Speiser Jaime L, Karvellas Constantine J, Shumilak Geoffery, Sligl Wendy I, Mirzanejad Yazdan, Gurka Dave, Kumar Aseem, Kumar Anand
1Department of Biostatistical Sciences, Division of Public Health Sciences, Wake Forest School of Medicine, Winston-Salem, NC USA.
2Department of Critical Care Medicine, University of Alberta, 1-40 Zeidler-Ledcor Building, Edmonton, Alberta T6G-2X8 Canada.
J Intensive Care. 2018 Oct 12;6:66. doi: 10.1186/s40560-018-0335-3. eCollection 2018.
Pneumonia complicated by septic shock is associated with significant morbidity and mortality. Classification and regression tree methodology is an intuitive method for predicting clinical outcomes using binary splits. We aimed to improve the prediction of in-hospital mortality in patients with pneumonia and septic shock using decision tree analysis.
Classification and regression tree models were applied to all patients with pneumonia-associated septic shock in the international, multicenter Cooperative Antimicrobial Therapy of Septic Shock database between 1996 and 2015. The association between clinical factors (time to appropriate antimicrobial therapy, severity of illness) and in-hospital mortality was evaluated. Accuracy in predicting clinical outcomes, sensitivity, specificity, and area under receiver operating curve of the final model was evaluated in training ( = 2111) and testing datasets ( = 2111).
The study cohort contained 4222 patients, and in-hospital mortality was 51%. The mean time from onset of shock to administration of appropriate antimicrobials was significantly higher for patients who died (17.2 h) compared to those who survived (5.0 h). In the training dataset ( = 2111), a tree model using Acute Physiology and Chronic Health Evaluation II Score, lactate, age, and time to appropriate antimicrobial therapy yielded accuracy of 73% and area under the receiver operating curve 0.75. The testing dataset ( = 2111) had accuracy of 69% and area under the receiver operating curve 0.72.
Overall mortality (51%) in patients with pneumonia complicated by septic shock is high. Increased time to administration of antimicrobial therapy, Acute Physiology and Chronic Health Evaluation II Score, serum lactate, and age were associated with increased in-hospital mortality. Classification and regression tree methodology offers a simple prognostic model with good performance in predicting in-hospital mortality.
肺炎并发感染性休克与显著的发病率和死亡率相关。分类回归树方法是一种使用二元分割预测临床结局的直观方法。我们旨在通过决策树分析改善对肺炎合并感染性休克患者院内死亡率的预测。
将分类回归树模型应用于1996年至2015年国际多中心感染性休克联合抗菌治疗数据库中所有肺炎相关性感染性休克患者。评估临床因素（开始适当抗菌治疗的时间、疾病严重程度）与院内死亡率之间的关联。在训练数据集（n = 2111）和测试数据集（n = 2111）中评估最终模型预测临床结局的准确性、敏感性、特异性和受试者工作特征曲线下面积。
研究队列包含4222例患者，院内死亡率为51%。死亡患者从休克发作到给予适当抗菌药物的平均时间（17.2小时）显著高于存活患者（5.0小时）。在训练数据集（n = 2111）中，使用急性生理与慢性健康状况评分系统II、乳酸、年龄和开始适当抗菌治疗时间的树模型准确率为７３％，受试者工作特征曲线下面积为0.75。测试数据集（n = 2111）的准确率为69％，受试者工作特征曲线下面积为0.72。
肺炎合并感染性休克患者的总体死亡率（51%）很高。抗菌治疗延迟、急性生理与慢性健康状况评分系统II、血清乳酸和年龄与院内死亡率增加相关。分类回归树方法提供了一个在预测院内死亡率方面具有良好性能的简单预后模型。
