Construction of a risk model through the fusion of experimental data and finite element modeling

Application to car crash-induced TBI

Seyed Saeed Ahmadisoleymani, Samy Missoum

Research output: Contribution to journalArticle

Abstract

This article introduces a new approach for the construction of a risk model for the prediction of Traumatic Brain Injury (TBI) as a result of a car crash. The probability of TBI is assessed through the fusion of an experiment-based logistic regression risk model and a finite element (FE) simulation-based risk model. The proposed approach uses a multilevel framework which includes FE simulations of vehicle crashes with dummy and FE simulations of the human brain. The loading conditions derived from the crash simulations are transferred to the brain model thus allowing the calculation of injury metrics such as the Cumulative Strain Damage Measure (CSDM). The framework is used to propagate uncertainties and obtain probabilities of TBI based on the CSDM injury metric. The risk model from FE simulations is constructed from a support vector machine classifier, adaptive sampling, and Monte-Carlo simulations. An approach to compute the total probability of TBI, which combines the FE-based risk assessment as well as the risk prediction from the experiment-based logistic regression model is proposed. In contrast to previous published work, the proposed methodology includes the uncertainty of explicit parameters such as impact conditions (e.g., velocity, impact angle), and material properties of the brain model. This risk model can provide, for instance, the probability of TBI for a given assumed crash impact velocity.

Original languageEnglish (US)
Pages (from-to)605-619
Number of pages15
JournalComputer Methods in Biomechanics and Biomedical Engineering
Volume22
Issue number6
DOIs
StatePublished - Apr 26 2019

Fingerprint

Brain
Railroad cars
Fusion reactions
Brain models
Logistics
Risk assessment
Support vector machines
Materials properties
Classifiers
Experiments
Sampling
Uncertainty

Keywords

  • Crash simulations
  • Data fusion
  • Finite element analysis
  • Risk model
  • Traumatic Brain Injury

ASJC Scopus subject areas

  • Bioengineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

@article{a01d8231848f46f49797c485570d3d8e,
title = "Construction of a risk model through the fusion of experimental data and finite element modeling: Application to car crash-induced TBI",
abstract = "This article introduces a new approach for the construction of a risk model for the prediction of Traumatic Brain Injury (TBI) as a result of a car crash. The probability of TBI is assessed through the fusion of an experiment-based logistic regression risk model and a finite element (FE) simulation-based risk model. The proposed approach uses a multilevel framework which includes FE simulations of vehicle crashes with dummy and FE simulations of the human brain. The loading conditions derived from the crash simulations are transferred to the brain model thus allowing the calculation of injury metrics such as the Cumulative Strain Damage Measure (CSDM). The framework is used to propagate uncertainties and obtain probabilities of TBI based on the CSDM injury metric. The risk model from FE simulations is constructed from a support vector machine classifier, adaptive sampling, and Monte-Carlo simulations. An approach to compute the total probability of TBI, which combines the FE-based risk assessment as well as the risk prediction from the experiment-based logistic regression model is proposed. In contrast to previous published work, the proposed methodology includes the uncertainty of explicit parameters such as impact conditions (e.g., velocity, impact angle), and material properties of the brain model. This risk model can provide, for instance, the probability of TBI for a given assumed crash impact velocity.",
keywords = "Crash simulations, Data fusion, Finite element analysis, Risk model, Traumatic Brain Injury",
author = "Ahmadisoleymani, {Seyed Saeed} and Samy Missoum",
year = "2019",
month = "4",
day = "26",
doi = "10.1080/10255842.2019.1574343",
language = "English (US)",
volume = "22",
pages = "605--619",
journal = "Computer Methods in Biomechanics and Biomedical Engineering",
issn = "1025-5842",
publisher = "Informa Healthcare",
number = "6",

}

TY - JOUR

T1 - Construction of a risk model through the fusion of experimental data and finite element modeling

T2 - Application to car crash-induced TBI

AU - Ahmadisoleymani, Seyed Saeed

AU - Missoum, Samy

PY - 2019/4/26

Y1 - 2019/4/26

N2 - This article introduces a new approach for the construction of a risk model for the prediction of Traumatic Brain Injury (TBI) as a result of a car crash. The probability of TBI is assessed through the fusion of an experiment-based logistic regression risk model and a finite element (FE) simulation-based risk model. The proposed approach uses a multilevel framework which includes FE simulations of vehicle crashes with dummy and FE simulations of the human brain. The loading conditions derived from the crash simulations are transferred to the brain model thus allowing the calculation of injury metrics such as the Cumulative Strain Damage Measure (CSDM). The framework is used to propagate uncertainties and obtain probabilities of TBI based on the CSDM injury metric. The risk model from FE simulations is constructed from a support vector machine classifier, adaptive sampling, and Monte-Carlo simulations. An approach to compute the total probability of TBI, which combines the FE-based risk assessment as well as the risk prediction from the experiment-based logistic regression model is proposed. In contrast to previous published work, the proposed methodology includes the uncertainty of explicit parameters such as impact conditions (e.g., velocity, impact angle), and material properties of the brain model. This risk model can provide, for instance, the probability of TBI for a given assumed crash impact velocity.

AB - This article introduces a new approach for the construction of a risk model for the prediction of Traumatic Brain Injury (TBI) as a result of a car crash. The probability of TBI is assessed through the fusion of an experiment-based logistic regression risk model and a finite element (FE) simulation-based risk model. The proposed approach uses a multilevel framework which includes FE simulations of vehicle crashes with dummy and FE simulations of the human brain. The loading conditions derived from the crash simulations are transferred to the brain model thus allowing the calculation of injury metrics such as the Cumulative Strain Damage Measure (CSDM). The framework is used to propagate uncertainties and obtain probabilities of TBI based on the CSDM injury metric. The risk model from FE simulations is constructed from a support vector machine classifier, adaptive sampling, and Monte-Carlo simulations. An approach to compute the total probability of TBI, which combines the FE-based risk assessment as well as the risk prediction from the experiment-based logistic regression model is proposed. In contrast to previous published work, the proposed methodology includes the uncertainty of explicit parameters such as impact conditions (e.g., velocity, impact angle), and material properties of the brain model. This risk model can provide, for instance, the probability of TBI for a given assumed crash impact velocity.

KW - Crash simulations

KW - Data fusion

KW - Finite element analysis

KW - Risk model

KW - Traumatic Brain Injury

UR - http://www.scopus.com/inward/record.url?scp=85065785316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065785316&partnerID=8YFLogxK

U2 - 10.1080/10255842.2019.1574343

DO - 10.1080/10255842.2019.1574343

M3 - Article

VL - 22

SP - 605

EP - 619

JO - Computer Methods in Biomechanics and Biomedical Engineering

JF - Computer Methods in Biomechanics and Biomedical Engineering

SN - 1025-5842

IS - 6

ER -