Development of inpatient risk stratification models of acute kidney injury for use in electronic health records.
Development of inpatient risk stratification models of acute kidney injury for use in electronic health records.
复制标题
DOI：
10.1177/0272989x10364246
复制
发表时间：
2010-11
期刊：
影响因子：
--
通讯作者：
Peterson JF
中科院分区：
文献类型：
--
作者：
Matheny ME;Miller RA;Ikizler TA;Waitman LR;Denny JC;Schildcrout JS;Dittus RS;Peterson JF
医院获得性急性肾损伤（AKI）患者面临死亡率增加和进一步医疗并发症的风险。使用电子健康记录（EHR）中易于实现的预测工具对这些患者进行评估，可以在AKI发展之前识别高风险患者，并可以预防医源性AKI发作并改善临床管理。我们使用从电子病历中获得的结构化临床数据来识别1999年8月1日至2003年7月31日入院的肾功能正常的患者。利用行政管理、计算机化的供应商订单输入和实验室测试数据，我们建立了一个3级风险分层模型，以预测由RIFLE标准定义的两种严重程度的院内AKI。严重程度定义为基线血清肌酐的150%或200%。模型判别和校准采用10倍交叉验证进行评估。模型的交叉验证结果显示，受试者工作特征曲线下面积分别为0.75（150%海拔）和0.78（200%海拔）。两个模型都经过了充分的校准，Hosmer-Lemeshow拟合优度检验卡方值分别为9.7 （p = 0.29）和12.7 （p = 0.12）。我们仅使用常用的电子数据生成了医院获得性AKI的风险预测模型。这些模型确定了AKI高风险患者，这些患者可能从早期干预或加强监测中受益。
Patients with hospital-acquired acute kidney injury (AKI) are at risk for increased mortality and further medical complications. Evaluating these patients with a prediction tool easily implemented within an electronic health record (EHR) would identify high risk patients prior to the development of AKI, and could prevent iatrogenically induced episodes of AKI and improve clinical management. We used structured clinical data acquired from an EHR to identify patients with normal kidney function for admissions from August 1st, 1999 to July 31st, 2003. Using administrative, computerized provider order entry, and laboratory test data, we developed a 3-level risk stratification model to predict each of two severity levels of in-hospital AKI as defined by RIFLE criteria. The severity levels were defined as 150% or 200% of baseline serum creatinine. Model discrimination and calibration was evaluated using 10-fold cross-validation. Cross-validation of the models resulted in area under the receiver operating characteristic (AUC) curves of 0.75 (150% elevation) and 0.78 (200% elevation). Both models were adequately calibrated as measured by the Hosmer-Lemeshow goodness-of-fit test chi-squared values of 9.7 (p = 0.29) and 12.7 (p = 0.12), respectively. We generated risk prediction models for hospital-acquired AKI using only commonly available electronic data. The models identify patients at high risk for AKI who might benefit from early intervention or increased monitoring.