Abstract
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.
Similar content being viewed by others
Notes
Segmentations of the raw 3D-DRA images for the AneuX dataset were performed using the Aneufuse platform. Data are stored at the Swiss Institute of Bioinformatics and available to the scientific community by written request at adb@itis.ethz.ch.
References
Rinkel GJ, Djibuti M, van Gijn J (1998) Prevalence and risk of rupture of intracranial aneurysms: a systematic review. Stroke 29:251–259
Vlak MH, Algra A, Brandenburg R, Rinkel GJ (2011) Prevalence of unruptured intracranial aneurysms, with emphasis on sex, age, comorbidity, country, and time period: a systematic review and meta-analysis. Lancet Neurol 10:626–636. https://doi.org/10.1016/s1474-4422(11)70109-0
Rivero-Arias O, Gray A, Wolstenholme J (2010) Burden of disease and costs of aneurysmal subarachnoid haemorrhage (aSAH) in the United Kingdom. Cost Eff Resour Alloc 8:6. https://doi.org/10.1186/1478-7547-8-6
Wang G, Zhang Z, Ayala C, Dunet DO, Fang J, George MG (2014) Costs of hospitalization for stroke patients aged 18–64 years in the United States. J Stroke Cerebrovasc Dis 23:861–868. https://doi.org/10.1016/j.jstrokecerebrovasdis.2013.07.017
Gabriel RA, Kim H, Sidney S, McCulloch CE, Singh V, Johnston SC, Ko NU, Achrol AS, Zaroff JG, Young WL (2010) Ten-year detection rate of brain arteriovenous malformations in a large, multiethnic, defined population. Stroke 41:21–26. https://doi.org/10.1161/STROKEAHA.109.566018
Juvela S, Poussa K, Lehto H, Porras M (2013) Natural history of unruptured intracranial aneurysms: a long-term follow-up study. Stroke 44:2414–2421. https://doi.org/10.1161/strokeaha.113.001838
Detmer FJ, Chung BJ, Mut F, Slawski M, Hamzei-Sichani F, Putman C, Jiménez C, Cebral JR (2018) Development and internal validation of an aneurysm rupture probability model based on patient characteristics and aneurysm location, morphology, and hemodynamics. Int J Comput Assist Radiol Surg. https://doi.org/10.1007/s11548-018-1837-0
Detmer FJ, Fajardo-Jiménez D, Mut F, Juchler N, Hirsch S, Pereira VM, Bijlenga P, Cebral JR (2018) External validation of cerebral aneurysm rupture probability model with data from two patient cohorts. Acta Neurochir 160:2425–2434. https://doi.org/10.1007/s00701-018-3712-8
Meier L, Van De Geer S, Bühlmann P (2008) The group lasso for logistic regression: Group Lasso for Logistic Regression. J R Stat Soc Series B Stat Methodol 70:53–71. https://doi.org/10.1111/j.1467-9868.2007.00627.x
Sangalli LM, Secchi P, Vantini S (2014) AneuRisk65: a dataset of three-dimensional cerebral vascular geometries. Electron J Stat 8:1879–1890. https://doi.org/10.1214/14-EJS938
Cebral JR, Castro MA, Appanaboyina S, Putman CM, Millan D, Frangi AF (2005) Efficient pipeline for image-based patient-specific analysis of cerebral aneurysm hemodynamics: technique and sensitivity. IEEE Trans Med Imaging 24:457–467
Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning. Springer, New York
Liu J, Chen Y, Lan L, Lin B, Chen W, Wang M, Li R, Yang Y, Zhao B, Hu Z, Duan Y (2018) Prediction of rupture risk in anterior communicating artery aneurysms with a feed-forward artificial neural network. Eur Radiol 28:3268–3275. https://doi.org/10.1007/s00330-017-5300-3
Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 10:61–74
DeLong E, DeLong D, Clarke-Pearson D (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845. https://doi.org/10.2307/2531595
Robin X, Turck N, Hainard A, Tiberti N, Lisacek F, Sanchez J-C, Müller M (2011) pROC: an open-source package for R and S + to analyze and compare ROC curves. BMC Bioinform 12:77
Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth International Group, Boston
Diaconis P (1988) Group representations in probability and statistics. Institute of Mathematical Statistics, Hayward
