基于电子健康记录机器学习模型预测新入院无认知障碍患者谵妄风险的开发与验证
本研究为回顾性队列研究,利用UCSF Health 2016年1月1日至2017年8月31日出院的14227例成人非ICU且入院无谵妄患者训练5种机器学习算法,以2017年8月1日至11月30日出院的3996例患者为测试集。谵妄定义为护理谵妄筛查量表或ICU意识模糊评估法阳性。梯度提升机模型表现最佳,AUC为0.855,优于AWOL评分的0.678;在特异度90%时,敏感度59.7%(95%CI 52.4%-66.7%),阳性预测值23.1%(95%CI 20.5%-25.9%),阴性预测值97.8%(95%CI 97.4%-98.1%),需筛查人数4.8。作者认为该模型可利用入院24小时内电子健康记录数据估计医院获得性谵妄风险,或可在不增加医护人员负担的情况下更精准分配谵妄预防资源。
要点
- 梯度提升机模型预测谵妄的AUC为0.855,优于AWOL评分的基线AUC 0.678。
- 在特异度设定为90%时,模型敏感度为59.7%(95%CI 52.4%-66.7%),阳性预测值23.1%(95%CI 20.5%-25.9%),阴性预测值97.8%(95%CI 97.4%-98.1%),需筛查人数4.8。
- 惩罚逻辑回归和随机森林模型同样表现良好,AUC分别为0.854和0.848。
- 模型基于入院24小时内可获取的电子健康记录数据(人口学特征、诊断、护理记录、实验室结果和药物)构建。
- 训练集和测试集的谵妄发生率均为4.8%(训练集687/14227,测试集191/3996)。
适用人群与场景
- 训练集:2016年1月1日至2017年8月31日从UCSF Health出院的14227例成人患者,均为非重症监护室住院且入院时无谵妄。
- 测试集:2017年8月1日至11月30日出院的3996例住院患者。
- 总分析人群:18223例住院患者,其中6604例(36.2%)年龄>64岁,9301例(51.0%)为女性,878例(4.8%)发生谵妄。
诊断标准与关键阈值
- 谵妄定义:护理谵妄筛查量表(Nursing Delirium Screening Scale)阳性或ICU意识模糊评估法(Confusion Assessment Method for the Intensive Care Unit)评分阳性。
- AWOL评分:年龄>79岁、无法倒拼world、对地点定向障碍、护士评估疾病严重程度较高,共4项。
研究设计与关键结果
- 研究类型:回顾性队列研究,评估5种机器学习算法,使用专家小组确定的796个临床变量(入院24小时内电子健康记录中可获取)预测谵妄。
- 训练集14227例(5113例[35.9%]年龄>64岁;7335例[51.6%]女性;687例[4.8%]发生谵妄),测试集3996例(1491例[37.3%]年龄>64岁;1966例[49.2%]女性;191例[4.8%]发生谵妄)。
- AWOL评分基线AUC为0.678;梯度提升机模型AUC为0.855,表现最佳;惩罚逻辑回归和随机森林模型AUC分别为0.854和0.848。
- 在特异度90%时,梯度提升机模型的敏感度为59.7%(95%CI 52.4%-66.7%),阳性预测值为23.1%(95%CI 20.5%-25.9%),阴性预测值为97.8%(95%CI 97.4%-98.1%),需筛查人数为4.8。
证据类型、等级与局限
- 证据类型:回顾性队列研究(模型开发与验证)。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为,机器学习可利用入院24小时内可获取的电子健康记录数据估计医院获得性谵妄风险。
- 作者认为,该模型或可在不增加医护人员负担的情况下,更精准地将谵妄预防资源用于高危患者。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
IMPORTANCE: Current methods for identifying hospitalized patients at increased risk of delirium require nurse-administered questionnaires with moderate accuracy.
OBJECTIVE: To develop and validate a machine learning model that predicts incident delirium risk based on electronic health data available on admission.
DESIGN, SETTING, AND PARTICIPANTS: Retrospective cohort study evaluating 5 machine learning algorithms to predict delirium using 796 clinical variables identified by an expert panel as relevant to delirium prediction and consistently available in electronic health records within 24 hours of admission. The training set comprised 14 227 adult patients with non-intensive care unit hospital stays and no delirium on admission who were discharged between January 1, 2016, and August 31, 2017, from UCSF Health, a large academic health institution. The test set comprised 3996 patients with hospital stays who were discharged between August 1, 2017, and November 30, 2017.
EXPOSURES: Patient demographic characteristics, diagnoses, nursing records, laboratory results, and medications available in electronic health records during hospitalization.
MAIN OUTCOMES AND MEASURES: Delirium was defined as a positive Nursing Delirium Screening Scale or Confusion Assessment Method for the Intensive Care Unit score. Models were assessed using the area under the receiver operating characteristic curve (AUC) and compared against the 4-point scoring system AWOL (age >79 years, failure to spell world backward, disorientation to place, and higher nurse-rated illness severity), a validated delirium risk-assessment tool routinely administered in this cohort.
RESULTS: The training set included 14 227 patients (5113 [35.9%] aged >64 years; 7335 [51.6%] female; 687 [4.8%] with delirium), and the test set included 3996 patients (1491 [37.3%] aged >64 years; 1966 [49.2%] female; 191 [4.8%] with delirium). In total, the analysis included 18 223 hospital admissions (6604 [36.2%] aged >64 years; 9301 [51.0%] female; 878 [4.8%] with delirium). The AWOL system achieved a baseline AUC of 0.678. The gradient boosting machine model performed best, with an AUC of 0.855. Setting specificity at 90%, the model had a 59.7% (95% CI, 52.4%-66.7%) sensitivity, 23.1% (95% CI, 20.5%-25.9%) positive predictive value, 97.8% (95% CI, 97.4%-98.1%) negative predictive value, and a number needed to screen of 4.8. Penalized logistic regression and random forest models also performed well, with AUCs of 0.854 and 0.848, respectively.
CONCLUSIONS AND RELEVANCE: Machine learning can be used to estimate hospital-acquired delirium risk using electronic health record data available within 24 hours of hospital admission. Such a model may allow more precise targeting of delirium prevention resources without increasing the burden on health care professionals.
参考来源
- Wong A, Young AT, Liang AS, et al. Development and Validation of an Electronic Health Record-Based Machine Learning Model to Estimate Delirium Risk in Newly Hospitalized Patients Without Known Cognitive Impairment. JAMA Netw Open. 2018. PMID: 30646095. doi:10.1001/jamanetworkopen.2018.1018
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。