Department of National Defense, Royal Canadian Medical Services, 1745 Alta Vista Drive, Ottawa, K1A 0K6 Ontario Canada ; London Health Sciences Center, Divisions of Critical Care and Robarts Research Institute, Western University, 800 Commissioner's Rd E., London, Ontario N6A 5W9 Canada ; Harvard School of Public Health, Harvard University, 677 Huntington Ave., Boston, 02115 MA USA.
London Health Sciences Center, Divisions of Critical Care and Robarts Research Institute, Western University, 800 Commissioner's Rd E., London, Ontario N6A 5W9 Canada.
J Intensive Care. 2016 Feb 29;4:16. doi: 10.1186/s40560-016-0143-6. eCollection 2016.
Intensive care unit (ICU) scoring systems or prediction models evolved to meet the desire of clinical and administrative leaders to assess the quality of care provided by their ICUs. The Critical Care Information System (CCIS) is province-wide data information for all Ontario, Canada level 3 and level 2 ICUs collected for this purpose. With the dataset, we developed a multivariable logistic regression ICU mortality prediction model during the first 24 h of ICU admission utilizing the explanatory variables including the two validated scores, Multiple Organs Dysfunctional Score (MODS) and Nine Equivalents Nursing Manpower Use Score (NEMS) followed by the variables age, sex, readmission to the ICU during the same hospital stay, admission diagnosis, source of admission, and the modified Charlson Co-morbidity Index (CCI) collected through the hospital health records.
This study is a single-center retrospective cohort review of 8822 records from the Critical Care Trauma Centre (CCTC) and Medical-Surgical Intensive Care Unit (MSICU) of London Health Sciences Centre (LHSC), Ontario, Canada between 1 Jan 2009 to 30 Nov 2012. Multivariable logistic regression on training dataset (n = 4321) was used to develop the model and validate by bootstrapping method on the testing dataset (n = 4501). Discrimination, calibration, and overall model performance were also assessed.
The predictors significantly associated with ICU mortality included: age (p < 0.001), source of admission (p < 0.0001), ICU admitting diagnosis (p < 0.0001), MODS (p < 0.0001), and NEMS (p < 0.0001). The variables sex and modified CCI were not significantly associated with ICU mortality. The training dataset for the developed model has good discriminating ability between patients with high risk and those with low risk of mortality (c-statistic 0.787). The Hosmer and Lemeshow goodness-of-fit test has a strong correlation between the observed and expected ICU mortality (χ (2) = 5.48; p > 0.31). The overall optimism of the estimation between the training and testing data set ΔAUC = 0.003, indicating a stable prediction model.
This study demonstrates that CCIS data available after the first 24 h of ICU admission at LHSC can be used to create a robust mortality prediction model with acceptable fit statistic and internal validity for valid benchmarking and monitoring ICU performance.
重症监护病房（ICU）评分系统或预测模型的发展是为了满足临床和管理领导者评估 ICU 提供的护理质量的愿望。Critical Care Information System（CCIS）是为安大略省所有 3 级和 2 级 ICU 收集的全省数据信息。有了这个数据集，我们利用包括两个经过验证的评分在内的解释变量，即多器官功能障碍评分（MODS）和 9 个等效护理人力使用评分（NEMS），在 ICU 入住后的前 24 小时内开发了一个多变量逻辑回归 ICU 死亡率预测模型，随后是年龄、性别、同一住院期间再次入住 ICU、入院诊断、入院来源和通过医院健康记录收集的改良 Charlson 合并症指数（CCI）等变量。
这项研究是对安大略省伦敦健康科学中心（LHSC）重症监护创伤中心（CCTC）和内科-外科重症监护病房（MSICU）的 8822 份记录进行的单中心回顾性队列研究，这些记录的时间为 2009 年 1 月 1 日至 2012 年 11 月 30 日。对训练数据集（n=4321）进行多变量逻辑回归，使用bootstrap 方法对测试数据集（n=4501）进行验证。还评估了区分度、校准度和整体模型性能。
与 ICU 死亡率显著相关的预测因子包括：年龄（p<0.001）、入院来源（p<0.0001）、ICU 入院诊断（p<0.0001）、MODS（p<0.0001）和 NEMS（p<0.0001）。性别和改良 CCI 这两个变量与 ICU 死亡率没有显著关联。该模型的训练数据集在高风险和低风险死亡率患者之间具有良好的区分能力（c 统计量为 0.787）。Hosmer 和 Lemeshow 拟合优度检验显示观察到的 ICU 死亡率与预期死亡率之间具有很强的相关性（χ²=5.48；p>0.31）。训练数据集和测试数据集之间的整体预测值差异为 AUCΔ=0.003，表明预测模型稳定。
这项研究表明，LHSC ICU 入住后的前 24 小时内可用的 CCIS 数据可用于创建一个稳健的死亡率预测模型，该模型具有可接受的拟合统计量和内部有效性，可用于有效的基准测试和 ICU 绩效监测。
