Development and internal validation of an aneurysm rupture probability model based on patient characteristics and aneurysm location, morphology, and hemodynamics

Felicitas J. Detmer, Bong Jae Chung, Fernando Mut, Martin Slawski, Farid Hamzei-Sichani, Christopher Putman, Carlos Jiménez, Juan R. Cebral

Research output: Contribution to journalArticleResearchpeer-review

7 Citations (Scopus)

Abstract

Purpose: Unruptured cerebral aneurysms pose a dilemma for physicians who need to weigh the risk of a devastating subarachnoid hemorrhage against the risk of surgery or endovascular treatment and their complications when deciding on a treatment strategy. A prediction model could potentially support such treatment decisions. The aim of this study was to develop and internally validate a model for aneurysm rupture based on hemodynamic and geometric parameters, aneurysm location, and patient gender and age. Methods: Cross-sectional data from 1061 patients were used for image-based computational fluid dynamics and shape characterization of 1631 aneurysms for training an aneurysm rupture probability model using logistic group Lasso regression. The model’s discrimination and calibration were internally validated based on the area under the curve (AUC) of the receiver operating characteristic and calibration plots. Results: The final model retained 11 hemodynamic and 12 morphological variables, aneurysm location, as well as patient age and gender. An adverse hemodynamic environment characterized by a higher maximum oscillatory shear index, higher kinetic energy and smaller low shear area as well as a more complex aneurysm shape, male gender and younger age were associated with an increased rupture risk. The corresponding AUC of the model was 0.86 (95% CI [0.85, 0.86], after correction for optimism 0.84). Conclusion: The model combining variables from various domains was able to discriminate between ruptured and unruptured aneurysms with an AUC of 86%. Internal validation indicated potential for the application of this model in clinical practice after evaluation with longitudinal data.

Original languageEnglish
Pages (from-to)1767-1779
Number of pages13
JournalInternational Journal of Computer Assisted Radiology and Surgery
Volume13
Issue number11
DOIs
StatePublished - 1 Nov 2018

Fingerprint

Hemodynamics
Aneurysm
Rupture
Area Under Curve
Calibration
Ruptured Aneurysm
Intracranial Aneurysm
Subarachnoid Hemorrhage
Hydrodynamics
ROC Curve
Therapeutics
Logistic Models
Kinetic energy
Surgery
Physicians
Logistics
Computational fluid dynamics

Keywords

  • Cerebral aneurysm
  • Hemodynamics
  • Prediction
  • Risk factors
  • Rupture
  • Shape

Cite this

Detmer, Felicitas J. ; Chung, Bong Jae ; Mut, Fernando ; Slawski, Martin ; Hamzei-Sichani, Farid ; Putman, Christopher ; Jiménez, Carlos ; Cebral, Juan R. / Development and internal validation of an aneurysm rupture probability model based on patient characteristics and aneurysm location, morphology, and hemodynamics. In: International Journal of Computer Assisted Radiology and Surgery. 2018 ; Vol. 13, No. 11. pp. 1767-1779.
@article{421dc08bc78f457cb942a156568e4102,
title = "Development and internal validation of an aneurysm rupture probability model based on patient characteristics and aneurysm location, morphology, and hemodynamics",
abstract = "Purpose: Unruptured cerebral aneurysms pose a dilemma for physicians who need to weigh the risk of a devastating subarachnoid hemorrhage against the risk of surgery or endovascular treatment and their complications when deciding on a treatment strategy. A prediction model could potentially support such treatment decisions. The aim of this study was to develop and internally validate a model for aneurysm rupture based on hemodynamic and geometric parameters, aneurysm location, and patient gender and age. Methods: Cross-sectional data from 1061 patients were used for image-based computational fluid dynamics and shape characterization of 1631 aneurysms for training an aneurysm rupture probability model using logistic group Lasso regression. The model’s discrimination and calibration were internally validated based on the area under the curve (AUC) of the receiver operating characteristic and calibration plots. Results: The final model retained 11 hemodynamic and 12 morphological variables, aneurysm location, as well as patient age and gender. An adverse hemodynamic environment characterized by a higher maximum oscillatory shear index, higher kinetic energy and smaller low shear area as well as a more complex aneurysm shape, male gender and younger age were associated with an increased rupture risk. The corresponding AUC of the model was 0.86 (95{\%} CI [0.85, 0.86], after correction for optimism 0.84). Conclusion: The model combining variables from various domains was able to discriminate between ruptured and unruptured aneurysms with an AUC of 86{\%}. Internal validation indicated potential for the application of this model in clinical practice after evaluation with longitudinal data.",
keywords = "Cerebral aneurysm, Hemodynamics, Prediction, Risk factors, Rupture, Shape",
author = "Detmer, {Felicitas J.} and Chung, {Bong Jae} and Fernando Mut and Martin Slawski and Farid Hamzei-Sichani and Christopher Putman and Carlos Jim{\'e}nez and Cebral, {Juan R.}",
year = "2018",
month = "11",
day = "1",
doi = "10.1007/s11548-018-1837-0",
language = "English",
volume = "13",
pages = "1767--1779",
journal = "International Journal of Computer Assisted Radiology and Surgery",
issn = "1861-6410",
number = "11",

