Automated Problem and Allergy Lists Enrichment Based on High Accuracy Information Extraction from the Electronic Health Record

基于电子健康记录中高精度信息提取的自动化问题和过敏列表丰富

• 批准号: 9357564
• 负责人: STEPHANE MEYSTRE
• 金额: $ 76.75万
• 依托单位: CLINACUITY,INC.
• 依托单位国家: 美国
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-08-01 至 2020-02-29
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9357564
• 关键词: Adverse drug event; Cessation of life; Cities; Clinical; Code; Communications Media; Complex; Development; Disease; Electronic Health Record; Ensure; Environment; Excision; Goals; Health Insurance Portability and Accountability Act; Health Personnel; Healthcare; Hospitals; Huntsman Cancer Institute at the University of Utah; Hybrids; Hypersensitivity; Imagery; Incentives; Injury; Inpatients; Institutes; Laboratories; Malignant Neoplasms; Manuals; Medical; Medical Errors; Medication Errors; Methods; Modernization; Natural Language Processing; Outpatients; Output; Patient Care; Patients; Performance; Pharmaceutical Preparations; Phase; Process; Reference Standards; Reporting; Risk; Sampling; Savings; Secure; Site; Sodium Chloride; Speed; Structure; System; Test Result; Testing; Text; Time; Training; United States Centers for Medicare and Medicaid Services; Universities; Utah; Work; base; cancer care; commercial application; commercialization; computerized physician order entry; cost; design; improved; payment; prevent; processing speed; prototype; public health relevance; software development; standard measure; usability; web services

 DESCRIPTION (provided by applicant): Medical errors are recognized as the cause of numerous deaths, and even if some are difficult to avoid, many are preventable. Computerized physician order-entry systems with decision support have been proposed to reduce this risk of medication errors, but these systems rely on structured and coded information in the electronic health record (EHR). Unfortunately, a substantial proportion of the information available in the EHR is only mentioned in narrative clinical documents. Electronic lists of problems and allergies are available in most EHRs, but they require manual management by their users, to add new problems, modify existing ones, and the removal of the ones that are irrelevant. Consequently, these electronic lists are often incomplete, inaccurate, and out of date. Clinacuity, Inc. proposed a new system to automatically extract structured and coded medical problems and allergies from clinical narrative text in the EHR of patients suffering from cancer, and established its feasibility. To advance this new system from a prototype to an accurate, adaptable, and robust system, integrated into the commercial EHR system used in our implementation and testing site (Huntsman Cancer Institute and University of Utah Hospital, Salt Lake City, Utah), and ready for commercialization efforts, we will work on the following aims: 1) enhance the NLP system performance, scalability, and quality, 2) develop an advanced visualization interface for local adaptation of the NLP system, and 3) integrate the NLP system with a commercial EHR system. A large and varied reference standard for training and testing the information extraction application will also be developed, a reference standard including a random sample of de-identified clinical narratives from patients treated at the Huntsman Cancer Institute and at the University of Utah Hospital (Salt Lake City, Utah), with problems and allergies annotated by domain experts. Commercial application: The system Clinacuity proposes will not only help healthcare providers maintain complete and timely lists of problems and allergies, providing them with an efficient overview of a patient, but also help healthcare organizations attain meaningful use requirements. The proposed system has potential commercial applications in inpatient and outpatient settings, increasing the efficiency of busy healthcare providers by saving time, and aiding healthcare organizations in demonstrating "meaningful use" and obtaining Centers for Medicare & Medicaid Services incentive payments. Clinacuity will further extend the commercial potential of the system and its output, using modular design principles allowing utilization of each module independently, and enhancing its local adaptability for easier deployment.

 描述（由申请人提供）：医疗错误被认为是导致大量死亡的原因，即使有些难以避免，但许多是可以预防的。具有决策支持功能的计算机化医生医嘱输入系统已被提出来降低用药错误的风险，但这些系统依赖于电子健康记录 (EHR) 中的结构化和编码信息。不幸的是，电子病历中可用的大部分信息仅在叙述性临床文件中提及。大多数电子病历中都提供问题和过敏的电子列表，但它们需要用户手动管理，添加新问题、修改现有问题以及删除不相关的问题。因此，这些电子列表通常不完整、不准确且过时。 Clinacuity, Inc. 提议 一种新系统可以从癌症患者电子病历中的临床叙述文本中自动提取结构化和编码的医疗问题和过敏，并确定了其可行性。为了将这个新系统从原型发展为准确、适应性强且强大的系统，集成到我们的实施和测试站点（犹他州盐湖城的亨斯曼癌症研究所和犹他大学医院）中使用的商业 EHR 系统中，并为商业化工作做好准备，我们将致力于以下目标：1）增强 NLP 系统的性能、可扩展性和质量，2）开发用于本地适应 NLP 系统的高级可视化界面， 3）将 NLP 系统与商业 EHR 系统集成。还将开发用于培训和测试信息提取应用程序的大型且多样化的参考标准，该参考标准包括来自亨茨曼癌症研究所和犹他大学医院（犹他州盐湖城）治疗的患者的去识别临床叙述的随机样本，并由领域专家注释问题和过敏。商业应用：Clinacuity 提出的系统不仅可以帮助医疗保健提供者维护完整、及时的问题和过敏清单，为他们提供对患者的有效概述，而且还可以帮助医疗保健组织实现有意义的使用要求。拟议的系统在住院和门诊环境中具有潜在的商业应用，通过节省时间来提高繁忙的医疗保健提供者的效率，并帮助医疗保健组织展示“有意义的使用”并获得医疗保险和医疗补助服务中心的奖励付款。 Clinacuity 将进一步扩展该系统及其输出的商业潜力，采用模块化设计原则，允许独立利用每个模块，并增强其本地适应性以方便部署。

项目成果

Automated Extraction and Classification of Cancer Stage Mentions fromUnstructured Text Fields in a Central Cancer Registry.

从中央癌症登记处的非结构化文本字段中自动提取和分类癌症分期。

• 发表时间: 2018
• 期刊: AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science
• 作者: AAlAbdulsalam,AbdulrahmanK;Garvin,JenniferH;Redd,Andrew;Carter,MarjorieE;Sweeny,Carol;Meystre,StephaneM
• 通讯作者: Meystre,StephaneM