Engerström Lars, Nolin Thomas, Mårdh Caroline, Sjöberg Folke, Karlström Göran, Fredrikson Mats, Walther Sten M
Department of Anaesthesiology and Intensive Care and Department of Medical and Health Sciences, Linköping University, Norrköping, Sweden.
Department of Thoracic and Vascular Surgery and Department of Medical and Health Sciences, Linköping University, Linköping, Sweden.
Crit Care Med. 2017 Dec;45(12):2006-2013. doi: 10.1097/CCM.0000000000002706.
The Simplified Acute Physiology 3 outcome prediction model has a narrow time window for recording physiologic measurements. Our objective was to examine the prevalence and impact of missing physiologic data on the Simplified Acute Physiology 3 model's performance.
Retrospective analysis of prospectively collected data.
Sixty-three ICUs in the Swedish Intensive Care Registry.
Patients admitted during 2011-2014 (n = 107,310).
None.
Model performance was analyzed using the area under the receiver operating curve, scaled Brier's score, and standardized mortality rate. We used a recalibrated Simplified Acute Physiology 3 model and examined model performance in the original dataset and in a dataset of complete records where missing data were generated (simulated dataset). One or more data were missing in 40.9% of the admissions, more common in survivors and low-risk admissions than in nonsurvivors and high-risk admissions. Discrimination did not decrease with one to two missing variables, but accuracy was highest with no missing data. Calibration was best in the original dataset with a mix of full records and records with some missing values (area under the receiver operating curve was 0.85, scaled Brier 27%, and standardized mortality rate 0.99). With zero, one, and two data missing, the scaled Brier was 31%, 26%, and 21%; area under the receiver operating curve was 0.84, 0.87, and 0.89; and standardized mortality rate was 0.92, 1.05 and 1.10, respectively. Datasets where the missing data were simulated for oxygenation or oxygenation and hydrogen ion concentration together performed worse than datasets with these data originally missing.
There is a coupling between missing physiologic data, admission type, low risk, and survival. Increased loss of physiologic data reduced model performance and will deflate mortality risk, resulting in falsely high standardized mortality rates.
简化急性生理学3（Simplified Acute Physiology 3，SAPS 3）结局预测模型记录生理测量值的时间窗较窄。我们的目的是研究生理数据缺失在SAPS 3模型性能方面的发生率及影响。
对前瞻性收集的数据进行回顾性分析。
瑞典重症监护登记处的63个重症监护病房（ICU）。
2011 - 2014年期间收治的患者（n = 107,310）。
无。
使用受试者工作特征曲线下面积、校正的Brier评分和标准化死亡率分析模型性能。我们使用了重新校准的SAPS 3模型，并在原始数据集以及生成了缺失数据的完整记录数据集（模拟数据集）中检验模型性能。40.9%的入院患者存在一项或多项数据缺失，在幸存者和低风险入院患者中比在非幸存者和高风险入院患者中更常见。存在一至两个缺失变量时，辨别力并未降低，但无缺失数据时准确性最高。校准在原始数据集中表现最佳，该数据集包含完整记录和一些有缺失值的记录（受试者工作特征曲线下面积为0.85，校正的Brier评分为27%，标准化死亡率为0.99）。当缺失零项、一项和两项数据时，校正的Brier评分分别为31%、26%和21%；受试者工作特征曲线下面积分别为0.84、0.87和0.89；标准化死亡率分别为0.92、1.05和1.10。模拟氧合或氧合及氢离子浓度缺失数据的数据集比这些数据原本就缺失的数据集表现更差。
生理数据缺失、入院类型、低风险和生存之间存在关联。生理数据缺失增加会降低模型性能，并会低估死亡风险，导致标准化死亡率虚高。
