{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T15:19:57Z","timestamp":1790435997994,"version":"4.1.0"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2021,2,8]],"date-time":"2021-02-08T00:00:00Z","timestamp":1612742400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"TECHNOLOGIC S.r.l."}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Osteoporosis is an asymptomatic disease of high prevalence and incidence, leading to bone fractures burdened by high mortality and disability, mainly when several subsequent fractures occur. A fragility fracture predictive model, Artificial Intelligence-based, to identify dual X-ray absorptiometry (DXA) variables able to characterise those patients who are prone to further fractures called Bone Strain Index, was evaluated in this study.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>In a prospective, longitudinal, multicentric study 172 female outpatients with at least one vertebral fracture at the first observation were enrolled. They performed a spine X-ray to calculate spine deformity index (SDI) and a lumbar and femoral DXA scan to assess bone mineral density (BMD) and bone strain index (BSI) at baseline and after a follow-up period of 3 years in average. At the end of the follow-up, 93 women developed a further vertebral fracture. The further vertebral fracture was considered as one unit increase of SDI. We assessed the predictive capacity of supervised Artificial Neural Networks (ANNs) to distinguish women who developed a further fracture from those without it, and to detect those variables providing the maximal amount of relevant information to discriminate the two groups. ANNs choose appropriate input data automatically (TWIST-system, Training With Input Selection and Testing). Moreover, we built a semantic connectivity map usingthe Auto Contractive Map to provide further insights about the convoluted connections between the osteoporotic variables under consideration and the two scenarios (further fracture vs no further fracture).<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>TWIST system selected 5 out of 13 available variables: age, menopause age, BMI, FTot BMC, FTot BSI. With training testing procedure, ANNs reached predictive accuracy of 79.36%, with a sensitivity of 75% and a specificity of 83.72%.<\/jats:p>\n<jats:p>The semantic connectivity map highlighted the role of BSI in predicting the risk of a further fracture.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>Artificial Intelligence is a useful method to analyse a complex system like that regarding osteoporosis, able to identify patients prone to a further fragility fracture. BSI appears to be a useful DXA index in identifying those patients who are at risk of further vertebral fractures.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0245967","type":"journal-article","created":{"date-parts":[[2021,2,8]],"date-time":"2021-02-08T23:59:45Z","timestamp":1612828785000},"page":"e0245967","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":28,"title":["Bone strain index as a predictor of further vertebral fracture in osteoporotic women: An artificial intelligence-based analysis"],"prefix":"10.1371","volume":"16","author":[{"given":"Fabio Massimo","family":"Ulivieri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Rinaudo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca Petruccio","family":"Piodi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7518-5773","authenticated-orcid":true,"given":"Carmelo","family":"Messina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca Maria","family":"Sconfienza","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Sardanelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Guglielmi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enzo","family":"Grossi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,2,8]]},"reference":[{"key":"pone.0245967.ref001","first-page":"785","article-title":"NIH Consensus Development Panel on Osteoporosis Prevention, Diagnosis, and Therapy. Osteoporosis prevention, diagnosis, and therapy","volume":"285","year":"2001","journal-title":"JAMA"},{"key":"pone.0245967.ref002","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/0002-9343(93)90218-E","article-title":"Consensus development conference: diagnosis, prophylaxis, and treatment of osteoporosis","volume":"94","year":"1993","journal-title":"Am J Med"},{"key":"pone.0245967.ref003","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s00198-012-2074-y","article-title":"European guidance for the diagnosis and management of osteoporosis in postmenopausal women","volume":"24","author":"JA Kanis","year":"2013","journal-title":"Osteoporos Int"},{"key":"pone.0245967.ref004","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1136\/bmj.312.7041.1254","article-title":"Meta-analysis of how well measures of bone mineral density predict occurrence of osteoporotic fractures","volume":"312","author":"D Marshall","year":"1996","journal-title":"BMJ"},{"key":"pone.0245967.ref005","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1093\/oxfordjournals.aje.a115204","article-title":"Epidemiology of vertebral fractures in women","volume":"129","author":"LJ Melton","year":"1989","journal-title":"Am J Epidemiol"},{"key":"pone.0245967.ref006","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/S8756-3282(00)00381-1","article-title":"Risk of hip fracture according to the World Health Organization criteria for osteopenia and osteoporosis","volume":"27","author":"JA Kanis","year":"2000","journal-title":"Bone"},{"key":"pone.0245967.ref007","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1359\/jbmr.090803","article-title":"Contribution of