Department of Medical Informatics, Academic Medical Center, University of Amsterdam, Amsterdam, 1100 DE, The Netherlands.
J Crit Care. 2011 Feb;26(1):105.e11-8. doi: 10.1016/j.jcrc.2010.07.007. Epub 2010 Sep 24.
The aim of this study was to validate and compare the performance of the Acute Physiology and Chronic Health Evaluation (APACHE) IV in the Dutch intensive care unit (ICU) population to the APACHE II and Simplified Acute Physiology Score (SAPS) II.
This is a prospective study based on data from a national quality registry between 2006 and 2009 from 59 Dutch ICUs. The validation set consisted of 62,737 patients; the 3 models were compared using 44,112 patients. Measures of discrimination, accuracy, and calibration (area under the receiver operating characteristic curve (AUC), Brier score, R(2), and Ĉ-statistic) were calculated using bootstrapping. In addition, the standardized mortality ratios were calculated.
The original APACHE IV showed good discrimination and accuracy (AUC = 0.87, Brier score = 0.10, R(2) = 0.29) but poor calibration (Ĉ-statistic = 822.67). Customization significantly improved the performance of the APACHE IV. The overall discrimination and accuracy of the customized APACHE IV were statistically better, and the overall Ĉ-statistic was inferior to those of the customized APACHE II and SAPS II, but these differences were small in perspective of clinical use.
The 3 models have comparable capabilities for benchmarking purposes after customization. Main advantage of APACHE IV is the large number of diagnoses that enable subgroup analysis. The APACHE IV coronary artery bypass grafting (CABG) model has a good performance in the Dutch ICU population and can be used to complement the 3 models.
本研究旨在验证并比较急性生理学与慢性健康状况评分系统第四版（APACHE IV）在荷兰重症监护病房（ICU）人群中的表现与急性生理学与慢性健康状况评分系统第二版（APACHE II）和简化急性生理学评分（SAPS）II 的表现。
这是一项基于 2006 年至 2009 年全国质量登记处数据的前瞻性研究，来自 59 家荷兰 ICU。验证集由 62737 例患者组成；使用 44112 例患者比较了这 3 种模型。使用自举法计算了区分度、准确性和校准度（受试者工作特征曲线下面积（AUC）、Brier 评分、R²和 Ĉ 统计量）。此外，还计算了标准化死亡率比。
原始的 APACHE IV 表现出良好的区分度和准确性（AUC=0.87，Brier 评分=0.10，R²=0.29），但校准效果较差（Ĉ 统计量=822.67）。定制化显著改善了 APACHE IV 的性能。定制后的 APACHE IV 的整体区分度和准确性在统计学上更好，整体 Ĉ 统计量低于定制后的 APACHE II 和 SAPS II，但从临床应用的角度来看，这些差异很小。
在定制后，这 3 种模型在基准比较方面具有相当的能力。APACHE IV 的主要优势在于它包含大量诊断，可以进行亚组分析。APACHE IV 冠状动脉旁路移植术（CABG）模型在荷兰 ICU 人群中表现良好，可以与这 3 种模型互补使用。
