Augmenting Prediction of Intracranial Aneurysms’ Risk Status Using Velocity-Informatics: Initial Experience

• Published in: Journal of cardiovascular translational research Vol. 16; no. 5; pp. 1153 - 1165
• Main Authors: Jiang, J., Rezaeitaleshmahalleh, M., Lyu, Z., Mu, Nan, Ahmed, A. S., MD, C. M. Strother, Gemmete, J. J., Pandey, A. S.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.10.2023
• Subjects: Aneurysm, Ruptured; Biomedical Engineering and Bioengineering; Biomedicine; Cardiology; Computer Simulation; Hemodynamics; Human Genetics; Humans; Informatics; Intracranial Aneurysm - diagnostic imaging; Medicine; Medicine & Public Health; Original Article; Intracranial Aneurysm; Velocity-informatics; Rupture Risk Prediction; Hemodynamics; Machine Learning
• ISSN: 1937-5387; 1937-5395; 1937-5395
• DOI: 10.1007/s12265-023-10394-6

Our primary goal here is to demonstrate that innovative analytics of aneurismal velocities, named velocity-informatics, enhances intracranial aneurysm (IA) rupture status prediction. 3D computer models were generated using imaging data from 112 subjects harboring anterior IAs (4–25 mm; 44 ruptured and 68 unruptured). Computational fluid dynamics simulations and geometrical analyses were performed. Then, computed 3D velocity vector fields within the IA dome were processed for velocity-informatics. Four machine learning methods (support vector machine, random forest, generalized linear model, and GLM with Lasso or elastic net regularization) were employed to assess the merits of the proposed velocity-informatics. All 4 ML methods consistently showed that, with velocity-informatics metrics, the area under the curve and prediction accuracy both improved by approximately 0.03. Overall, with velocity-informatics, the support vector machine’s prediction was most promising: an AUC of 0.86 and total accuracy of 77%, with 60% and 88% of ruptured and unruptured IAs being correctly identified, respectively.