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Mane D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Viegas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2016) TensorFlow: large-scale machine learning on heterogeneous systems. arXiv:1603.04467
Kleinloog R, de Mul N, Verweij BH, Post JA, Rinkel GJE, Ruigrok YM (2017) Risk factors for intracranial aneurysm rupture: a systematic review. Neurosurgery. https://doi.org/10.1093/neuros/nyx238
Tominari S, Morita A, Ishibashi T, Yamazaki T, Takao H, Murayama Y, Sonobe M, Yonekura M, Saito N, Shiokawa Y, Date I, Tominaga T, Nozaki K, Houkin K, Miyamoto S, Kirino T, Hashi K, Nakayama T, Unruptured Cerebral Aneurysm Study Japan Investigators (2015) Prediction model for 3-year rupture risk of unruptured cerebral aneurysms in Japanese patients. Ann Neurol 77:1050–1059. https://doi.org/10.1002/ana.24400
Greving JP, Wermer MJ, Brown RD, Morita A, Juvela S, Yonekura M, Ishibashi T, Torner JC, Nakayama T, Rinkel GJ, Algra A (2014) Development of the PHASES score for prediction of risk of rupture of intracranial aneurysms: a pooled analysis of six prospective cohort studies. Lancet Neurol 13:59–66. https://doi.org/10.1016/s1474-4422(13)70263-1
Xiang J, Yu J, Snyder KV, Levy EI, Siddiqui AH, Meng H (2016) Hemodynamic-morphological discriminant models for intracranial aneurysm rupture remain stable with increasing sample size. J Neurointerv Surg 8:104–110. https://doi.org/10.1136/neurintsurg-2014-011477
Bisbal J, Engelbrecht G, Villa-Uriol M-C, Frangi AF (2011) Prediction of cerebral aneurysm rupture using hemodynamic, morphologic and clinical features: a data mining approach. In: Hameurlain A, Liddle SW, Schewe K-D, Zhou X (eds) Database and expert systems applications. Springer, Berlin, pp 59–73
Cebral JR, Raschi M (2013) Suggested connections between risk factors of intracranial aneurysms: a review. Ann Biomed Eng 41:1366–1383. https://doi.org/10.1007/s10439-012-0723-0
Meng H, Tutino VM, Xiang J, Siddiqui A (2013) High WSS or low WSS? Complex interactions of hemodynamics with intracranial aneurysm initiation, growth, and rupture: toward a unifying hypothesis. AJNR Am J Neuroradiol. https://doi.org/10.3174/ajnr.A3558
Raghavan ML, Ma B, Harbaugh RE (2005) Quantified aneurysm shape and rupture risk. J Neurosurg 102:355–362
Dhar S, Tremmel M, Mocco J, Kim M, Yamamoto J, Siddiqui AH, Hopkins LN, Meng H (2008) Morphology parameters for intracranial aneurysm rupture risk assessment. Neurosurgery 63:185–197
Zhou S, Dion PA, Rouleau GA (2018) Genetics of intracranial aneurysms. Stroke 49:780–787. https://doi.org/10.1161/STROKEAHA.117.018152
Acknowledgements
The authors would like to thank Olivier Brina, Norman Juchler, Rafik Ouared, Diana Sapina, and Mari Cruz Villa-Uriol for helping with the collection and image segmentation of the AneuX data.
Funding
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).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Informed consent
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. Raw 3D-DRA of the AneuX test data set were provided by the University Hospital of Geneva and collected with formal patient consent according to the @neurIST protocol and ethics authorization PB_2018-00073 (previously CER 07-05) released June 1st 2007 and renewed April 13th 2010, August 19th 2014 and February 28th 2018 initially by the Geneva Cantonal Ethics Commission for Research involving Humans and renewed by Swissethics in 2018.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Detmer, F.J., Lückehe, D., Mut, F. et al. Comparison of statistical learning approaches for cerebral aneurysm rupture assessment. Int J CARS 15, 141–150 (2020). https://doi.org/10.1007/s11548-019-02065-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-019-02065-2