Constructing a prognostic prediction model for conservative treatment of aortic dissection based on LASSO-Cox regression
WANG Xinyan
XIAO Ziya
LI Yong
LI Teng
GUO Yanji
Abstract：Objective To perform survival analysis in patients with aortic dissection who received conservative treatment,and to establish a simple and practical nomogram model for predicting patient survival rate.Methods Patients diagnosed with aortic dissection were enrolled as the research subjects in the Affiliated Hospital of Jining Medical University from Jan.2019 to Dec.2021,and their survival time was followed up.The Kaplan-Meier method was used to plot survival curves,Log-rank test was employed to compare survival rate differences among patients with different Stanford classifications.LASSO regression was applied to screen variables with non-zero coefficients,which were then included in multivariate Cox regression survival analysis.The stepwise backward regression method with the minimum Akaike Information Criterion(AIC)was adopted to determine the final model,and a nomogram of the prediction model was plotted.The C-index was used to evaluate the discrimination of the model,calibration curves were drawn to assess the calibration of the model,and decision curve analysis was performed to evaluate the clinical benefit of the model.Results A total of 128 patients with aortic dissection were included in this study,with an overall mortality rate of 45.31%(58/128).The overall survival rates at 3 months,6 months and 1 y after conservative treatment were 61.72%,59.38%and 54.69%,respectively.The mortality rate was significantly higher in patients with Stanford type A aortic dissection than that in patients with type B(62.07%vs.31.43%,P<0.001).Through LASSO regression,8 variables with non-zero coefficients were identified,including age,myoglobin(Mb),hemoglobin(Hb),platelets,fibrinogen(FIB),sinus involvement,false lumen range and complications.The variables finally included in the multivariate Cox regression model were age(HR=1.011,P=0.073),Hb(HR=0.983,P=0.090),FIB(HR=0.804,P=0.023),sinus involvement(HR=2.134,P=0.018),false lumen range(HR=1.495,P=0.036)and complications(HR=4.484,P<0.001).A nomogram prediction model for 3-month,6-month and 1-y survival rates in patients with aortic dissection after conservative treatment was further constructed.The C-index of the model was 0.824,calibration curves indicated good calibration of the model,and decision curve analysis demonstrated favorable clinical benefits of the model.Conclusion The nomogram prediction model constructed based on age,hemoglobin,fibrinogen,sinus involvement,false lumen range and complications has good predictive performance,and can be used to evaluate the 3-month,6-month and 1-y survival in patients with aortic dissection undergoing conservative treatment.
Keywords：aortic dissectionCox regression analysissurvival curvenomogramprognosis
Publication Date：2026-02-20
Online Publishing Date：2026-03-19(First online date of this platform, not the publication date of the document)
Pages：6( 178-183 )