Peter L. Reichertz Institute for Medical Informatics, TU Braunschweig and Hannover Medical School, Braunschweig, Germany.
Department of Health Information Management, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran.
Stud Health Technol Inform. 2022 Jun 29;295:5-11. doi: 10.3233/SHTI220646.
The early warning system alarms the rapid response team (RRT) for clinical deterioration monitoring and prediction. Available systems do not perform well to decrease the number of ICU transfers or death. This study aimed to address the requirement of an intelligent warning system for timely and accurate RRT activation.
A literature review was conducted in scientific databases to extract data. Then, a questionnaire was developed for experts' views collection (N=12). The collected data were analyzed using the Content Validity Ratio (CVR). According to the Lawshe table for the corresponding number of experts, the cut-off=0.56 for items to be accepted/rejected was considered. A schematic structure was suggested.
The analysis of the extracted papers (N=24) and qualitative analysis addressed 44 requirements in the frame of five involved sub-systems, including a patient monitoring system, electronic health record, clinical decision support system, remote monitoring patient, and dashboard ®istries. They were confirmed by meeting the least cut-off value (CVR= 0.86).
An integrated approach and technologies of IoT, deep and machine learning techniques, big data, advanced databases, and standards to create an intelligent EWS are required.
早期预警系统为临床恶化监测和预测报警快速反应小组（RRT）。现有的系统在减少 ICU 转科或死亡人数方面效果不佳。本研究旨在满足智能预警系统对及时、准确激活 RRT 的需求。
在科学数据库中进行文献回顾以提取数据。然后，为专家意见收集开发了一份问卷（N=12）。使用内容有效性比（CVR）分析收集的数据。根据 Lawshe 表对应专家数量，将 0.56 作为接受/拒绝项目的截止值。提出了一个示意结构图。
对提取的论文（N=24）进行分析和定性分析，在五个相关子系统的框架内确定了 44 项要求，包括患者监测系统、电子健康记录、临床决策支持系统、远程监测患者以及仪表板和登记册。它们通过满足最低截止值（CVR=0.86）得到确认。
需要采用物联网、深度学习和机器学习技术、大数据、高级数据库和标准的集成方法和技术来创建智能 EWS。
