医学
列线图
逐步回归
肾脏替代疗法
急性肾损伤
败血症
沙发评分
回顾性队列研究
接收机工作特性
内科学
比例危险模型
自举(财务)
外科
金融经济学
经济
作者
Zhenghai Bai,Guo Xiao-qing,Rong Dong,Na Lei,Hong Pei,Hai Wang
标识
DOI:10.1016/j.amjms.2020.11.028
摘要
Background Acute kidney injury (AKI) is a severe and common complication in critically ill patients and is associated with increased morbidity and mortality. At present, there is not a tool to predict the prognosis of critically ill patients with AKI and treated with continuous renal replacement therapy (CRRT). Methods A retrospective cohort study was to construct a prediction model for the 28-day mortality of patients with AKI and treated with CRRT. From January 2009 to September 2016, A total of 846 cases were included in our study. Results A total of five variables selected by multi-factor Cox regression analysis were used to constructed three predictive models and adopted bootstrapping for internal validation. Finally, we get five sets of models (three sets of construction models and two sets of internal verification models) with similar predictive value. The stepwise model, which including four variables (CCI score, Alb, Phosphate (24h) and SOFA score), was the simplest model, so we chose it as our final predictive model and constructed a nomogram based on it. The area under the ROC curve (AUC) of the stepwise model and the stepwise bootstrap model (BS stepwise) were respectively 0.78(0.75,0.82) and 0.78 (0.75,0.82). The AUC of the stepwise model and the BS stepwise in patients with sepsis were 0.77 (0.73,0.81) and 0.77 (0.73,0.81). The AUC of the stepwise model and the BS stepwise in patients without sepsis were 0.83 (0.78,0.89) and 0.83 (0.78,0.89). Conclusions We developed a four-marker-based prognostic tool that could effectively predict each individual's 28-day mortality for patients with AKI and treated with CRRT.
科研通智能强力驱动
Strongly Powered by AbleSci AI