A型主动脉夹层术后急性心肌梗死相关危险因素的套索回归分析  

LASSO regression analysis of risk factors for postoperative acute myocardial infarction in type A aortic dissection patients

作　　者：张浩 贾博 乔环宇[2] 杨波[2] 杨璟[1] 黑飞龙 侯晓彤[3] 朱俊明[2] 刘永民[2] Zhang Hao;Jia Bo;Qiao Huanyu;Yang Bo;Yang Jing;Hei Feilong;Hou Xiaotong;Zhu Junming;Liu Yongmin(Department of Cardiac Surgery,Beijing Anzhen Hospital,Capital Medical University,Beijing 100029,China)

机构地区：[1]首都医科大学附属北京安贞医院体外循环与机械循环辅助科,北京100029 [2]首都医科大学附属北京安贞医院心脏外科中心,北京100029 [3]首都医科大学附属北京安贞医院心脏外科危重症中心,北京100029

出　　处：《中国体外循环杂志》2024年第3期210-217,共8页Chinese Journal of Extracorporeal Circulation

基　　金：北京市科委项目(Z191100006619094)。

摘　　要：目的探索A型主动脉夹层(TAAD)术后急性心肌梗死(PAMI)患者的危险因素并构建模型,以预测此类患者PAMI的风险。方法回顾性分析2018年1月至2022年10月,就诊于北京安贞医院并接受外科手术治疗TAAD患者的临床资料。以PAMI为终点,随机将这些患者的70%划分为训练集,剩余30%的患者划分为验证集。在训练集中应用套索(LASSO)回归探寻危险因素,构建模型,绘制列线图,并在验证集中验证模型的区分度和校准度。结果本研究共纳入1206例患者,83例(6.9%)患者发生终点事件。LASSO回归分析表明冠脉灌注不良、凝血酶原时间、纤维蛋白原降解产物、淀粉酶、手术时间、心肺转流时间对TAAD PAMI有较高的重要度。根据预测因子构建出的模型在训练集中区分度良好,一致性指数(C-index)为0.843,且模型的准确度较高。模型在验证集中的C-index为0.845。在预测的主要终点事件发生风险低于50%的患者中,校准曲线表明预测风险和观测风险基本一致。结论本研究形成的TAAD患者PAMI预测模型具有良好的区分能力,有助于临床医生早期干预PAMI的发生发展,进而提高TAAD患者临床预后。Objective To investigate the potential risk factors associated with postoperative acute myocardial infarction(PAMI)in individuals diagnosed with type A aortic dissection(TAAD).Additionally,the study aims to develop a predictive model to assess the likelihood of PAMI in these patients following surgical intervention.Methods A retrospective analysis was performed on the clinical data of patients diagnosed with TAAD who underwent surgical treatment at Beijing Anzhen Hospital between January 2018 and October 2022.The primary outcome of interest was PAMI.A random allocation resulted in 70%of the patients being assigned to a training set,while the remaining 30%were assigned to a validation set.LASSO regression was employed in the training set to identify potential risk factors,and subsequently,a model was constructed.A column chart was generated to visually represent the findings.The model’s discrimination and calibration were then assessed using the validation set.Results In this study of 1206 patients,6.9%experienced endpoint events.LASSO regression analysis identified several important factors for PAMI in TAAD,including coronary hypoperfusion,PT,FDP,amylase,surgery time and cardiopulmonary bypass time.The model based on these factors had good discrimination in the training set(C-index of 0.843)and high accuracy.In the validation set,the model had a C-index of 0.845.The calibration curve showed that the predicted and observed risks aligned for patients with a predicted risk below 50%.Conclusion The study’s predictive model for PAMI in TAAD is effective in helping doctors intervene early and improve patient prognosis.

关 键 词：A型主动脉夹层 术后急性心肌梗死 心肌保护 预测模型 

分 类 号：R654.2[医药卫生—外科学]