A metamodeling approach for instant severity assessment and uncertainty quantification of iliac artery stenoses

S.G.H. Heinen (Corresponding author), K. Gashi, D.A.F. van den Heuvel, J.P.P.M. de Vries, F.N. van de Vosse, T. Delhaas, W. Huberts

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Two-dimensional (2D) or three-dimensional (3D) models of blood flow in stenosed arteries can be used to patient-specifically predict outcome metrics, thereby supporting the physicians in decision making processes. However, these models are time consuming which limits the feasibility of output uncertainty quantification (UQ). Accurate surrogates (metamodels) might be the solution. In this study, we aim to demonstrate the feasibility of a generalized polynomial chaos expansion-based metamodel to predict a clinically relevant output metric and to quantify the output uncertainty. As an example, a metamodel was constructed from a recently developed 2D model that was shown to be able to estimate translesional pressure drops in iliac artery stenoses (-0.9 ± 12.7 mmHg, R2 = 0.81). The metamodel was constructed from a virtual database using the adaptive generalized polynomial chaos expansion (agPCE) method. The constructed metamodel was then applied to 25 stenosed iliac arteries to predict the patient-specific pressure drop and to perform UQ. Comparing predicted pressure drops of the metamodel and in vivo measured pressure drops, the mean bias (-0.2 ± 13.7 mmHg) and the coefficient of determination (R2 = 0.80) were as good as of the original 2D computational fluid dynamics (CFD) model. UQ results of the 2D and metamodel were comparable. Estimation of the uncertainty interval using the original 2D model took 14 days, whereas the result of the metamodel was instantly available. In conclusion, it is feasible to quantify the uncertainty of the output metric and perform sensitivity analysis (SA) instantly using a metamodel. Future studies should investigate the possibility to construct a metamodel of more complex problems.

LanguageEnglish
Article number011010
Number of pages8
JournalJournal of Biomechanical Engineering
Volume142
Issue number1
DOIs
StatePublished - 1 Jan 2020

Fingerprint

Iliac Artery
Uncertainty
Pathologic Constriction
Pressure drop
Pressure
Chaos theory
Polynomials
Hydrodynamics
Sensitivity analysis
Dynamic models
Decision Making
Computational fluid dynamics
Blood
Arteries
Decision making
Databases
Physicians

Cite this

@article{7748bd5417444ee6bc84ddc7f05af3d9,
title = "A metamodeling approach for instant severity assessment and uncertainty quantification of iliac artery stenoses",
abstract = "Two-dimensional (2D) or three-dimensional (3D) models of blood flow in stenosed arteries can be used to patient-specifically predict outcome metrics, thereby supporting the physicians in decision making processes. However, these models are time consuming which limits the feasibility of output uncertainty quantification (UQ). Accurate surrogates (metamodels) might be the solution. In this study, we aim to demonstrate the feasibility of a generalized polynomial chaos expansion-based metamodel to predict a clinically relevant output metric and to quantify the output uncertainty. As an example, a metamodel was constructed from a recently developed 2D model that was shown to be able to estimate translesional pressure drops in iliac artery stenoses (-0.9 ± 12.7 mmHg, R2 = 0.81). The metamodel was constructed from a virtual database using the adaptive generalized polynomial chaos expansion (agPCE) method. The constructed metamodel was then applied to 25 stenosed iliac arteries to predict the patient-specific pressure drop and to perform UQ. Comparing predicted pressure drops of the metamodel and in vivo measured pressure drops, the mean bias (-0.2 ± 13.7 mmHg) and the coefficient of determination (R2 = 0.80) were as good as of the original 2D computational fluid dynamics (CFD) model. UQ results of the 2D and metamodel were comparable. Estimation of the uncertainty interval using the original 2D model took 14 days, whereas the result of the metamodel was instantly available. In conclusion, it is feasible to quantify the uncertainty of the output metric and perform sensitivity analysis (SA) instantly using a metamodel. Future studies should investigate the possibility to construct a metamodel of more complex problems.",
author = "S.G.H. Heinen and K. Gashi and {van den Heuvel}, D.A.F. and {de Vries}, J.P.P.M. and {van de Vosse}, F.N. and T. Delhaas and W. Huberts",
year = "2020",
month = "1",
day = "1",
doi = "10.1115/1.4044502",
language = "English",
volume = "142",
journal = "Journal of Biomechanical Engineering : Transactions of the ASME",
issn = "0148-0731",
publisher = "American Society of Mechanical Engineers",
number = "1",

}

A metamodeling approach for instant severity assessment and uncertainty quantification of iliac artery stenoses. / Heinen, S.G.H. (Corresponding author); Gashi, K.; van den Heuvel, D.A.F.; de Vries, J.P.P.M.; van de Vosse, F.N.; Delhaas, T.; Huberts, W.

