Validation of a Delirium Risk Assessment Using Electronic Medical Record Information
Validation of a Delirium Risk Assessment Using Electronic Medical Record Information
复制标题
DOI：
10.1016/j.jamda.2015.10.020
复制
发表时间：
2016-03-01
影响因子：
7.6
通讯作者：
Archambault, Elizabeth
中科院分区：
文献类型：
--
作者：
Rudolph, James L.;Doherty, Kelly;Archambault, Elizabeth
目的：识别有谵妄风险的患者可以及时应用预防，诊断和治疗策略;但很少这样做。一旦出现谵妄，患者更可能需要spitalization后熟练的护理。本研究使用国家临床卓越中心荟萃分析中确定的独立风险因素开发了一种先验电子预测规则，并验证了在2个队列中预测谵妄的能力。设计：回顾性分析，随后进行前瞻性验证。设置：新英格兰的三级VA医院。参与者：共计27，625例住院患者的病历和246例前瞻性入组患者入院。使用从患者电子病历（EMR）获得的数据创建电子谵妄风险预测规则。主要结局谵妄通过两种方式确定：（1）EMR（回顾性队列）和（2）入组时和此后每日的临床评估（前瞻性受试者）。我们用C统计量评估谵妄预测规则的区分度。次要结果是住院时间和出院到rehabilitation.Results：回顾性，谵妄被确定在8%的医疗记录（n = 2343）;前瞻性，谵妄住院期间存在于26%的参与者（n = 64）。在回顾性队列中，在低、中、高和极高风险组中，分别有2%、3%、11%和38%的患者确定了病历谵妄（C-统计量= 0.81; 95%置信区间0.80 - 0.82）。Proximity，电子预测规则在这些组中确定了15%、18%、31%和55%的谵妄（C-统计量= 0.69; 95%置信区间0.61 - 0.77）。与低风险患者相比，高或极高谵妄风险患者的住院时间延长（5.7 +/-5.6 vs 3.7 +/-2.7天; P = 0.001）和更高的出院率（8.9% vs 20.8%; P =.02）。使用EMR算法自动计算谵妄风险识别处于谵妄风险的患者，这为获得临床效率和改进谵妄识别创造了关键机会，包括那些需要专业护理的人。爱思唯尔公司出版代表AMDA-急性后和长期护理医学协会。
Objective: Identifying patients at risk for delirium allows prompt application of prevention, diagnostic, and treatment strategies; but is rarely done. Once delirium develops, patients are more likely to need posthospitalization skilled care. This study developed an a priori electronic prediction rule using independent risk factors identified in a National Center of Clinical Excellence meta-analysis and validated the ability to predict delirium in 2 cohorts.Design: Retrospective analysis followed by prospective validation.Setting: Tertiary VA Hospital in New England.Participants: A total of 27,625 medical records of hospitalized patients and 246 prospectively enrolled patients admitted to the hospital.Measurements: The electronic delirium risk prediction rule was created using data obtained from the patient electronic medical record (EMR). The primary outcome, delirium, was identified 2 ways: (1) from the EMR (retrospective cohort) and (2) clinical assessment on enrollment and daily thereafter (prospective participants). We assessed discrimination of the delirium prediction rule with the C-statistic. Secondary outcomes were length of stay and discharge to rehabilitation.Results: Retrospectively, delirium was identified in 8% of medical records (n = 2343); prospectively, delirium during hospitalization was present in 26% of participants (n = 64). In the retrospective cohort, medical record delirium was identified in 2%, 3%, 11%, and 38% of the low, intermediate, high, and very high-risk groups, respectively (C-statistic = 0.81; 95% confidence interval 0.80-0.82). Prospectively, the electronic prediction rule identified delirium in 15%, 18%, 31%, and 55% of these groups (C-statistic = 0.69; 95% confidence interval 0.61-0.77). Compared with low-risk patients, those at high-or very high delirium risk had increased length of stay (5.7 +/- 5.6 vs 3.7 +/- 2.7 days; P =.001) and higher rates of discharge to rehabilitation (8.9% vs 20.8%; P =.02).Conclusions: Automatic calculation of delirium risk using an EMR algorithm identifies patients at risk for delirium, which creates a critical opportunity for gaining clinical efficiencies and improving delirium identification, including those needing skilled care. Published by Elsevier Inc. on behalf of AMDA - The Society for Post-Acute and Long-Term Care Medicine.