Lyu Zonghan, Rezaeitaleshmahalleh Mostafa, Mu Nan, Jiang Jingfeng
Biomedical Engineering, Michigan Technological University, Houghton, MI, United States of America.
Joint Center for Biocomputing and Digital Health, Health Research Institute and Institute of Computing and Cybernetics, Michigan Technological University, Houghton, MI, United States of America.
Biomed Phys Eng Express. 2025 Apr 24;11(3). doi: 10.1088/2057-1976/adcc34.
. Selecting patients with high-risk intracranial aneurysms (IAs) is of clinical importance. Recent work in machine learning-based (ML) predictive modeling has demonstrated that lesion-specific hemodynamics within IAs can be combined with other information to provide critical insights for assessing rupture risk. However, how the adoption of blood rheology models (i.e., Newtonian and Non-Newtonian blood models) may influence ML-based predictive modeling of IA rupture risk has not been investigated.In this study, we conducted transient CFD simulations using Newtonian and non-Newtonian rheology (Carreau-Yasuda [CY]) models on a large cohort of 'patient-specific' IA geometries (>100) under pulsatile flow conditions to investigate how each blood model may affect the characterization of the IAs' rupture status. Key hemodynamic parameters were analyzed and compared, including wall shear stress (WSS) and vortex-based parameters. In addition, velocity-informatics features extracted from the flow velocity were utilized to train a support vector machine (SVM) model for rupture status prediction.Our findings demonstrate significant differences between the two models (i.e., Newtonian versus CY) regarding the WSS-related metrics. In contrast, the parameters derived from the flow vortices and velocity informatics agree. Similar to other studies, using a non-Newtonian CY model results in lower peak WSS and higher oscillatory shear index (OSI) values. Furthermore, integrating velocity informatics and machine learning achieved robust performance for both blood models (area under the curve [AUC] ˃0.85).Our preliminary study found that ML-based rupture status prediction derived from velocity informatics and geometrical parameters yielded comparable results despite differences observed in aneurysmal hemodynamics using two blood rheology models (i.e., Newtonian versus CY).
选择高危颅内动脉瘤（IA）患者具有临床重要性。基于机器学习（ML）的预测建模的最新研究表明，IA内病变特异性血流动力学可与其他信息相结合，为评估破裂风险提供关键见解。然而，采用血液流变学模型（即牛顿和非牛顿血液模型）如何影响基于ML的IA破裂风险预测建模尚未得到研究。在本研究中，我们在脉动流条件下，使用牛顿和非牛顿流变学（Carreau-Yasuda [CY]）模型对大量“患者特异性”IA几何模型（>100个）进行了瞬态计算流体动力学（CFD）模拟，以研究每种血液模型如何影响IA破裂状态的特征。分析并比较了关键血流动力学参数，包括壁面剪应力（WSS）和基于涡旋的参数。此外，利用从流速中提取的速度信息学特征训练支持向量机（SVM）模型用于破裂状态预测。我们的研究结果表明，在与WSS相关的指标方面，两种模型（即牛顿模型与CY模型）存在显著差异。相比之下，从流动涡旋和速度信息学得出的参数是一致的。与其他研究类似，使用非牛顿CY模型会导致较低的峰值WSS和较高的振荡剪切指数（OSI）值。此外，将速度信息学与机器学习相结合，两种血液模型均实现了稳健的性能（曲线下面积[AUC]>0.85）。我们的初步研究发现，尽管使用两种血液流变学模型（即牛顿模型与CY模型）观察到动脉瘤血流动力学存在差异，但基于速度信息学和几何参数得出的基于ML的破裂状态预测结果相当。
