A simplified critical illness severity scoring system (CISSS): Development and internal validation
A simplified critical illness severity scoring system (CISSS): Development and internal validation
复制标题
DOI：
10.1016/j.jcrc.2020.09.029
复制
发表时间：
2021-02-01
影响因子：
3.7
通讯作者：
Sarrazin, Mary Vaughan
中科院分区：
文献类型：
--
作者：
Fortis, Spyridon;O'Shea, Amy M. J.;Sarrazin, Mary Vaughan
目的：创建一个简化的危重病严重程度评分系统，仅使用常用变量，对30天死亡率具有高预测准确性。材料和方法：这是一项回顾性队列研究，2010-2015年在117家退伍军人事务部（VA）医院的306个ICU入院。我们将队列随机分为训练数据集（75%）和验证数据集（25%）。我们使用年龄、合并症、心率、平均动脉压、体温、呼吸频率、红细胞压积、白色血细胞计数、肌酐、钠、葡萄糖、白蛋白、胆红素、碳酸氢盐、有创机械通气的使用以及是否手术入院创建了危重病严重程度评分系统（CISSS）。我们验证了CISSS预测30天死亡率的性能internal.Results：在排除31，743例再次入院后，我们将样本（n = 534，001）分为训练数据集（n = 400，613）和验证数据集（n = 133，388）。在训练数据集中，CISSS的曲线下面积（AUC）为0.847（95%CI = 0.845-0.850）。在验证数据集中，AUC为0.848（95%CI = 0.844-0.852），标准化死亡率比（SMR）为1.00（95%CI = 0.98-1.02），30天死亡率的Brier评分为0.058（95%CI = 0.057-0.059）。结论：CISSS具有很好的性能，只需要常用的变量，可以很容易地提取的电子健康档案。爱思唯尔公司出版。
Purpose: To create a simplified critical illness severity scoring system with high prediction accuracy for 30-day mortality using only commonly available variables.Materials and methods: This is a retrospective cohort study of ICU admissions 2010-2015 in 306 ICUs in 117 Veterans Affairs (VA) hospitals. We randomly divided our cohort into a training dataset (75%) and a validation dataset (25%). We created a critical illness severity scoring system (CISSS) using age, comorbidities, heart rate, mean arterial blood pressure, temperature, respiratory rate, hematocrit, white blood cell count, creatinine, sodium, glucose, albumin, bilirubin, bicarbonate, use of invasive mechanical ventilation, and whether the admission was surgical or not. We validated the performance of CISSS to predict 30-day mortality internally.Results: After excluding 31,743 re-admissions, we divided our sample (n = 534,001) into a training (n = 400,613) and a validation dataset ( n = 133,388). In the training dataset, the area under the curve (AUC) of CISSS was 0.847(95%CI = 0.845-0.850). In the validation dataset, the AUC was 0.848 (95%CI = 0.844-0.852), the standardized mortality ratio (SMR) was 1.00 (95%CI = 0.98-1.02), and Brier's score for 30-day mortality was 0.058 (95%CI = 0.057-0.059). CISSS calibration was acceptable.Conclusions: CISSS has very good performance and requires only commonly used variables that can be easily extracted by electronic health records. Published by Elsevier Inc.