Aortic dissection (AD) remains one of the most critical vascular conditions, characterized by the creation of a false lumen (FL) within the aortic wall. The progression of the disease is heavily influenced by the hemodynamic forces passing through the entry tear. This study investigates the feasibility of using machine learning (ML) to predict the volumetric expansion of the false lumen based on morphological and clinical parameters: entry tear size, blood pressure status, and smoking history. The dataset consists of 30 patients diagnosed with Type A Aortic Dissection. Morphological data regarding the entry tear area (cm2) and total false lumen volume (cm3) were analyzed alongside categorical clinical data. A Multivariate Linear Regression model was implemented to quantify the influence of these variables on FL volume. Preliminary results indicate a strong positive correlation (R2=0.78) between the entry tear size and FL volume. Specifically, the model identified that the presence of hypertension combined with smoking status acts as a significant multiplier, leading to an average volume increase of 22% compared to non-smoking, normotensive patients with similar tear sizes. The study demonstrates that ML algorithms can provide rapid, non-invasive estimates of FL progression, aiding clinicians in risk stratification and intervention planning. This computational approach offers a scalable framework for personalized vascular medicine, bridging the gap between raw imaging data and clinical decision-making.