Detecting deviations in clinical care in ICU data streams

检测 ICU 数据流中临床护理的偏差

• 批准号: 8098786
• 负责人: Gilles Clermont
• 金额: $ 49.85万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-09-01 至 2013-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/8098786
• 关键词: Algorithms; Anticoagulants; Belief; Cardiac; Caring; Cessation of life; Clinical; Clinical Data; Clinical Management; Computerized Medical Record; Computers; Critical Care; Critical Illness; Data; Databases; Detection; Development; Disadvantaged; Drops; Electronics; Evaluation; Event; Future; Healthcare; Heparin; Individual; Industry; Information Systems; Intensive Care Units; Knowledge; Lead; Left; Machine Learning; Measures; Medical Errors; Medicine; Methods; Modeling; Monitor; Operative Surgical Procedures; Patient Care; Patient Monitoring; Patients; Pattern; Performance; Physicians; Platelet Count measurement; Play; Practice Management; Quality of Care; Relative (related person); Research; Research Personnel; Services; Signal Transduction; Solutions; Statistical Models; Stream; System; Testing; Thrombocytopenia; Thrombosis; Time; Work; base; biomedical informatics; clinical care; clinical practice; computer science; cost; experience; follow-up; health care quality; improved; knowledge base; multidisciplinary; public health relevance; research study; tool

DESCRIPTION (provided by applicant): Timely detection of severe patient conditions or concerning events and their mitigation remains an important problem in clinical practice. This is especially true in the critically ill patient [1]. Typical computer-based detection methods developed for this purpose rely on the use of clinical knowledge, such as expert-derived rules, that are incorporated into monitoring and alerting systems. However, it is often time-consuming, costly, and difficult to extract and implement such knowledge in existing monitoring systems. The research work in this proposal offers computational, rather than expert-based, solutions that build alert systems from data stored in patient data repositories, such as electronic medical records. Briefly, our approach uses advanced machine learning algorithms to identify unusual clinical management patterns in individual patients, relative to patterns associated with comparable patients, and raises an alert signaling this discrepancy. Our preliminary studies provide support that such deviations often indicate clinically important events for which it is worthwhile to raise an alert. We propose an evaluation based on physician assessment of alerts that are generated from a retrospective set of intensive-care unit (ICU) patient cases. The project investigators comprise a multidisciplinary team with expertise in critical care medicine, computer science, biomedical informatics, statistical machine learning, knowledge based systems, and clinical data repositories. PUBLIC HEALTH RELEVANCE: There remain numerous opportunities to reduce medical errors in critical care by sending computer-based reminders and alerts to clinicians. This project uses past patient data, which is stored in electronic form, and machine-learning methods to help develop and refine computer-based alerts to improve healthcare quality and reduce costs.

描述（由申请人提供）：及时检测严重患者状况或相关事件及其缓解仍然是临床实践中的一个重要问题。这在重症患者中尤为明显[1]。为此目的开发的典型的基于计算机的检测方法依赖于临床知识的使用，例如专家导出的规则，这些规则被并入监测和警报系统中。然而，在现有的监控系统中提取和实施此类知识通常耗时、成本高且困难。该提案中的研究工作提供了计算而不是基于专家的解决方案，这些解决方案可以从存储在患者数据存储库中的数据（如电子病历）中构建警报系统。简而言之，我们的方法使用先进的机器学习算法来识别个体患者中不寻常的临床管理模式，相对于与可比患者相关的模式，并发出警报，表明这种差异。我们的初步研究提供了支持，这种偏离往往表明临床上重要的事件，这是值得提高警惕。我们提出了一个评估的基础上，从一组回顾性的重症监护病房（ICU）患者的情况下产生的警报的医生评估。项目研究人员组成了一个多学科团队，拥有重症监护医学，计算机科学，生物医学信息学，统计机器学习，基于知识的系统和临床数据存储库的专业知识。 公共卫生相关性：通过向临床医生发送基于计算机的提醒和警报，仍然有许多机会减少重症监护中的医疗错误。该项目使用以电子形式存储的过去患者数据和机器学习方法来帮助开发和改进基于计算机的警报，以提高医疗质量并降低成本。