Predicting reintervention after thoracic endovascular aortic repair of Stanford type B aortic dissection using machine learning

Abstract

Objectives: To construct models for predicting reintervention after thoracic endovascular aortic repair (TEVAR) of Stanford type B aortic dissection (TBAD).

Methods: A total of 192 TBAD patients who underwent TEVAR were included; 68 (35.4%) had indications for reintervention. Clinical characteristics, aorta characteristics on pre- and postoperative computed tomography angiography, and aorta characteristics on immediate postoperative aortic digital subtraction angiography were collected. The least absolute shrinkage and selection operator (LASSO) regression was applied to identify the risk factors for reintervention. Eight classifiers were used for modeling. The models were trained on 100 train-validation random splits with a ratio of 2:1. The performance was evaluated by the receiver operating characteristic curve.

Results: Seven predictors of reintervention were identified, including maximum false lumen diameter, aortic diameter measured at the level of approximately 15 mm distal to the left subclavian artery, aortic diameter measured at the level of the diaphragm, false lumen diameter measured at the level of the celiac artery, number of bare-metal and covered stents, number of bare-metal stents, and residual perfusion of the false lumen. Logistic regression (LR) yielded the highest performance, with an area under the curve of 0.802. A nomogram built for clinical use showed good calibration. The cutoff value for dividing patients into low- and high-risk subgroups was 0.413. Kaplan-Meier curves showed that the overall survival of high-risk patients was significantly shorter than that of low-risk patients (both p < 0.05).

Conclusion: Our nomogram could predict the reintervention after TEVAR in patients with TBAD, which may facilitate patient selection and surveillance strategies.

Key points: • Seven risk factors of reintervention after TEVAR of TBAD were identified for modeling. • Logistic regression performed best in predicting reintervention with an AUC of 0.802. • Patients with a high risk of reintervention had shorter OS than those with a low risk.

Keywords: Aortic dissection; Computer tomography angiography; Endovascular procedures; Mahine learning; Rik factors.