Recognition of morphometric vertebral fractures by artificial neural networks: Analysis from gismo Lombardia database

Cristina Eller-Vainicher, Iacopo Chiodini, Ivana Santi, Marco Massarotti, Luca Pietrogrande, Elisa Cairoli, Paolo Beck-Peccoz, Matteo Longhi, Valter Galmarini, Giorgio Gandolini, Maurizio Bevilacqua, Enzo Grossi

Research output: Contribution to journalArticle

Abstract

Background: It is known that bone mineral density (BMD) predicts the fracture's risk only partially and the severity and number of vertebral fractures are predictive of subsequent osteoporotic fractures (OF). Spinal deformity index (SDI) integrates the severity and number of morphometric vertebral fractures. Nowadays, there is interest in developing algorithms that use traditional statistics for predicting OF. Some studies suggest their poor sensitivity. Artificial Neural Networks (ANNs) could represent an alternative. So far, no study investigated ANNs ability in predicting OF and SDI. The aim of the present study is to compare ANNs and Logistic Regression (LR) in recognising, on the basis of osteoporotic risk-factors and other clinical information, patients with SDI≥1 and SDI≥5 from those with SDI = 0. Methodology: We compared ANNs prognostic performance with that of LR in identifying SDI≥1/SDI≥5 in 372 women with postmenopausal-osteoporosis (SDI≥1, n = 176; SDI = 0, n = 196; SDI≥5, n = 51), using 45 variables (44 clinical parameters plus BMD). ANNs were allowed to choose relevant input data automatically (TWIST-system-Semeion). Among 45 variables, 17 and 25 were selected by TWIST-system-Semeion, in SDI≥1 vs SDI = 0 (first) and SDI≥5 vs SDI = 0 (second) analysis. In the first analysis sensitivity of LR and ANNs was 35.8% and 72.5%, specificity 76.5% and 78.5% and accuracy 56.2% and 75.5%, respectively. In the second analysis, sensitivity of LR and ANNs was 37.3% and 74.8%, specificity 90.3% and 87.8%, and accuracy 63.8% and 81.3%, respectively. Conclusions: ANNs showed a better performance in identifying both SDI≥1 and SDI≥5, with a higher sensitivity, suggesting its promising role in the development of algorithm for predicting OF.

Original languageEnglish
Article numbere27277
JournalPLoS One
Volume6
Issue number11
DOIs
Publication statusPublished - Nov 4 2011

Fingerprint

Osteoporotic Fractures
Electric network analysis
neural networks
Logistic Models
Databases
Neural networks
Bone Density
Logistics
Postmenopausal Osteoporosis
bone density
Sensitivity analysis
Minerals
Bone
osteoporosis
Network performance
risk factors
statistics
Statistics

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Recognition of morphometric vertebral fractures by artificial neural networks : Analysis from gismo Lombardia database. / Eller-Vainicher, Cristina; Chiodini, Iacopo; Santi, Ivana; Massarotti, Marco; Pietrogrande, Luca; Cairoli, Elisa; Beck-Peccoz, Paolo; Longhi, Matteo; Galmarini, Valter; Gandolini, Giorgio; Bevilacqua, Maurizio; Grossi, Enzo.

In: PLoS One, Vol. 6, No. 11, e27277, 04.11.2011.

Research output: Contribution to journalArticle

Eller-Vainicher, C, Chiodini, I, Santi, I, Massarotti, M, Pietrogrande, L, Cairoli, E, Beck-Peccoz, P, Longhi, M, Galmarini, V, Gandolini, G, Bevilacqua, M & Grossi, E 2011, 'Recognition of morphometric vertebral fractures by artificial neural networks: Analysis from gismo Lombardia database', PLoS One, vol. 6, no. 11, e27277. https://doi.org/10.1371/journal.pone.0027277
Eller-Vainicher, Cristina ; Chiodini, Iacopo ; Santi, Ivana ; Massarotti, Marco ; Pietrogrande, Luca ; Cairoli, Elisa ; Beck-Peccoz, Paolo ; Longhi, Matteo ; Galmarini, Valter ; Gandolini, Giorgio ; Bevilacqua, Maurizio ; Grossi, Enzo. / Recognition of morphometric vertebral fractures by artificial neural networks : Analysis from gismo Lombardia database. In: PLoS One. 2011 ; Vol. 6, No. 11.
@article{a28772ee05ec467f90bdd73ab1b513f6,
title = "Recognition of morphometric vertebral fractures by artificial neural networks: Analysis from gismo Lombardia database",
abstract = "Background: It is known that bone mineral density (BMD) predicts the fracture's risk only partially and the severity and number of vertebral fractures are predictive of subsequent osteoporotic fractures (OF). Spinal deformity index (SDI) integrates the severity and number of morphometric vertebral fractures. Nowadays, there is interest in developing algorithms that use traditional statistics for predicting OF. Some studies suggest their poor sensitivity. Artificial Neural Networks (ANNs) could represent an alternative. So far, no study investigated ANNs ability in predicting OF and SDI. The aim of the present study is to compare ANNs and Logistic Regression (LR) in recognising, on the basis of osteoporotic risk-factors and other clinical information, patients with SDI≥1 and SDI≥5 from those with SDI = 0. Methodology: We compared ANNs prognostic performance with that of LR in identifying SDI≥1/SDI≥5 in 372 women with postmenopausal-osteoporosis (SDI≥1, n = 176; SDI = 0, n = 196; SDI≥5, n = 51), using 45 variables (44 clinical parameters plus BMD). ANNs were allowed to choose relevant input data automatically (TWIST-system-Semeion). Among 45 variables, 17 and 25 were selected by TWIST-system-Semeion, in SDI≥1 vs SDI = 0 (first) and SDI≥5 vs SDI = 0 (second) analysis. In the first analysis sensitivity of LR and ANNs was 35.8{\%} and 72.5{\%}, specificity 76.5{\%} and 78.5{\%} and accuracy 56.2{\%} and 75.5{\%}, respectively. In the second analysis, sensitivity of LR and ANNs was 37.3{\%} and 74.8{\%}, specificity 90.3{\%} and 87.8{\%}, and accuracy 63.8{\%} and 81.3{\%}, respectively. Conclusions: ANNs showed a better performance in identifying both SDI≥1 and SDI≥5, with a higher sensitivity, suggesting its promising role in the development of algorithm for predicting OF.",
author = "Cristina Eller-Vainicher and Iacopo Chiodini and Ivana Santi and Marco Massarotti and Luca Pietrogrande and Elisa Cairoli and Paolo Beck-Peccoz and Matteo Longhi and Valter Galmarini and Giorgio Gandolini and Maurizio Bevilacqua and Enzo Grossi",
year = "2011",
month = "11",
day = "4",
doi = "10.1371/journal.pone.0027277",
language = "English",
volume = "6",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

