Department of Biomedical Informatics, University of Utah, Salt Lake City, UT 84108, United States.
College of Pharmacy, Idaho State University, Meridian, ID 83642, United States.
J Am Med Inform Assoc. 2023 Dec 22;31(1):256-273. doi: 10.1093/jamia/ocad203.
Surveillance algorithms that predict patient decompensation are increasingly integrated with clinical workflows to help identify patients at risk of in-hospital deterioration. This scoping review aimed to identify the design features of the information displays, the types of algorithm that drive the display, and the effect of these displays on process and patient outcomes.
The scoping review followed Arksey and O'Malley's framework. Five databases were searched with dates between January 1, 2009 and January 26, 2022. Inclusion criteria were: participants-clinicians in inpatient settings; concepts-intervention as deterioration information displays that leveraged automated AI algorithms; comparison as usual care or alternative displays; outcomes as clinical, workflow process, and usability outcomes; and context as simulated or real-world in-hospital settings in any country. Screening, full-text review, and data extraction were reviewed independently by 2 researchers in each step. Display categories were identified inductively through consensus.
Of 14 575 articles, 64 were included in the review, describing 61 unique displays. Forty-one displays were designed for specific deteriorations (eg, sepsis), 24 provided simple alerts (ie, text-based prompts without relevant patient data), 48 leveraged well-accepted score-based algorithms, and 47 included nurses as the target users. Only 1 out of the 10 randomized controlled trials reported a significant effect on the primary outcome.
Despite significant advancements in surveillance algorithms, most information displays continue to leverage well-understood, well-accepted score-based algorithms. Users' trust, algorithmic transparency, and workflow integration are significant hurdles to adopting new algorithms into effective decision support tools.
预测患者失代偿的监测算法越来越多地与临床工作流程相结合，以帮助识别有住院恶化风险的患者。本范围综述旨在确定信息显示的设计特征、驱动显示的算法类型，以及这些显示对流程和患者结局的影响。
该范围综述遵循 Arksey 和 O'Malley 的框架。五个数据库进行了搜索，时间范围为 2009 年 1 月 1 日至 2022 年 1 月 26 日。纳入标准为：参与者——住院环境中的临床医生；概念——作为利用自动化 AI 算法的恶化信息显示的干预措施；对照为常规护理或替代显示；结局为临床、工作流程和可用性结局；背景为任何国家的模拟或真实医院环境。筛选、全文审查和数据提取由每个步骤的 2 名研究人员独立进行。通过共识确定显示类别。
在 14575 篇文章中，有 64 篇被纳入综述，描述了 61 个独特的显示。41 个显示是为特定恶化设计的（例如，脓毒症），24 个提供简单警报（即，没有相关患者数据的基于文本的提示），48 个利用公认的基于评分的算法，47 个将护士作为目标用户。在 10 项随机对照试验中，只有 1 项报告了对主要结局的显著影响。
尽管监测算法取得了重大进展，但大多数信息显示仍然利用了众所周知、被广泛接受的基于评分的算法。用户信任、算法透明度和工作流程集成是将新算法有效纳入决策支持工具的重大障碍。
