Comparison of statistical learning approaches for cerebral aneurysm rupture assessment

Detmer, Felicitas J; Lückehe, Daniel; Mut, Fernando; Slawski, Martin; Hirsch, Sven; Bijlenga, Philippe Alexandre Pierre; von Voigt, Gabriele; Cebral, Juan R

doi:10.1007/s11548-019-02065-2

Scientific article

English

Comparison of statistical learning approaches for cerebral aneurysm rupture assessment

ContributorsDetmer, Felicitas J; Lückehe, Daniel; Mut, Fernando; Slawski, Martin; Hirsch, Sven; Bijlenga, Philippe Alexandre Pierre; von Voigt, Gabriele; Cebral, Juan R

Published inInternational Journal of Computer Assisted Radiology and Surgery, vol. 15, no. 1, p. 141-150

Publication date2020

Abstract

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.

Keywords

Aneurysm, Ruptured/diagnosis/physiopathology
Decision Trees
Hemodynamics/physiology
Humans
Intracranial Aneurysm/diagnosis/physiopathology
Models, Statistical
ROC Curve
Support Vector Machine

Affiliation entities

Faculté de médecine / Section de médecine clinique / Département des neurosciences cliniques

Research groups

Groupe Schaller Karl Lothard (neurochirurgie) (851)

Funding

Autre - @neurIST project funded by the EU commission (IST-2004-027703)
Autre - AneuX project evaluated by the Swiss National Science Foundation and funded by the SystemsX.ch initiative (MRD 2014/261)

Citation (ISO format)

DETMER, Felicitas J et al. Comparison of statistical learning approaches for cerebral aneurysm rupture assessment. In: International Journal of Computer Assisted Radiology and Surgery, 2020, vol. 15, n° 1, p. 141–150. doi: 10.1007/s11548-019-02065-2