TY - JOUR

T1 - Comparison of statistical learning approaches for cerebral aneurysm rupture assessment

AU - Detmer, Felicitas J.

AU - Lückehe, Daniel

AU - Mut, Fernando

AU - Slawski, Martin

AU - Hirsch, Sven

AU - Bijlenga, Philippe

AU - von Voigt, Gabriele

AU - Cebral, Juan R.

N1 - Funding Information: SH and PB were supported by SystemsX.ch project AneuX evaluated by the Swiss National Science Foundation. Data for the AneuX dataset was collected and processed in the context of the @neurIST project funded by the EU commission (IST-2004-027703) and AneuX project evaluated by the Swiss National Science Foundation and funded by the SystemsX.ch initiative (MRD 2014/261). Acknowledgements

PY - 2020/1

Y1 - 2020/1

N2 - Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.

AB - Purpose: 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. Methods: 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. Results: 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. Conclusion: 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.

KW - Cerebral aneurysm

KW - Hemodynamics

KW - Machine learning

KW - Prediction

KW - Risk factors

KW - Shape

UR - http://www.scopus.com/inward/record.url?scp=85072183125&partnerID=8YFLogxK

U2 - 10.1007/s11548-019-02065-2

DO - 10.1007/s11548-019-02065-2

M3 - Article

C2 - 31485987

AN - SCOPUS:85072183125

VL - 15

SP - 141

EP - 150

JO - International journal of computer assisted radiology and surgery

JF - International journal of computer assisted radiology and surgery

SN - 1861-6410

ER -