Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.

<h4>Background</h4>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...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: 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
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2011
Materias:
R
Q
Acceso en línea:https://doaj.org/article/49e41c12c19e40fe831cabb9d5fa0a1a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:49e41c12c19e40fe831cabb9d5fa0a1a
record_format dspace
spelling oai:doaj.org-article:49e41c12c19e40fe831cabb9d5fa0a1a2021-11-18T07:34:54ZRecognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.1932-620310.1371/journal.pone.0027277https://doaj.org/article/49e41c12c19e40fe831cabb9d5fa0a1a2011-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/22076144/?tool=EBIhttps://doaj.org/toc/1932-6203<h4>Background</h4>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.<h4>Methodology</h4>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.<h4>Conclusions</h4>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.Cristina Eller-VainicherIacopo ChiodiniIvana SantiMarco MassarottiLuca PietrograndeElisa CairoliPaolo Beck-PeccozMatteo LonghiValter GalmariniGiorgio GandoliniMaurizio BevilacquaEnzo GrossiPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 6, Iss 11, p e27277 (2011)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
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
Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.
description <h4>Background</h4>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.<h4>Methodology</h4>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.<h4>Conclusions</h4>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.
format article
author 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
author_facet 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
author_sort Cristina Eller-Vainicher
title Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.
title_short Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.
title_full Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.
title_fullStr Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.
title_full_unstemmed Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO Lombardia Database.
title_sort recognition of morphometric vertebral fractures by artificial neural networks: analysis from gismo lombardia database.
publisher Public Library of Science (PLoS)
publishDate 2011
url https://doaj.org/article/49e41c12c19e40fe831cabb9d5fa0a1a
work_keys_str_mv AT cristinaellervainicher recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT iacopochiodini recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT ivanasanti recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT marcomassarotti recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT lucapietrogrande recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT elisacairoli recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT paolobeckpeccoz recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT matteolonghi recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT valtergalmarini recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT giorgiogandolini recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT mauriziobevilacqua recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
AT enzogrossi recognitionofmorphometricvertebralfracturesbyartificialneuralnetworksanalysisfromgismolombardiadatabase
_version_ 1718423220017692672