Bioengineering Department, Volgenau School of Engineering, George Mason University, 4400 University Drive, Fairfax, VA, 22030, USA.
Computational Health Informatics, Leibniz University, Hannover, Germany.
Int J Comput Assist Radiol Surg. 2020 Jan;15(1):141-150. doi: 10.1007/s11548-019-02065-2. Epub 2019 Sep 4.
Incidental aneurysms pose a challenge to physicians who need to decide whether or not to treat them. A statistical model could potentially support such treatment decisions. The aim of this study was to compare a previously developed aneurysm rupture logistic regression probability model (LRM) to other machine learning (ML) classifiers for discrimination of aneurysm rupture status.
Hemodynamic, morphological, and patient-related information of 1631 cerebral aneurysms characterized by computational fluid dynamics simulations were used to train support vector machines (SVMs) with linear and RBF kernel (RBF-SVM), k-nearest neighbors (kNN), decision tree, random forest, and multilayer perceptron (MLP) neural network classifiers for predicting the aneurysm rupture status. The classifiers' accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were evaluated and compared to the LRM using 249 test cases obtained from two external cohorts. Additionally, important variables were determined based on the random forest and weights of the linear SVM.
The AUCs of the MLP, LRM, linear SVM, RBF-SVM, kNN, decision tree, and random forest were 0.83, 0.82, 0.80, 0.81, 0.76, 0.70, and 0.79, respectively. The accuracy ranged between 0.76 (decision tree,) and 0.79 (linear SVM, RBF-SVM, and MLP). Important variables for predicting the aneurysm rupture status included aneurysm location, the mean surface curvature, and maximum flow velocity.
The performance of the LRM was overall comparable to that of the other ML classifiers, confirming its potential for aneurysm rupture assessment. To further improve the predictions, additional information, e.g., related to the aneurysm wall, might be needed.
偶然发现的动脉瘤给需要决定是否治疗的医生带来了挑战。统计模型有可能支持这种治疗决策。本研究的目的是比较先前开发的动脉瘤破裂逻辑回归概率模型（LRM）与其他机器学习（ML）分类器，以区分动脉瘤破裂状态。
使用计算流体动力学模拟的 1631 个脑动脉瘤的血流动力学、形态学和患者相关信息，训练支持向量机（SVM），包括线性和 RBF 核（RBF-SVM）、k-最近邻（kNN）、决策树、随机森林和多层感知器（MLP）神经网络分类器，以预测动脉瘤破裂状态。使用来自两个外部队列的 249 个测试病例评估和比较分类器的准确性、敏感性、特异性和接收者操作特征曲线下的面积（AUC），并与 LRM 进行比较。此外，还根据随机森林和线性 SVM 的权重确定了重要变量。
MLP、LRM、线性 SVM、RBF-SVM、kNN、决策树和随机森林的 AUC 分别为 0.83、0.82、0.80、0.81、0.76、0.70 和 0.79。准确性范围在 0.76（决策树）和 0.79（线性 SVM、RBF-SVM 和 MLP）之间。预测动脉瘤破裂状态的重要变量包括动脉瘤位置、平均表面曲率和最大流速。
LRM 的性能总体上与其他 ML 分类器相当，证实了其在动脉瘤破裂评估中的潜力。为了进一步提高预测精度，可能需要额外的信息，例如与动脉瘤壁相关的信息。
