AUTHOR=Wang Yonggang , Zhou Min , Ding Yong , Li Xu , Zhou Zhenyu , Shi Zhenyu , Fu Weiguo 

TITLE=Development and Comparison of Multimodal Models for Preoperative Prediction of Outcomes After Endovascular Aneurysm Repair

JOURNAL=Frontiers in Cardiovascular Medicine

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/cardiovascular-medicine/articles/10.3389/fcvm.2022.870132

DOI=10.3389/fcvm.2022.870132

ISSN=2297-055X

ABSTRACT=Objective: To develop and compare multi-modal models for predicting outcomes after endovascular abdominal aortic aneurysm repair (EVAR) based on morphological, deep learning (DL) and radiomics features.
Methods: We retrospectively reviewed 979 patients (2010.1-2019.12) with infra-renal AAAs who underwent elective EVAR procedures. 486 patients (2010.1-2015.12) were used for morphological feature model development and optimization. Univariable and multivariable analyses were conducted to determine significant morphological features of EVAR-related severe adverse events (SAEs) and to build morphological feature model based on different machine learning algorithms. Subsequently, to develop the morphological feature model more easily and better comparable with other modal models, 340 patients of AAA with intraluminal thrombosis (ILT) were used for automatic segmentation of ILT based on Deep Convolutional Neural Networks (DCNNs). 493 patients (2016.1-2019.12) were used for multi-modal models (optimized morphological feature, DL and radiomics models) development and comparison. 80% of patients were classified as the training set and 20% of patients were classified as the test set. The area under the curve was used to evaluate the predictive abilities of different modal models.
Results: The mean age of the patients was 69.9 years, the mean follow-up was 54.0 months, and 307 patients (31.4%) patients experienced SAEs. Statistical analysis revealed that short neck, angulated neck, conical neck, ILT, ILT percentage ≥ 51.6%, luminal calcification, double iliac sign, and common iliac artery index ≥ 1.255 were associated with SAEs. The morphological feature model based on Support Vector Machine had better predictive performance with AUC 0.76, accuracy 0.76 and F1 score 0.82. Our DCNNs model achieved mean intersection over union score of more than 90.78% for segmentation of ILT and AAA aortic lumen. Multi-modal models result showed that the radiomics model based on Logistics Regression had better predictive performance (AUC 0.93, accuracy 0.86, F1 score 0.91), while the optimized morphological feature model (AUC 0.62, accuracy 0.69, F1 score 0.81) and the DL model (AUC 0.82, accuracy 0.85, F1 score 0.89).
Conclusion: The radiomics model has better predictive performance for patient status after EVAR. The morphological feature model and DL model have their own advantages could also be used to predict outcomes after EVAR.