Section of Nephrology, Department of Medicine, Yale University School of Medicine, New Haven, CT; Clinical and Translational Research Accelerator, Yale University School of Medicine, New Haven, CT; Division of Nephrology, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD.
Section of Nephrology, Department of Medicine, Yale University School of Medicine, New Haven, CT; Clinical and Translational Research Accelerator, Yale University School of Medicine, New Haven, CT.
Am J Kidney Dis. 2020 Dec;76(6):806-814.e1. doi: 10.1053/j.ajkd.2020.05.003. Epub 2020 Jun 4.
RATIONALE & OBJECTIVE: Acute kidney injury (AKI) is diagnosed based on changes in serum creatinine concentration, a late marker of this syndrome. Algorithms that predict elevated risk for AKI are of great interest, but no studies have incorporated such an algorithm into the electronic health record to assist with clinical care. We describe the experience of implementing such an algorithm.
Prospective observational cohort study.
SETTING & PARTICIPANTS: 2,856 hospitalized adults in a single urban tertiary-care hospital with an algorithm-predicted risk for AKI in the next 24 hours>15%. Alerts were also used to target a convenience sample of 100 patients for measurement of 16 urine and 6 blood biomarkers.
Clinical characteristics at the time of pre-AKI alert.
AKI within 24 hours of pre-AKI alert (AKI).
Descriptive statistics and univariable associations.
At enrollment, mean predicted probability of AKI was 19.1%; 18.9% of patients went on to develop AKI. Outcomes were generally poor among this population, with 29% inpatient mortality among those who developed AKI and 14% among those who did not (P<0.001). Systolic blood pressure<100mm Hg (28% of patients with AKI vs 18% without), heart rate>100 beats/min (32% of patients with AKI vs 24% without), and oxygen saturation<92% (15% of patients with AKI vs 6% without) were all more common among those who developed AKI. Of all biomarkers measured, only hyaline casts on urine microscopy (72% of patients with AKI vs 25% without) and fractional excretion of urea nitrogen (20% [IQR, 12%-36%] among patients with AKI vs 34% [IQR, 25%-44%] without) differed between those who did and did not develop AKI.
Single-center study, reliance on serum creatinine level for AKI diagnosis, small number of patients undergoing biomarker evaluation.
A real-time AKI risk model was successfully integrated into the EHR.
急性肾损伤（AKI）的诊断依据是血清肌酐浓度的变化，这是该综合征的一个晚期标志物。预测 AKI 风险的算法非常重要，但目前尚无研究将此类算法纳入电子健康记录以辅助临床护理。本研究旨在介绍此类算法的应用经验。
前瞻性观察性队列研究。
单中心城市三级医院的 2856 例住院成人患者，其在未来 24 小时内 AKI 的算法预测风险>15%。该算法还用于针对 100 例方便样本进行 16 项尿液和 6 项血液生物标志物检测。
出现 AKI 预警前的临床特征。
AKI 预警后 24 小时内发生 AKI（AKI）。
描述性统计和单变量关联分析。
入组时，AKI 的预测概率平均为 19.1%；18.9%的患者最终发生 AKI。该人群的结局普遍较差，发生 AKI 的患者住院死亡率为 29%，未发生 AKI 的患者为 14%（P<0.001）。收缩压<100mmHg（AKI 患者中占 28%，无 AKI 患者中占 18%）、心率>100 次/分（AKI 患者中占 32%，无 AKI 患者中占 24%）和血氧饱和度<92%（AKI 患者中占 15%，无 AKI 患者中占 6%）在发生 AKI 的患者中更为常见。在所有检测的生物标志物中，仅透明管型在尿液显微镜下（AKI 患者中占 72%，无 AKI 患者中占 25%）和尿素氮排泄分数（AKI 患者中占 20%[IQR，12%-36%]，无 AKI 患者中占 34%[IQR，25%-44%]）在发生 AKI 和未发生 AKI 的患者之间存在差异。
单中心研究、仅依赖血清肌酐水平诊断 AKI、行生物标志物检测的患者数量较少。
成功地将实时 AKI 风险模型整合到 EHR 中。
