Fusion of clinical and stochastic finite element data for hip fracture risk prediction

Peng Jiang, Samy Missoum, Zhao Chen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Hip fracture affects more than 250,000 people in the US and 1.6 million worldwide per year. With an aging population, the development of reliable fracture risk models is therefore of prime importance. Due to the complexity of the hip fracture phenomenon, the use of clinical data only, as it is done traditionally, might not be sufficient to ensure an accurate and robust hip fracture prediction model. In order to increase the predictive ability of the risk model, the authors propose to supplement the clinical data with computational data from finite element models. The fusion of the two types of data is performed using deterministic and stochastic computational data. In the latter case, uncertainties in loading and material properties of the femur are accounted for and propagated through the finite element model. The predictive capability of a support vector machine (SVM) risk model constructed by combining clinical and finite element data was assessed using a Women's Health Initiative (WHI) dataset. The dataset includes common factors such as age and BMD as well as geometric factors obtained from DXA imaging. The fusion of computational and clinical data systematically leads to an increase in predictive ability of the SVM risk model as measured by the AUC metric. It is concluded that the largest gains in AUC are obtained by the stochastic approach. This gain decreases as the dimensionality of the problem increases: a 5.3% AUC improvement was achieved for a 9 dimensional problem involving geometric factors and weight while a 1.3% increase was obtained for a 20 dimensional case including geometric and conventional factors.

Original languageEnglish (US)
Pages (from-to)4043-4052
Number of pages10
JournalJournal of Biomechanics
Volume48
Issue number15
DOIs
StatePublished - Nov 26 2015

Fingerprint

Hip Fractures
Fusion reactions
Area Under Curve
Women's Health
Support vector machines
Femur
Uncertainty
Weights and Measures
Materials properties
Population
Aging of materials
Imaging techniques
Support Vector Machine
Datasets

Keywords

  • Data fusion
  • Finite element modeling
  • Hip fracture prediction
  • Support vector machines

ASJC Scopus subject areas

  • Orthopedics and Sports Medicine
  • Rehabilitation
  • Biophysics
  • Biomedical Engineering

Cite this

Fusion of clinical and stochastic finite element data for hip fracture risk prediction. / Jiang, Peng; Missoum, Samy; Chen, Zhao.

In: Journal of Biomechanics, Vol. 48, No. 15, 26.11.2015, p. 4043-4052.

Research output: Contribution to journalArticle

@article{cb7ee0d5394d46d18bffeeadff60d238,
title = "Fusion of clinical and stochastic finite element data for hip fracture risk prediction",
abstract = "Hip fracture affects more than 250,000 people in the US and 1.6 million worldwide per year. With an aging population, the development of reliable fracture risk models is therefore of prime importance. Due to the complexity of the hip fracture phenomenon, the use of clinical data only, as it is done traditionally, might not be sufficient to ensure an accurate and robust hip fracture prediction model. In order to increase the predictive ability of the risk model, the authors propose to supplement the clinical data with computational data from finite element models. The fusion of the two types of data is performed using deterministic and stochastic computational data. In the latter case, uncertainties in loading and material properties of the femur are accounted for and propagated through the finite element model. The predictive capability of a support vector machine (SVM) risk model constructed by combining clinical and finite element data was assessed using a Women's Health Initiative (WHI) dataset. The dataset includes common factors such as age and BMD as well as geometric factors obtained from DXA imaging. The fusion of computational and clinical data systematically leads to an increase in predictive ability of the SVM risk model as measured by the AUC metric. It is concluded that the largest gains in AUC are obtained by the stochastic approach. This gain decreases as the dimensionality of the problem increases: a 5.3{\%} AUC improvement was achieved for a 9 dimensional problem involving geometric factors and weight while a 1.3{\%} increase was obtained for a 20 dimensional case including geometric and conventional factors.",
keywords = "Data fusion, Finite element modeling, Hip fracture prediction, Support vector machines",
author = "Peng Jiang and Samy Missoum and Zhao Chen",
year = "2015",
month = "11",
day = "26",
doi = "10.1016/j.jbiomech.2015.09.044",
language = "English (US)",
volume = "48",
pages = "4043--4052",
journal = "Journal of Biomechanics",
issn = "0021-9290",
publisher = "Elsevier Limited",
number = "15",

}

TY - JOUR

T1 - Fusion of clinical and stochastic finite element data for hip fracture risk prediction

AU - Jiang, Peng

AU - Missoum, Samy

AU - Chen, Zhao

PY - 2015/11/26

Y1 - 2015/11/26

N2 - Hip fracture affects more than 250,000 people in the US and 1.6 million worldwide per year. With an aging population, the development of reliable fracture risk models is therefore of prime importance. Due to the complexity of the hip fracture phenomenon, the use of clinical data only, as it is done traditionally, might not be sufficient to ensure an accurate and robust hip fracture prediction model. In order to increase the predictive ability of the risk model, the authors propose to supplement the clinical data with computational data from finite element models. The fusion of the two types of data is performed using deterministic and stochastic computational data. In the latter case, uncertainties in loading and material properties of the femur are accounted for and propagated through the finite element model. The predictive capability of a support vector machine (SVM) risk model constructed by combining clinical and finite element data was assessed using a Women's Health Initiative (WHI) dataset. The dataset includes common factors such as age and BMD as well as geometric factors obtained from DXA imaging. The fusion of computational and clinical data systematically leads to an increase in predictive ability of the SVM risk model as measured by the AUC metric. It is concluded that the largest gains in AUC are obtained by the stochastic approach. This gain decreases as the dimensionality of the problem increases: a 5.3% AUC improvement was achieved for a 9 dimensional problem involving geometric factors and weight while a 1.3% increase was obtained for a 20 dimensional case including geometric and conventional factors.

AB - Hip fracture affects more than 250,000 people in the US and 1.6 million worldwide per year. With an aging population, the development of reliable fracture risk models is therefore of prime importance. Due to the complexity of the hip fracture phenomenon, the use of clinical data only, as it is done traditionally, might not be sufficient to ensure an accurate and robust hip fracture prediction model. In order to increase the predictive ability of the risk model, the authors propose to supplement the clinical data with computational data from finite element models. The fusion of the two types of data is performed using deterministic and stochastic computational data. In the latter case, uncertainties in loading and material properties of the femur are accounted for and propagated through the finite element model. The predictive capability of a support vector machine (SVM) risk model constructed by combining clinical and finite element data was assessed using a Women's Health Initiative (WHI) dataset. The dataset includes common factors such as age and BMD as well as geometric factors obtained from DXA imaging. The fusion of computational and clinical data systematically leads to an increase in predictive ability of the SVM risk model as measured by the AUC metric. It is concluded that the largest gains in AUC are obtained by the stochastic approach. This gain decreases as the dimensionality of the problem increases: a 5.3% AUC improvement was achieved for a 9 dimensional problem involving geometric factors and weight while a 1.3% increase was obtained for a 20 dimensional case including geometric and conventional factors.

KW - Data fusion

KW - Finite element modeling

KW - Hip fracture prediction

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=84952864688&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84952864688&partnerID=8YFLogxK

U2 - 10.1016/j.jbiomech.2015.09.044

DO - 10.1016/j.jbiomech.2015.09.044

M3 - Article

VL - 48

SP - 4043

EP - 4052

JO - Journal of Biomechanics

JF - Journal of Biomechanics

SN - 0021-9290

IS - 15

ER -