}

Development and internal validation of an aneurysm rupture probability model based on patient characteristics and aneurysm location, morphology, and hemodynamics. / Detmer, Felicitas J.; Chung, Bong Jae; Mut, Fernando; Slawski, Martin; Hamzei-Sichani, Farid; Putman, Christopher; Jiménez, Carlos; Cebral, Juan R.

In: International Journal of Computer Assisted Radiology and Surgery, Vol. 13, No. 11, 01.11.2018, p. 1767-1779.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Development and internal validation of an aneurysm rupture probability model based on patient characteristics and aneurysm location, morphology, and hemodynamics

AU - Detmer, Felicitas J.

AU - Chung, Bong Jae

AU - Mut, Fernando

AU - Slawski, Martin

AU - Hamzei-Sichani, Farid

AU - Putman, Christopher

AU - Jiménez, Carlos

AU - Cebral, Juan R.

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Purpose: Unruptured cerebral aneurysms pose a dilemma for physicians who need to weigh the risk of a devastating subarachnoid hemorrhage against the risk of surgery or endovascular treatment and their complications when deciding on a treatment strategy. A prediction model could potentially support such treatment decisions. The aim of this study was to develop and internally validate a model for aneurysm rupture based on hemodynamic and geometric parameters, aneurysm location, and patient gender and age. Methods: Cross-sectional data from 1061 patients were used for image-based computational fluid dynamics and shape characterization of 1631 aneurysms for training an aneurysm rupture probability model using logistic group Lasso regression. The model’s discrimination and calibration were internally validated based on the area under the curve (AUC) of the receiver operating characteristic and calibration plots. Results: The final model retained 11 hemodynamic and 12 morphological variables, aneurysm location, as well as patient age and gender. An adverse hemodynamic environment characterized by a higher maximum oscillatory shear index, higher kinetic energy and smaller low shear area as well as a more complex aneurysm shape, male gender and younger age were associated with an increased rupture risk. The corresponding AUC of the model was 0.86 (95% CI [0.85, 0.86], after correction for optimism 0.84). Conclusion: The model combining variables from various domains was able to discriminate between ruptured and unruptured aneurysms with an AUC of 86%. Internal validation indicated potential for the application of this model in clinical practice after evaluation with longitudinal data.

AB - Purpose: Unruptured cerebral aneurysms pose a dilemma for physicians who need to weigh the risk of a devastating subarachnoid hemorrhage against the risk of surgery or endovascular treatment and their complications when deciding on a treatment strategy. A prediction model could potentially support such treatment decisions. The aim of this study was to develop and internally validate a model for aneurysm rupture based on hemodynamic and geometric parameters, aneurysm location, and patient gender and age. Methods: Cross-sectional data from 1061 patients were used for image-based computational fluid dynamics and shape characterization of 1631 aneurysms for training an aneurysm rupture probability model using logistic group Lasso regression. The model’s discrimination and calibration were internally validated based on the area under the curve (AUC) of the receiver operating characteristic and calibration plots. Results: The final model retained 11 hemodynamic and 12 morphological variables, aneurysm location, as well as patient age and gender. An adverse hemodynamic environment characterized by a higher maximum oscillatory shear index, higher kinetic energy and smaller low shear area as well as a more complex aneurysm shape, male gender and younger age were associated with an increased rupture risk. The corresponding AUC of the model was 0.86 (95% CI [0.85, 0.86], after correction for optimism 0.84). Conclusion: The model combining variables from various domains was able to discriminate between ruptured and unruptured aneurysms with an AUC of 86%. Internal validation indicated potential for the application of this model in clinical practice after evaluation with longitudinal data.

KW - Cerebral aneurysm

KW - Hemodynamics

KW - Prediction

KW - Risk factors

KW - Rupture

KW - Shape

UR - http://www.scopus.com/inward/record.url?scp=85051630282&partnerID=8YFLogxK

U2 - 10.1007/s11548-018-1837-0

DO - 10.1007/s11548-018-1837-0

M3 - Article

VL - 13

SP - 1767

EP - 1779

JO - International Journal of Computer Assisted Radiology and Surgery

JF - International Journal of Computer Assisted Radiology and Surgery

SN - 1861-6410

IS - 11

ER -