge; Leadership; Learning; Measures; Medical; Meta-Analysis; Minnesota; Modeling; Monitor; Morphologic artifacts; Natural Language Processing; Observational Study; Patients; Phenotype; Play; Precision Medicine Initiative; Privacy; Process; Rare Diseases; Recruitment Activity; Research; Research Infrastructure; Research Personnel; Rest; Risk; Role; Sampling; Security; Semantics; Site; Source; Structure; System; Talents; Techniques; Testing; Text; Time; Training; Translational Research; Universities; Work; base; citizen science; cohort; collaboratory; data registry; empowered; health data; improved; indexing; individual patient; informatics infrastructure; innovation; interest; novel; phenotypic data; phrases; portability; statistics; tool; usability; virtual

Project Summary One of the major barriers in leveraging Electronic Health Record (EHR) data for clinical and translational science is the prevalent use of unstructured or semi-structured clinical narratives for documenting clinical information. Natural Language Processing (NLP), which extracts structured information from narratives, has received great attention and has played a critical role in enabling secondary use of EHRs for clinical and translational research. As demonstrated by large scale efforts such as ACT (Accrual of patients for Clinical Trials), eMERGE, and PCORnet, using EHR data for research rests on the capabilities of a robust data and informatics infrastructure that allows the structuring of clinical narratives and supports the extraction of clinical information for downstream applications. Current successful NLP use cases often require a strong informatics team (with NLP experts) to work with clinicians to supply their domain knowledge and build customized NLP engines iteratively. This requires close collaboration between NLP experts and clinicians, not feasible at institutions with limited informatics support. Additionally, the usability, portability, and generalizability of the NLP systems are still limited, partially due to the lack of access to EHRs across institutions to train the systems. The limited availability of EHR data limits the training available to improve the workforce competence in clinical NLP. We aim to address the above challenges by extending our existing collaboration among multiple CTSA hubs on open health natural language processing (OHNLP) to share distributional information of NLP artifacts (i.e., words, n-grams, phrases, sentences, concept mentions, concepts, and text segments) acquired from real EHRs across multiple institutions. We will leverage the advanced privacy-preserving computing infrastructure of iDASH (integrating Data for Analysis, Anonymization, and SHaring) for privacy- preserving data analysis models and will partner with diverse communities including Observational Health Data Sciences and Informatics (OHDSI), Precision Medicine Initiative (PMI), PCORnet, and Rare Diseases Clinical Research Network (RDCRN) to demonstrate the utility of NLP for translational research. This CTSA innovation award RFA provides us with a unique opportunity to address the challenges faced with clinical NLP and through strong partnership with multiple research communities and leadership roles of the research team in clinical NLP, we envision that the successful delivery of this project will broaden the utilization of clinical NLP across the research community. There are four aims planned: i) obtain PHI-suppressed NLP artifacts with retained distribution information across multiple institutions and assess the privacy risk of accessing PHI- suppressed artifacts, ii) generate a synthetic text corpus for exploratory analysis of clinical narratives and assess its utility in NLP tasks leveraging various NLP challenges, iii) develop privacy-preserving computational phenotyping models empowered with NLP, and iv) partner with diverse communities to demonstrate the utility of our project for translational research.

项目摘要 利用电子健康记录（EHR）数据的主要障碍之一 科学是普遍使用非结构化或半结构化临床叙述来记录临床的 信息。自然语言处理（NLP）从叙述中提取结构化信息， 受到了极大的关注，并且在使EHR用于临床和 翻译研究。正如大规模努力（例如ACT）所证明的那样（临床患者应计 试验），出现和PCORNET使用EHR数据进行研究，取决于强大的数据的功能 信息基础设施，允许临床叙事结构并支持临床的提取 下游应用程序的信息。当前成功的NLP用例通常需要强大的信息学 团队（与NLP专家一起）与临床医生一起提供其领域知识并建立定制的NLP 发动机迭代。这需要NLP专家和临床医生之间的密切合作，在 信息学支持有限的机构。此外， NLP系统仍然受到限制，部分原因是跨机构无法访问EHR来培训 系统。 EHR数据的有限可用性限制了可用的培训以提高劳动力能力 在临床NLP中。我们的目的是通过扩展我们现有的合作来应对上述挑战 关于开放健康自然语言处理（OHNLP）的多个CTSA枢纽，以共享 NLP工件（即单词，n-grams，短语，句子，概念提及，概念和文本段） 从多个机构中从真实的EHR中获取。我们将利用高级隐私权 计算IDASH的基础架构（集成数据以进行分析，匿名和共享）以进行隐私 - 保存数据分析模型，并将与包括观察健康数据在内的不同社区合作 科学和信息学（OHDSI），精密医学倡议（PMI），PCORNET和罕见疾病临床 研究网络（RDCRN）证明了NLP用于转化研究的实用性。这项CTSA创新 RFA奖为我们提供了一个独特的机会，以应对临床NLP和 通过与多个研究社区和研究团队的领导角色的牢固伙伴关系 临床NLP，我们设想该项目的成功交付将扩大临床NLP的利用 在整个研究界。计划有四个目标：i）与 保留多个机构之间的分销信息，并评估访问PHI的隐私风险 抑制工件，ii）生成一个合成文本语料库，用于临床叙述和 评估其在利用各种NLP挑战的NLP任务中的效用，iii）开发保护隐私计算 通过NLP授权的表型模型，iv）与不同社区合作以展示实用程序 我们的转化研究项目。