Automated CTA-Based Morphometric Analysis for Predicting Primary Entry Tear Location in Stanford Type A Aortic Dissection

The study developed and externally validated a model to distinguish between primary entry tears in the ascending aorta and aortic arch in Stanford type A aortic dissection using automatically quantified aortic morphology. The research included a development cohort of 680 patients (529 with ascending aorta entry tears and 151 with arch entry tears) and an external validation cohort of 89 patients (47 with ascending aorta entry tears and 42 with arch entry tears). A model based on five morphological features achieved an area under the ROC curve of 0.862 in internal validation with sensitivity of 92.7% and specificity of 66.5%. In external validation, the model achieved an area under the ROC curve of 0.785 with sensitivity of 97.6% and specificity of 17.0%. The researchers concluded that the model distinguishes between ascending aorta and arch entry tears, but further prospective multicenter validation is required before clinical use.