基于Cox回归的Stanford B型主动脉夹层术后谵妄预测模型的构建

Construction of postoperative delirium prediction model for Stanford type B aortic dissection patients based on Cox regression

目的开发适用于Stanford B型主动脉夹层患者术后的谵妄预测模型,为早期识别该人群的术后谵妄提供依据。方法回顾性纳入2019年1月至2021年3月559例Stanford B型主动脉夹层术后患者,应用Lasso回归选出与术后谵妄相关的预测变量,随后采用多变量Cox回归分析进一步探索术后谵妄的预测因素并构建列线图预测模型。采用自助法重抽样1000次进行内部验证。结果术后谵妄的发生率为14.49%,基于5个预测因素[年龄≥60岁、晕厥、入住ICU、入院时中性粒细胞计数>6.3×10^(9)/L、术后估计肾小球滤过率<90 mL/(min·1.73 m^(2))]构建的列线图预测模型,C指数为0.774,在内部验证中为0.762。术后1 d、3 d和7 d的AUC分别为0.776、0.771和0.778,相应的校准图也显示了预测结果和实际观察之间的较好一致性。结论基于Cox回归分析以5个预测因素构建的列线图预测模型具有较好的风险预测价值,可帮助医护人员识别Stanford B型主动脉夹层患者术后谵妄风险,为临床工作中针对性地预防和干预术后谵妄提供借鉴。

Objective To develop and validate a nomogram for predicting postoperative delirium among patients with Stanford type B aortic dissection after surgery.Methods In this retrospective cohort study, 559 patients with Stanford type B aortic dissection who underwent treatment from January 2019 to March 2021 were included.Lasso regression method was applied to select useful predictive variables associated with postoperative delirium.A multivariable Cox regression model using a backward stepwise approach was conducted to further explore predictors for postoperative delirium.A nomogram based on these predictors was developed and an internal validation using a bootstrap technique with 1000 resamples was applied.Results The incidence of postoperative delirium was 14.49%. Age ≥60 years, presenting with syncope, neutrophil count >6.3×10^(9)/L at admission, ICU admission, and postoperative estimated glomerular filtration rate <90 mL/(min·1.73 m^(2)) were selected as predictors.The nomogram based on the 5 predictors demonstrated good discriminative ability with a C-index of 0.774 in the primary cohort and 0.762 in the internal bootstrap validation.The 1-day, 3-day and 7-day AUCs were 0.776 0.771 and 0.778 respectively. The calibration plots for 1-day, 3-day and 7-day postoperative delirium also demonstrated good agreement between the prediction results and actual observations.Conclusion This nomogram which has good predictive values thanks to 5 predictors, can help healthcare professionals identify the risk of postoperative delirium in patients with Stanford type B aortic dissection and provide reference for prevention and treatment of post-operative delirium in clinical work.