Table_2_A machine learning approach for predicting descending thoracic aortic diameter.XLSX

BackgroundTo establish models for predicting descending thoracic aortic diameters and provide evidence for selecting the size of the stent graft for TBAD patients.
MethodsA total of 200 candidates without severe deformation of aorta were included. CTA information was collected and 3D reconstructed. In the reconstructed CTA, a total of 12 cross-sections of peripheral vessels were made perpendicular to the axis of flow of the aorta. Parameters of the cross sections and basic clinical characteristics were used for prediction. The data was randomly split into the training set and the test set in an 8:2 ratio. To fully describe diameters of descending thoracic aorta, three predicted points were set based quadrisection, and a total of 12 models at three predicted points were established using four algorithms included linear regression (LR), support vector machine (SVM), Extra-Tree regression (ETR) and random forest regression (RFR). The performance of models was evaluated by mean square error (MSE) of the prediction value, and the ranking of feature importance was given by Shapley value. After modeling, prognosis of five TEVAR cases and stent oversizing were compared.
ResultsWe identified a series of parameters which affect the diameter of descending thoracic aorta, including age, hypertension, the area of proximal edge of superior mesenteric artery, etc. Among four predictive models, all the MSEs of SVM models at three different predicted position were less than 2 mm2, with approximately 90% predicted diameters error less than 2 mm in the test sets. In patients with dSINE, stent oversizing was about 3 mm, while only 1 mm in patients without complications.
ConclusionThe predictive models established by machine learning revealed the relationship between basic characteristics and diameters of different segment of descending aorta, which help to provide evidence for selecting the matching distal size of the stent for TBAD patients, thereby reducing the incidence of TEVAR complications.

**背景**：旨在构建降胸主动脉直径预测模型，为胸主动脉夹层（Thoracic Aortic Dissection, TBAD）患者的支架移植物尺寸选择提供依据。
**方法**：本研究共纳入200例无主动脉严重变形的受试者，收集其计算机断层血管造影（Computed Tomographic Angiography, CTA）影像并进行三维重建。于重建后的CTA影像中，沿主动脉血流轴垂直方向共截取12处横截面，以横截面参数及基础临床特征作为预测变量。将数据按8:2的比例随机划分为训练集与测试集。为全面表征降胸主动脉直径，基于四分法设置3个预测点位，采用线性回归（Linear Regression, LR）、支持向量机（Support Vector Machine, SVM）、极端树回归（Extra-Tree Regression, ETR）及随机森林回归（Random Forest Regression, RFR）共4种算法，在3个预测点位分别构建12个预测模型。以预测值的均方误差（Mean Square Error, MSE）评估模型性能，通过夏普利值（Shapley Value）获取特征重要性排序。建模完成后，对比5例胸主动脉腔内修复术（Thoracic Endovascular Aortic Repair, TEVAR）病例的预后情况与支架过尺寸参数。
**结果**：本研究筛选出一系列影响降胸主动脉直径的参数，包括年龄、高血压、肠系膜上动脉近缘面积等。在4类预测模型中，3个不同预测点位的支持向量机模型均方误差均小于2 mm²，测试集内约90%的预测直径误差小于2 mm。合并支架移植物诱导远端新发破口（distal Stent Graft-induced New Entry, dSINE）的患者中，支架过尺寸约为3 mm，无并发症患者的支架过尺寸仅为1 mm。
**结论**：本研究构建的机器学习预测模型揭示了基础临床特征与降胸主动脉各节段直径间的关联，可为TBAD患者匹配远端支架尺寸提供依据，从而降低TEVAR并发症的发生率。