Construction and evaluation of a prognostic model for the risk of rupture of posterior communicating artery aneurysms
Objective To construct a predictive model for the risk of posterior communicating artery aneurysm rupture from a morphological perspective and to evaluate its effectiveness.Methods A retrospective analysis was conducted on the clinical data of 177 patients with posterior communicating artery aneurysms(192 cases)admitted to the Department of Neurosurgery,Linyi People's Hospital from March 2022 to December 2023.UKnow® intracranial aneurysm surgical planning software based on artificial intelligence algorithms was utilized,17 morphological parameters(length diameter,width,height,longest diameter,ratio of length to width,aneurysm volume,aneurysm neck area,aneurysm neck diameter,ratio of transverse diameter to aneurysm neck diameter,aneurysm angle,fluctuation index,size ratio,non-spherical index,aspect ratio,ratio of aneurysm volume to aneurysm neck area,transverse diameter,inflow angle)were accurately measured.According to whether the aneurysm ruptured or not,they were divided into ruptured group(108 cases)and unruptured group(84 cases).Univariate and multivariate logistic regression analyses were used to compare the clinical data and morphological characteristics of two groups of aneurysms,and construct a rupture risk prediction model.R language was used to draw a column chart of the prediction model and its receiver operating characteristic(ROC)curve.The decision curve analysis(DCA)method was used to evaluate the clinical efficacy of the prediction model,and calibration curve was used to evaluate the accuracy of the prediction model.Results The results of univariate logistic regression analysis showed that history of alcohol consumption,larger length diameter,height,longest diameter,ratio of length to width,ratio of transverse diameter to aneurysm neck diameter,inflow angle,aneurysm angle,fluctuation index,size ratio,aspect ratio,ratio of aneurysm volume to aneurysm neck area,as well as the presence of ascus in aneurysm body and more aneurysm body ascus were all positive influencing factors for aneurysm rupture(all P＜0.05).Multiple logistic regression analysis showed that increased ratio of length to width(OR=238.26,95％CI:6.48-8 761.90,P=0.003),increased inflow angle(OR=1.08,95％CI:1.04-1.11,P＜0.001),increased aspect ratio(OR=8.44,95％CI:1.17-61.19,P=0.035),and the presence of ascus in aneurysm body(OR=42.39,95％CI:8.68-206.92,P＜0.001)were independent risk factors for aneurysm rupture.The area under the ROC curve of the prediction model was 0.97.According to the DCA curve and calibration curve,the model had clinical practical benefits and good accuracy.Conclusion The rupture risk prediction model based on the ratio of length to width,inflow angle,aspect ratio and the presence of ascus in aneurysm body has good diagnostic efficacy,and its nomogram can evaluate the rupture risk of unruptured posterior communicating artery aneurysms more accurately and conveniently.
NETL
NSTL
万方数据
