南方医科大学学报

南方医科大学学报 ›› 2024, Vol. 44 ›› Issue (3): 491-498.doi: 10.12122/j.issn.1673-4254.2024.03.10

• • 上一篇    下一篇

VA-ECMO患者院内死亡风险预测模型的构建及验证：一项多中心、回顾性、病例对照研究

戈 悦，李建伟，梁宏开，侯六生，左六二，陈 珍，卢剑海，赵 新，梁静漪，彭 岚，包静娜，段佳欣，刘 俐，毛可晴，曾振华，胡鸿彬，陈仲清   

  1. 南方医科大学南方医院重症医学科，护理学院，广东 广州 510515，中山市人民医院重症医学科，广东 中山 528403；南方医科大学顺德医院//顺德第一人民医院重症医学科，广东 佛山 528308
  • 出版日期:2024-03-20 发布日期:2024-04-03

Construction and validation of an in-hospital mortality risk prediction model for patients receiving VA-ECMO: a retrospective multi-center case-control study

GE Yue, LI Jianwei, LIANG Hongkai, HOU Liusheng, ZUO Liuer, CHEN Zhen, LU Jianhai, ZHAO Xin, LIANG Jingyi, PENG Lan, BAO Jingna, DUAN Jiaxin, LIU Li, MAO Keqing, ZENG Zhenhua, HU Hongbin, CHEN Zhongqing   

  1. Department of Critical Care Medicine, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China; School of Nursing, Southern Medical University, Guangzhou 510515, China; Department of Critical Care Medicine, Zhongshan People's Hospital, Zhongshan 528403, China; Department of Intensive Care Unit, Shunde Hospital Affiliated to Southern Medical University (Shunde First People's Hospital), Foshan 528308, China
  • Online:2024-03-20 Published:2024-04-03

RichHTML

9

PDF

49

摘要： 目的 分析静脉-动脉体外膜肺氧合技术（VA-ECMO）患者死亡危险因素，构建并验证VA-ECMO患者院内死亡风险预测模型。方法 采用便利抽样，选取2015年1月~2022年1月广东省三家综合医院ICU的302例VA-ECMO患者作为研究对象，随机分为建模组201例，验证组101例。运用单因素及多因素Logistic回归分析VA-ECMO患者死亡危险因素，构建VA-ECMO患者死亡风险预测模型并以列线图形式呈现。使用受试者工作特征曲线（ROC曲线）、校准曲线和临床决策曲线评价模型区分度、一致性及临床有效性。结果 预测VA-ECMO患者院内死亡风险的最终模型包括了高血压（OR=3.694，95%CI 1.582-8.621）、连续性肾脏替代治疗（OR=9.661，95%CI 4.103-22.745）、钠离子（OR=1.048，95%CI 1.003-1.095）、血红蛋白（OR=0.987，95%CI 0.977-0.998）。建模组预测模型的受试者工作特征曲线下面积 AUC=0.829（95%CI 0.770-0.889），高于4个单独危险因素（AUC<0.800）、APACHE II评分[AUC=0.777（95%CI 0.714-0.840）]、SOFA评分的[AUC=0.721（95%CI 0.647-0.796）]。内部验证结果显示模型的受试者工作特征曲线下面积AUC为0.774（95%CI 0.679-0.869），拟合优度检验结果χ2=4.629，P>0.05。结论 构建的VA-ECMO患者院内死亡风险预测模型区分度、校准度及临床有效性均较好，优于常用疾病严重程度评分系统，对评估重症患者疾病的严重程度及预后的风险水平有重要意义。

关键词: 静脉-动脉体外膜肺氧合；死亡率；危险因素；风险预测模型

Abstract: Objective To investigate the risk factors of in-hospital mortality and establish a risk prediction model for patients receiving venoarterial extracorporeal membrane oxygenation (VA-ECMO). Methods We retrospectively collected the data of 302 patients receiving VA-ECMO in ICU of 3 hospitals in Guangdong Province between January, 2015 and January, 2022 using a convenience sampling method. The patients were divided into a derivation cohort (201 cases) and a validation cohort (101 cases). Univariate and multivariate logistic regression analyses were used to analyze the risk factors for in-hospital death of these patients, based on which a risk prediction model was established in the form of a nomogram. The receiver operator characteristic (ROC) curve, calibration curve and clinical decision curve were used to evaluate the discrimination ability, calibration and clinical validity of this model. Results The in-hospital mortality risk prediction model was established based the risk factors including hypertension (OR=3.694, 95% CI: 1.582-8.621), continuous renal replacement therapy (OR=9.661, 95%CI: 4.103-22.745), elevated Na2 + level (OR=1.048,95% CI: 1.003-1.095) and increased hemoglobin level (OR=0.987, 95% CI: 0.977-0.998). In the derivation cohort, the area under the ROC curve (AUC) of this model was 0.829 (95% CI: 0.770-0.889), greater than those of the 4 single factors (all AUC<0.800), APACHE II Score (AUC=0.777, 95% CI: 0.714-0.840) and the SOFA Score (AUC=0.721, 95% CI: 0.647-0.796). The results of internal validation showed that the AUC of the model was 0.774 (95% CI: 0.679-0.869), and the goodness of fit test showed a good fitting of this model (χ2=4.629, P>0.05). Conclusion The risk prediction model for in-hospital mortality of patients on VA-ECMO has good differentiation, calibration and clinical effectiveness and outperforms the commonly used disease severity scoring system, and thus can be used for assessing disease severity and prognostic risk level in critically ill patients.

Key words: venoarterial extracorporeal membrane oxygenation; mortality; risk factors; risk pre-diction model