trabecular and cortical components to biomechanical behavior of human vertebrae: an ex vivo study","volume":"25","author":"J-P Roux","year":"2010","journal-title":"J Bone Miner Res"},{"key":"pone.0245967.ref008","doi-asserted-by":"crossref","first-page":"1343","DOI":"10.1148\/rg.315105712","article-title":"Integrated imaging approach to osteoporosis: state-of-the-art review and update","volume":"31","author":"G Guglielmi","journal-title":"Radiographics"},{"key":"pone.0245967.ref009","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.jocd.2011.05.005","article-title":"Correlations between trabecular bone score, measured using anteroposterior dual-energy X-ray absorptiometry acquisition, and 3-dimensional parameters of bone microarchitecture: an experimental study on human cadaver vertebrae","volume":"14","author":"D Hans","year":"2011","journal-title":"J Clin Densitom"},{"key":"pone.0245967.ref010","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.jocd.2008.11.006","article-title":"Evaluation of the potential use of trabecular bone score to complement bone mineral density in the diagnosis of osteoporosis: a preliminary spine BMD-matched, case-control study","volume":"12","author":"L Pothuaud","year":"2009","journal-title":"J Clin Densitom"},{"issue":"12","key":"pone.0245967.ref011","doi-asserted-by":"crossref","first-page":"e0225905","DOI":"10.1371\/journal.pone.0225905","article-title":"A new finite element based parameter to predict bone fracture","volume":"14","author":"C Colombo","year":"2019","journal-title":"PLoS One"},{"key":"pone.0245967.ref012","volume-title":"The Finite Element Method: Its Basis and Fundamentals","author":"OC Zienkiewicz","year":"2005"},{"key":"pone.0245967.ref013","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1002\/jbmr.2291","article-title":"Prediction of incident hip fracture with the estimated femoral strength by finite element analysis of DXA Scans in the study of osteoporotic fractures","volume":"29","author":"L Yang","year":"2014","journal-title":"J Bone Miner Res"},{"key":"pone.0245967.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10255842.2016.1193596","article-title":"Lumbar spine finite element model for healthy subjects: development and validation","volume":"20","author":"M Xu","year":"2017","journal-title":"Comput Methods Biomech Biomed Engin"},{"issue":"3","key":"pone.0245967.ref015","doi-asserted-by":"crossref","first-page":"e0229820","DOI":"10.1371\/journal.pone.0229820","article-title":"Artificial neural network analysis of bone quality DXA parameters response to teriparatide in fractured osteoporotic patients","volume":"15","author":"C Messina","year":"2020","journal-title":"PLoS One"},{"key":"pone.0245967.ref016","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s41747-020-00151-8","article-title":"Bone strain index in the prediction of vertebral fragility refracture","volume":"4","author":"FM Ulivieri","year":"2020","journal-title":"Eur Radiol Exp"},{"key":"pone.0245967.ref017","doi-asserted-by":"crossref","first-page":"220","DOI":"10.3389\/fbioe.2019.00220","article-title":"Improving the hip fracture risk prediction through 2D finite element models from DXA images: Validation against 3D models","volume":"7","author":"M Terzini","year":"2019","journal-title":"Front Bioeng Biotechnol"},{"issue":"1","key":"pone.0245967.ref018","doi-asserted-by":"crossref","first-page":"e0190477","DOI":"10.1371\/journal.pone.0190477","article-title":"The role of carboxy-terminal cross-linking telopeptide of type I collagen, dual x-ray absorptiometry bone strain and Romberg test in a new osteoporotic fracture risk evaluation: A proposal from an observational study","volume":"13","author":"FM Ulivieri","year":"2018","journal-title":"PLoS One"},{"key":"pone.0245967.ref019","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1111\/hae.13611","article-title":"Usefulness of bone microarchitectural and geometric DXA-derived parameters in haemophilic patients","volume":"24","author":"FM Ulivieri","year":"2018","journal-title":"Haemophilia"},{"key":"pone.0245967.ref020","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/s11657-018-0507-8","article-title":"Progressive bone impairment with age and pubertal development in neurofibromatosis type I","volume":"13","author":"G Rodari","year":"2018","journal-title":"Arch Osteoporos"},{"key":"pone.0245967.ref021","doi-asserted-by":"crossref","first-page":"481","DOI":"10.2174\/156720508785908928","article-title":"Auto-Contractive Maps: an artificial adaptive system for data mining. An application to Alzheimer disease","volume":"5","author":"M Buscema","year":"2008","journal-title":"Curr Alzheimer Res"},{"key":"pone.0245967.ref022","doi-asserted-by":"crossref","first-page":"175","DOI":"10.2217\/epi.14.77","article-title":"Application of artificial neural networks to link genetic and environmental factors to DNA methylation in colorectal cancer","volume":"7","author":"F Copped\u00e8","year":"2015","journal-title":"Epigenomics"},{"key":"pone.0245967.ref023","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.3233\/JAD-160210","article-title":"Artificial Neural Networks Link One-Carbon Metabolism to Gene-Promoter Methylation in Alzheimer\u2019s Disease","volume":"53","author":"E Grossi","year":"2016","journal-title":"J Alzheimer\u2019s Dis"},{"key":"pone.0245967.ref024","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1038\/ismej.2016.183","article-title":"Microbiota network and mathematic microbe mutualism in colostrum and mature milk collected in two different geographic areas: Italy versus Burundi","volume":"11","author":"L Drago","year":"2017","journal-title":"ISME