Department of Clinical Pharmacy, Canisius Wilhelmina Hospital, Nijmegen, The Netherlands.
CWZ Academy, Canisius Wilhelmina Hospital, Nijmegen, The Netherlands.
Int J Clin Pharm. 2023 Oct;45(5):1128-1135. doi: 10.1007/s11096-023-01641-6. Epub 2023 Sep 15.
It is estimated that one-third of delirium cases in hospitals could be prevented with appropriate interventions. In Dutch hospitals a manual instrument (VMS-questions) is used to identify patients at-risk for delirium. Delirium Model (DEMO) is an automated model which could support delirium prevention more efficiently. However, it has not been validated beyond the hospital it was developed in.
To externally validate the DEMO and compare its performance to the VMS-questions.
A retrospective cohort study between July and December 2018 was conducted. Delirium cases were identified through a chart review, and the VMS-questions were extracted from the electronic health records. The DEMO was validated in patients ≥ 60 years, and a comparison with the VMS-questions was made in patients ≥ 70 years.
In total 1,345 admissions were included. The DEMO predicted 59 out of 75 delirium cases (sensitivity 0.79, 95% CI = 0.68-0.87; specificity 0.75, 95% CI = 0.72-0.77). Compared to the VMS-questions, the DEMO showed a lower specificity (0.64 vs. 0.72; p < 0.001) and a comparable sensitivity (0.83 vs. 0.80; p = 0.56). The VMS-questions were missing in 20% of admissions, in which the DEMO correctly predicted 10 of 12 delirium cases.
The DEMO showed acceptable performance for delirium prediction. Overall the DEMO predicted more delirium cases because the VMS-questions were missing in 20% of admissions. This study shows that automated instruments such as DEMO could play a key role in the efficient and timely deployment of measures to prevent delirium.
据估计，医院中三分之一的谵妄病例可以通过适当的干预措施预防。在荷兰的医院中，使用一种手动工具（VMS-questions）来识别有谵妄风险的患者。Delirium Model (DEMO) 是一种自动化模型，它可以更有效地支持预防谵妄。然而，它尚未在开发它的医院之外进行验证。
对外验证 DEMO 并将其性能与 VMS-questions 进行比较。
在 2018 年 7 月至 12 月期间进行了回顾性队列研究。通过病历回顾确定谵妄病例，并从电子病历中提取 VMS-questions。在年龄≥60 岁的患者中验证了 DEMO，并在年龄≥70 岁的患者中与 VMS-questions 进行了比较。
共纳入 1345 例入院患者。DEMO 预测了 75 例谵妄病例中的 59 例（敏感性 0.79，95%置信区间 = 0.68-0.87；特异性 0.75，95%置信区间 = 0.72-0.77）。与 VMS-questions 相比，DEMO 的特异性较低（0.64 与 0.72；p<0.001），敏感性相当（0.83 与 0.80；p=0.56）。VMS-questions 在 20%的入院患者中缺失，在这些患者中，DEMO 正确预测了 12 例谵妄病例中的 10 例。
DEMO 对谵妄预测的表现可接受。总体而言，DEMO 预测了更多的谵妄病例，因为 VMS-questions 在 20%的入院患者中缺失。这项研究表明，像 DEMO 这样的自动化工具可以在高效和及时地部署预防谵妄的措施方面发挥关键作用。
