PACS INFRASTRUCTURE TO SUPPORT-BASED MEDICAL PRACTICE

该计划项目赠款的广泛的长期目标是开发一个有效的基于成像的信息和医疗保健提供系统，以支持临床实践、研究和教育。拨款的具体目标是：(1)将PACS发展为促进患者主观临床症状客观化的有效基础设施；(2)开发通过结构化数据收集、医疗报告(NLP)的自然语言处理和医学图像的参数摘要来改进医疗数据表征的方法；(3)提供灵活的、针对患者的医学图像、时间表和结构化医疗数据的呈现方法。医疗数据的对象化、智能化访问和灵活的呈现提供了更好的信息，这将促进医学的循证实践，加强研究和评估。五个综合项目采用新的技术来处理该系统的具体内容。智能选择的成像方案被用于客观化患者的症状。明确定义的信息单元捕获和组织各种形式的数据，无论是直接或间接地通过用于图像参数摘要的文本的NP。患者病历通过内容与医学文献相关联。时间线将数据组织成一种格式，使医疗事件、其相关性和条件趋势易于可视化(项目3)。基于场景的代理提供对相关医疗信息的最新访问。当找不到完全匹配的信息时，Relation会将查询范围扩大到医疗信息。软件工具包和用户模型支持特定于用户、特定于域和特定于任务的定制。独立于硬件的架构将有助于跨不同平台和软件子系统访问该系统。它们共同构成了一个独特的基础设施，可提供对定义明确的结构化数据和最新文献的广泛、智能的定制访问。除了患者特定的相关数据、专家意见和已知结果的类似病例外，这将促进循证医学实践。五个综合项目采用新的技术来处理该系统的具体内容。智能秘密成像协议被用来客观化患者的症状。定义明确的信息单元可以直接或间接地通过NLP捕获和组织各种形式的数据，用于文本或图像的参数摘要。患者病历通过内容与医学文献相关联。时间线将数据组织成一种格式，使医疗事件、其相关性和条件趋势易于可视化(项目3)。基于场景的代理提供对相关医疗信息的最新访问。当找不到完全匹配的信息时，Relation会将查询范围扩大到医疗信息。软件工具包和用户模型支持特定于用户、特定于域和特定于任务的定制。独立于硬件的架构将有助于跨不同平台和软件子系统访问该系统。它们共同构成了一个独特的基础设施，可提供对定义明确的结构化数据和最新文献的广泛、智能的定制访问。除了患者特定的相关数据、专家意见和已知结果的类似病例外，这将促进循证医学实践。对拟议系统的影响的评估将侧重于技术措施、护理过程以及患者和医生的满意度。评估还将探讨流程变化与具体结果之间的关系，特别是与短期健康相关的生活质量。虽然没有提出正式的成本效益研究，但当这些PAC技术成熟时，就为这些测量奠定了基础。这些测量将通过记录资源利用情况、确定基于成像的护理事件以及与主要投诉相关的反特定信息来促进。

The broad, tong-term objective of this Program Project Grant is to develop an effective imaging-based information and health care delivery system to support clinical practice, research, and education. The specific aims of the grant are to: (1) evolve PACS into an effective infrastructure that promotes the objectification of subjective patient clinical symptoms, (2) develop methods for improving the characterization of medical data through structured data collection, natural language processing of medical reports (NLP) and parametric summarization for medical images, (3) provide flexible, patient -specific presentation methods of medical images, timelines, and structured medical data. The objectification, intelligent access, and flexible presentation of medical data provide better information, which will facilitate the evidence-based practice of medicine and enhance research and evaluation. Five integrated projects employ novel techniques to address specific elements of the system. Intelligently selected imaging protocols are used to objectify patient symptoms. Well-defined information units capture and structure diverse forms of data, whether directly or indirectly through NP for text of parametric summarization for images. Patient medical records are correlated with medical literature by content. Timelines organize the data into a format that allow medical events, their dependencies, and conditional trends to be easily visualized (Project 3). Scenario-based proxies provide up-to-date access to relevant medical information. Relaxation broadens queries to medical information when exact matches are not found. Software toolkits and user models enable user-, and domain-, and task-specific customizations. The hardware independent architecture will facilitate access to the system across different platforms and software subsystems. Together, they form a unique infrastructure that provides broad and intelligently customized access to well-defined structured data and up-to-date literature. This, in addition to patient-specific relevant data, expert opinion, and similar cases with known outcome, will promote the evidence-based practice of medicine. Five integrated projects employ novel techniques to address specific elements of the system. Intelligently secreted imaging protocols are used to objectify patient symptoms. Well-defined information units capture and structure diverse forms of data, whether directly or indirectly through NLP for text or parametric summarization for images. Patient medical records are correlated with medical literature by content. Timelines organize the data into a format that allow medical events, their dependencies, and conditional trends to be easily visualized (Project 3). Scenario-based proxies provide up-to-date access to relevant medical information. Relaxation broadens queries to medical information when exact matches are not found. Software toolkits and user models enable user-, and domain-, and task-specific customizations. The hardware independent architecture will facilitate access to the system across different platforms and software subsystems. Together, they form a unique infrastructure that provides broad and intelligently customized access to well-defined structured data and up-to-date literature. This, in addition to patient-specific relevant data, expert opinion, and similar cases with known outcome, will promote the evidence-based practice of medicine. Evaluation of the impact of the proposed system will focus on technical measures; process of care; and patient and physician satisfaction. The evaluation will also explore the relationship between process changes and specific outcomes, particularly short-term health related quality of life. Although a formal cost-effectiveness study is not proposed, the foundation is laid for these measurements when these PACs technologies mature. These measurements will be facilitated by recording resource utilization, determining of imaging-based episodes of care, and counter- specific information related to a chief complaint.