Center for Comprehensive Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA; Department of Internal Medicine, Division of Pulmonary, Critical Care and Occupation Medicine, University of Iowa Roy J. and Lucille A. Carver College of Medicine, Iowa City, IA, USA.
Center for Comprehensive Access & Delivery Research & Evaluation (CADRE), Iowa City VA Health Care System, Iowa City, IA, USA; Department of Internal Medicine, Division of General Internal Medicine, University of Iowa Roy J. and Lucille A. Carver College of Medicine, Iowa City, IA, USA.
J Crit Care. 2018 Dec;48:237-242. doi: 10.1016/j.jcrc.2018.09.005. Epub 2018 Sep 6.
To evaluate the performance of an automated computerized ICU severity scoring derived from the APACHE III.
Within a retrospective cohort of patients admitted to Veterans Health Administration ICUs between 2009 and 2015, we created an automated illness severity score(modified APACHE or mAPACHE), that we extracted from the electronic health records, using the same scoring as the APACHE III excluding the Glasgow Coma Scale, urine output, arterial blood gas components of APACHE III. We assessed the mAPACHE discrimination by using the area under the curve(AUC), and calibration by using the Hosmer-Lemeshow test and calculating the difference between observed and expected mortality across equal-sized risk deciles for death.
The ICU and 30-day mortality was 5.07% of 7.82%, respectively (n = 490,955 patients). The AUC of mAPACHE for ICU and 30-day mortality was 0.771 and 0.786, respectively. The Hosmer-Lemeshow test was significant for both ICU and 30-day mortality (p < .001). The absolute difference between observed and expected mortality did not exceed ±1.53% across equal-sized deciles of risk for death. The AUC for ICU mortality was >0.7 in all admission diagnosis categories except in endocrine, respiratory, and sepsis. The AUC for 30-day mortality was >0.7 in every category.
mAPACHE has adequate performance to predict mortality.
评估源自急性生理学与慢性健康状况评分系统 III（APACHE III）的自动化计算机重症监护严重程度评分的性能。
在 2009 年至 2015 年间入住退伍军人健康管理局重症监护病房的患者回顾性队列中，我们创建了一个自动疾病严重程度评分（改良急性生理学评分或 mAPACHE），该评分是从电子病历中提取的，使用与 APACHE III 相同的评分，但不包括格拉斯哥昏迷量表、尿量、APACHE III 的动脉血气成分。我们通过曲线下面积（AUC）评估 mAPACHE 的区分度，并通过 Hosmer-Lemeshow 检验和计算死亡风险相等的十分位数之间观察到的和预期的死亡率之间的差异来评估校准。
重症监护病房和 30 天死亡率分别为 5.07%和 7.82%（n=490955 例患者）。mAPACHE 对重症监护病房和 30 天死亡率的 AUC 分别为 0.771 和 0.786。Hosmer-Lemeshow 检验对重症监护病房和 30 天死亡率均有显著意义（p<0.001）。在死亡风险相等的十分位数中，观察到的死亡率与预期死亡率之间的绝对差异不超过±1.53%。重症监护病房死亡率的 AUC 在除内分泌、呼吸和脓毒症以外的所有入院诊断类别中均大于 0.7。30 天死亡率的 AUC 在所有类别中均大于 0.7。
mAPACHE 具有预测死亡率的足够性能。
