Reiner Bruce
Department of Radiology, Baltimore VA Medical Center, 10 North Greene Street, Baltimore, MD, 21201, USA,
J Digit Imaging. 2015 Aug;28(4):381-5. doi: 10.1007/s10278-015-9795-3.
In current medical practice, data extraction is limited by a number of factors including lack of information system integration, manual workflow, excessive workloads, and lack of standardized databases. The combined limitations result in clinically important data often being overlooked, which can adversely affect clinical outcomes through the introduction of medical error, diminished diagnostic confidence, excessive utilization of medical services, and delays in diagnosis and treatment planning. Current technology development is largely inflexible and static in nature, which adversely affects functionality and usage among the diverse and heterogeneous population of end users. In order to address existing limitations in medical data extraction, alternative technology development strategies need to be considered which incorporate the creation of end user profile groups (to account for occupational differences among end users), customization options (accounting for individual end user needs and preferences), and context specificity of data (taking into account both the task being performed and data subject matter). Creation of the proposed context- and user-specific data extraction and presentation templates offers a number of theoretical benefits including automation and improved workflow, completeness in data search, ability to track and verify data sources, creation of computerized decision support and learning tools, and establishment of data-driven best practice guidelines.
在当前的医疗实践中,数据提取受到多种因素的限制,包括信息系统缺乏整合、手工工作流程、工作量过大以及缺乏标准化数据库。这些综合限制导致具有临床重要性的数据常常被忽视,进而可能通过引入医疗差错、降低诊断信心、过度使用医疗服务以及延误诊断和治疗规划等方式对临床结果产生不利影响。当前的技术发展在很大程度上本质上是不灵活和静态的,这对最终用户群体的多样性和异构性中的功能和使用产生不利影响。为了解决医疗数据提取中现有的限制,需要考虑替代技术开发策略,其中包括创建最终用户档案组(以考虑最终用户之间的职业差异)、定制选项(考虑个别最终用户的需求和偏好)以及数据的上下文特异性(同时考虑正在执行的任务和数据主题)。创建所提议的上下文和用户特定的数据提取和呈现模板具有许多理论优势,包括自动化和改进工作流程、数据搜索的完整性、跟踪和验证数据源的能力、创建计算机化决策支持和学习工具以及建立数据驱动的最佳实践指南。