Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model.
Predicting Pressure Injury in Critical Care Patients: A Machine-Learning Model.
复制标题
DOI：
10.4037/ajcc2018525
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Cummins MR
中科院分区：
文献类型：
--
作者：
Alderden J;Pepper GA;Wilson A;Whitney JD;Richardson S;Butcher R;Jo Y;Cummins MR
医院获得性压力损伤是重症监护患者中的一个严重问题。有些可以通过使用特殊病床等措施来预防，但由于成本原因，这些措施对每个病人都不可行。然而，决定哪些病人将受益最多的专科病床是困难的，因为现有的工具，以确定压力损伤的风险的结果表明，大多数重症监护患者处于高风险。建立一个预测外科危重病人压力损伤发展的模型。来自电子健康记录的数据被分为训练（67%）和测试（33%）数据集，并通过R包“randomforest”使用随机森林算法开发模型。在6376例患者的样本中，516例患者（8.1%）发生了1级或以上（结局变量1）的医院获得性压力损伤，257例患者（4.0%）发生了2级或以上（结局变量2）的损伤。开发了随机森林模型，通过使用测试集评估分类器性能来预测1级及以上和2级及以上损伤。两种模型的受试者工作特征曲线下面积均为0.79。这种机器学习方法与其他可用的模型不同，因为它不需要临床医生将信息输入到工具中（例如，Braden量表）。相反，它使用电子健康记录中随时可用的信息。接下来的步骤包括在独立样品中进行测试，然后进行校准以优化特异性。（American Journal of Critical Care）2018; 27：461-468）
Hospital-acquired pressure injuries are a serious problem among critical care patients. Some can be prevented by using measures such as specialty beds, which are not feasible for every patient because of costs. However, decisions about which patient would benefit most from a specialty bed are difficult because results of existing tools to determine risk for pressure injury indicate that most critical care patients are at high risk. To develop a model for predicting development of pressure injuries among surgical critical care patients. Data from electronic health records were divided into training (67%) and testing (33%) data sets, and a model was developed by using a random forest algorithm via the R package “randomforest.” Among a sample of 6376 patients, hospital-acquired pressure injuries of stage 1 or greater (outcome variable 1) developed in 516 patients (8.1%) and injuries of stage 2 or greater (outcome variable 2) developed in 257 (4.0%). Random forest models were developed to predict stage 1 and greater and stage 2 and greater injuries by using the testing set to evaluate classifier performance. The area under the receiver operating characteristic curve for both models was 0.79. This machine-learning approach differs from other available models because it does not require clinicians to input information into a tool (eg, the Braden Scale). Rather, it uses information readily available in electronic health records. Next steps include testing in an independent sample and then calibration to optimize specificity. (American Journal of Critical Care. 2018; 27:461–468)
登录
查看更多内容
DOI：
10.1097/won.0b013e3181f90a34
发表时间：
2010-11-01
影响因子：
2.6
作者：
Slowikowski, Gerri C.;Funk, Marjorie
通讯作者：
Funk, Marjorie
影响因子：
1.4
作者：
Bruce, Tracey A.;Shever, Leah L.;Gombert, Jan
通讯作者：
Gombert, Jan
基于模型的递归分区的随机森林方法：R。
影响因子：
3
作者：
Garge NR;Bobashev G;Eggleston B
通讯作者：
Eggleston B
DOI：
10.4037/ajcc2013991
发表时间：
2013-11
期刊：
American journal of critical care : an official publication, American Association of Critical-Care Nurses
影响因子：
--
作者：
Hyun S;Vermillion B;Newton C;Fall M;Li X;Kaewprag P;Moffatt-Bruce S;Lenz ER
通讯作者：
Lenz ER
DOI：
10.1196/annals.1310.015
发表时间：
2004-01-01
期刊：
APPLICATIONS OF BIOINFORMATICS IN CANCER DETECTION
影响因子：
--
作者：
Izmirlian, G
通讯作者：
Izmirlian, G