In: Journal of Biomechanical Engineering, Vol. 142, No. 1, 011010, 01.01.2020.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A metamodeling approach for instant severity assessment and uncertainty quantification of iliac artery stenoses

AU - Heinen,S.G.H.

AU - Gashi,K.

AU - van den Heuvel,D.A.F.

AU - de Vries,J.P.P.M.

AU - van de Vosse,F.N.

AU - Delhaas,T.

AU - Huberts,W.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Two-dimensional (2D) or three-dimensional (3D) models of blood flow in stenosed arteries can be used to patient-specifically predict outcome metrics, thereby supporting the physicians in decision making processes. However, these models are time consuming which limits the feasibility of output uncertainty quantification (UQ). Accurate surrogates (metamodels) might be the solution. In this study, we aim to demonstrate the feasibility of a generalized polynomial chaos expansion-based metamodel to predict a clinically relevant output metric and to quantify the output uncertainty. As an example, a metamodel was constructed from a recently developed 2D model that was shown to be able to estimate translesional pressure drops in iliac artery stenoses (-0.9 ± 12.7 mmHg, R2 = 0.81). The metamodel was constructed from a virtual database using the adaptive generalized polynomial chaos expansion (agPCE) method. The constructed metamodel was then applied to 25 stenosed iliac arteries to predict the patient-specific pressure drop and to perform UQ. Comparing predicted pressure drops of the metamodel and in vivo measured pressure drops, the mean bias (-0.2 ± 13.7 mmHg) and the coefficient of determination (R2 = 0.80) were as good as of the original 2D computational fluid dynamics (CFD) model. UQ results of the 2D and metamodel were comparable. Estimation of the uncertainty interval using the original 2D model took 14 days, whereas the result of the metamodel was instantly available. In conclusion, it is feasible to quantify the uncertainty of the output metric and perform sensitivity analysis (SA) instantly using a metamodel. Future studies should investigate the possibility to construct a metamodel of more complex problems.

AB - Two-dimensional (2D) or three-dimensional (3D) models of blood flow in stenosed arteries can be used to patient-specifically predict outcome metrics, thereby supporting the physicians in decision making processes. However, these models are time consuming which limits the feasibility of output uncertainty quantification (UQ). Accurate surrogates (metamodels) might be the solution. In this study, we aim to demonstrate the feasibility of a generalized polynomial chaos expansion-based metamodel to predict a clinically relevant output metric and to quantify the output uncertainty. As an example, a metamodel was constructed from a recently developed 2D model that was shown to be able to estimate translesional pressure drops in iliac artery stenoses (-0.9 ± 12.7 mmHg, R2 = 0.81). The metamodel was constructed from a virtual database using the adaptive generalized polynomial chaos expansion (agPCE) method. The constructed metamodel was then applied to 25 stenosed iliac arteries to predict the patient-specific pressure drop and to perform UQ. Comparing predicted pressure drops of the metamodel and in vivo measured pressure drops, the mean bias (-0.2 ± 13.7 mmHg) and the coefficient of determination (R2 = 0.80) were as good as of the original 2D computational fluid dynamics (CFD) model. UQ results of the 2D and metamodel were comparable. Estimation of the uncertainty interval using the original 2D model took 14 days, whereas the result of the metamodel was instantly available. In conclusion, it is feasible to quantify the uncertainty of the output metric and perform sensitivity analysis (SA) instantly using a metamodel. Future studies should investigate the possibility to construct a metamodel of more complex problems.

UR - http://www.scopus.com/inward/record.url?scp=85073073028&partnerID=8YFLogxK

U2 - 10.1115/1.4044502

DO - 10.1115/1.4044502

M3 - Article

VL - 142

JO - Journal of Biomechanical Engineering : Transactions of the ASME

T2 - Journal of Biomechanical Engineering : Transactions of the ASME

JF - Journal of Biomechanical Engineering : Transactions of the ASME

SN - 0148-0731

IS - 1

M1 - 011010

ER -