TY - JOUR

T1 - Recognition of morphometric vertebral fractures by artificial neural networks

T2 - Analysis from gismo Lombardia database

AU - Eller-Vainicher, Cristina

AU - Chiodini, Iacopo

AU - Santi, Ivana

AU - Massarotti, Marco

AU - Pietrogrande, Luca

AU - Cairoli, Elisa

AU - Beck-Peccoz, Paolo

AU - Longhi, Matteo

AU - Galmarini, Valter

AU - Gandolini, Giorgio

AU - Bevilacqua, Maurizio

AU - Grossi, Enzo

PY - 2011/11/4

Y1 - 2011/11/4

N2 - Background: It is known that bone mineral density (BMD) predicts the fracture's risk only partially and the severity and number of vertebral fractures are predictive of subsequent osteoporotic fractures (OF). Spinal deformity index (SDI) integrates the severity and number of morphometric vertebral fractures. Nowadays, there is interest in developing algorithms that use traditional statistics for predicting OF. Some studies suggest their poor sensitivity. Artificial Neural Networks (ANNs) could represent an alternative. So far, no study investigated ANNs ability in predicting OF and SDI. The aim of the present study is to compare ANNs and Logistic Regression (LR) in recognising, on the basis of osteoporotic risk-factors and other clinical information, patients with SDI≥1 and SDI≥5 from those with SDI = 0. Methodology: We compared ANNs prognostic performance with that of LR in identifying SDI≥1/SDI≥5 in 372 women with postmenopausal-osteoporosis (SDI≥1, n = 176; SDI = 0, n = 196; SDI≥5, n = 51), using 45 variables (44 clinical parameters plus BMD). ANNs were allowed to choose relevant input data automatically (TWIST-system-Semeion). Among 45 variables, 17 and 25 were selected by TWIST-system-Semeion, in SDI≥1 vs SDI = 0 (first) and SDI≥5 vs SDI = 0 (second) analysis. In the first analysis sensitivity of LR and ANNs was 35.8% and 72.5%, specificity 76.5% and 78.5% and accuracy 56.2% and 75.5%, respectively. In the second analysis, sensitivity of LR and ANNs was 37.3% and 74.8%, specificity 90.3% and 87.8%, and accuracy 63.8% and 81.3%, respectively. Conclusions: ANNs showed a better performance in identifying both SDI≥1 and SDI≥5, with a higher sensitivity, suggesting its promising role in the development of algorithm for predicting OF.

AB - Background: It is known that bone mineral density (BMD) predicts the fracture's risk only partially and the severity and number of vertebral fractures are predictive of subsequent osteoporotic fractures (OF). Spinal deformity index (SDI) integrates the severity and number of morphometric vertebral fractures. Nowadays, there is interest in developing algorithms that use traditional statistics for predicting OF. Some studies suggest their poor sensitivity. Artificial Neural Networks (ANNs) could represent an alternative. So far, no study investigated ANNs ability in predicting OF and SDI. The aim of the present study is to compare ANNs and Logistic Regression (LR) in recognising, on the basis of osteoporotic risk-factors and other clinical information, patients with SDI≥1 and SDI≥5 from those with SDI = 0. Methodology: We compared ANNs prognostic performance with that of LR in identifying SDI≥1/SDI≥5 in 372 women with postmenopausal-osteoporosis (SDI≥1, n = 176; SDI = 0, n = 196; SDI≥5, n = 51), using 45 variables (44 clinical parameters plus BMD). ANNs were allowed to choose relevant input data automatically (TWIST-system-Semeion). Among 45 variables, 17 and 25 were selected by TWIST-system-Semeion, in SDI≥1 vs SDI = 0 (first) and SDI≥5 vs SDI = 0 (second) analysis. In the first analysis sensitivity of LR and ANNs was 35.8% and 72.5%, specificity 76.5% and 78.5% and accuracy 56.2% and 75.5%, respectively. In the second analysis, sensitivity of LR and ANNs was 37.3% and 74.8%, specificity 90.3% and 87.8%, and accuracy 63.8% and 81.3%, respectively. Conclusions: ANNs showed a better performance in identifying both SDI≥1 and SDI≥5, with a higher sensitivity, suggesting its promising role in the development of algorithm for predicting OF.

UR - http://www.scopus.com/inward/record.url?scp=80655133829&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80655133829&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0027277

DO - 10.1371/journal.pone.0027277

M3 - Article

C2 - 22076144

AN - SCOPUS:80655133829

VL - 6

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

M1 - e27277

ER -