J"},{"key":"pone.0245967.ref025","doi-asserted-by":"crossref","first-page":"481","DOI":"10.2174\/156720508785908928","article-title":"Auto-Contractive Maps: An Artificial Adaptive System for Data Mining. An Application to Alzheimer Disease","volume":"5","author":"M Buscema","year":"2008","journal-title":"Curr Alzheimer Res"},{"key":"pone.0245967.ref026","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1504\/IJDMB.2008.022159","article-title":"The semantic connectivity map: an adapting self-organising knowledge discovery method in data bases. Experience in gastro-oesophageal reflux disease","volume":"2","author":"M Buscema","year":"2008","journal-title":"Int J Data Min Bioinform"},{"key":"pone.0245967.ref027","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.bone.2005.04.003","article-title":"Prognostic utility of a semiquantitative spinal deformity index","volume":"37","author":"GG Crans","year":"2005","journal-title":"Bone"},{"key":"pone.0245967.ref028","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1097\/SMJ.0b013e31817a8b02","article-title":"Report of the International Society for Clinical Densitometry 2007 Adult Position Development Conference and Official Positions","volume":"101","author":"EM Lewiecki","year":"2008","journal-title":"South Med J"},{"key":"pone.0245967.ref029","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1016\/S0021-9290(03)00071-X","article-title":"Trabecular bone modulus-density relationships depend on anatomic site","volume":"36","author":"EF Morgan","year":"2003","journal-title":"J Biomech"},{"key":"pone.0245967.ref030","doi-asserted-by":"crossref","first-page":"969","DOI":"10.1016\/j.medengphy.2012.09.009","article-title":"Lumbar spinal loads vary with body height and weight","volume":"35","author":"KS Han","year":"2013","journal-title":"Med Eng Phys"},{"key":"pone.0245967.ref031","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1002\/jbmr.5650080915","article-title":"Vertebral fracture assessment using a semiquantitative technique","volume":"8","author":"HK Genant","year":"1993","journal-title":"J Bone Miner Res"},{"key":"pone.0245967.ref032","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.21037\/qims.2019.09.10","article-title":"How to define an osteoporotic vertebral fracture?","volume":"9","author":"D Diacinti","year":"2019","journal-title":"Quant Imaging Med Surg"},{"key":"pone.0245967.ref033","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5236.001.0001","volume-title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition","author":"D.E. Rumelhart","year":"1986"},{"key":"pone.0245967.ref034","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.artmed.2004.12.001","article-title":"An optimized experimental protocol based on neuro-evolutionary algorithms: Application to the classification of dyspeptic patients and to the prediction of the effectiveness of their treatment","volume":"34","author":"M Buscema","year":"2005","journal-title":"Artif Intell Med"},{"key":"pone.0245967.ref035","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1111\/j.1468-0394.2004.00264.x","article-title":"Genetic Doping Algorihm (GenD): theory and applications","volume":"21","author":"M. Buscema","year":"2004","journal-title":"Expert Syst"},{"key":"pone.0245967.ref036","first-page":"35021","article-title":"The implicit function as squashing time model: a novel parallel nonlinear EEG analysis technique distinguishing mild cognitive impairment and Alzheimer\u2019s disease subjects with high degree of accuracy","author":"M Buscema","year":"2007","journal-title":"Comput Intell Neurosci"},{"key":"pone.0245967.ref037","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.3233\/JAD-2010-1300","article-title":"Artificial neural networks identify the predictive values of risk factors on the conversion of amnestic mild cognitive impairment","volume":"19","author":"M Tabaton","year":"2010","journal-title":"J Alzheimer\u2019s Dis"},{"key":"pone.0245967.ref038","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/1471-2431-8-24","article-title":"Placental determinants of fetal growth: identification of key factors in the insulin-like growth factor and cytokine systems using artificial neural networks","volume":"8","author":"ME Street","year":"2008","journal-title":"BMC Pediatr"},{"key":"pone.0245967.ref039","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1186\/1471-2377-7-15","article-title":"Neuropathological findings processed by artificial neural networks (ANNs) can perfectly distinguish Alzheimer\u2019s patients from controls in the Nun Study","volume":"7","author":"E Grossi","year":"2007","journal-title":"BMC Neurol"},{"key":"pone.0245967.ref040","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1186\/1471-2105-9-254","article-title":"New application of intelligent agents in sporadic amyotrophic lateral sclerosis identifies unexpected specific genetic background","volume":"9","author":"S Penco","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"pone.0245967.ref041","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.semarthrit.2006.04.002","article-title":"Bone Strength: The Whole Is Greater Than the Sum of Its Parts","volume":"36","author":"KS Davison","year":"2006","journal-title":"Semin Arthritis Rheum"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0245967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,9]],"date-time":"2021-02-09T00:00:04Z","timestamp":1612828804000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0245967"}},"subtitle":[],"editor":[{"given":"Ezio","family":"Lanza","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,2,8]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0245967","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,8]]}}}