{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T13:12:14Z","timestamp":1792156334195,"version":"4.4.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:sec>\n            <jats:title>Abstract<\/jats:title>\n            <jats:p>Osteoporosis is widespread with a high incidence rate, resulting in fragility fractures which are a major contributor to mortality among the elderly. Artificial intelligence (AI), in particular artificial neural networks, appears to be useful in managing osteoporosis complexity, where bone mineral density usually reduces with aging, losing the pivotal role in decision-making regarding fracture prediction and treatment choice. Nevertheless, only some osteoporotic patients develop fragility fractures, and treatments often are not prescribed because of the high costs and poor patient adherence. AI can help clinicians to identify patients prone to fragility fractures who can benefit from preventive interventions. We describe herein the methodology issues underlying the potential advantages of introducing AI methods to support clinical decision-making in osteoporosis, being aware of challenges regarding data availability and quality, model interpretability, integration into clinical workflows, and validation of predictive accuracy. The fact that no AI fracture risk prediction software is still publicly available can be related to the fact that few high-quality datasets are available and that AI models, particularly deep learning approaches, often act as \u2018black boxes\u2019, making it difficult to understand how predictions are made. In addition, the effective implementation of predictive software has not reached sufficient integration with existing systems.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Relevance statement<\/jats:title>\n            <jats:p>With aging, bone mineral density may lose the pivotal role in osteoporosis decision-making regarding fracture prediction and treatment choice. In this scenario, AI, particularly artificial neural networks (ANNs), can be useful in supporting the clinical management of patients affected by osteoporosis.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Key Points<\/jats:title>\n            <jats:p>\n              <jats:list list-type=\"bullet\">\n                <jats:list-item>\n                  <jats:p>Osteoporosis is a complex disease with many interlinked clinical and radiological variables.<\/jats:p>\n                <\/jats:list-item>\n                <jats:list-item>\n                  <jats:p>Bone mineral density and other known indices do not allow optimal decision-making in patients affected by osteoporosis.<\/jats:p>\n                <\/jats:list-item>\n                <jats:list-item>\n                  <jats:p>ANN analysis can better discriminate osteoporotic patients particularly prone to fragility fractures and can predict future fractures.<\/jats:p>\n                <\/jats:list-item>\n              <\/jats:list>\n            <\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Graphical Abstract<\/jats:title>\n          <\/jats:sec>","DOI":"10.1186\/s41747-025-00572-3","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T18:08:47Z","timestamp":1750788527000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Artificial intelligence for predicting the risk of bone fragility fractures in osteoporosis"],"prefix":"10.1186","volume":"9","author":[{"given":"Fabio Massimo","family":"Ulivieri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7518-5773","authenticated-orcid":false,"given":"Carmelo","family":"Messina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco Maria","family":"Vitale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Rinaudo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enzo","family":"Grossi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"572_CR1","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/SVN-2017-000101","volume":"2","author":"F Jiang","year":"2017","unstructured":"Jiang F, Jiang Y, Zhi H et al (2017) Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2:230\u2013243. https:\/\/doi.org\/10.1136\/SVN-2017-000101","journal-title":"Stroke Vasc Neurol"},{"key":"572_CR2","doi-asserted-by":"publisher","first-page":"627892","DOI":"10.3389\/fmicb.2022.627892","volume":"13","author":"B Vilne","year":"2022","unstructured":"Vilne B, \u0136ibilds J, Siksna I et al (2022) Could artificial intelligence\/machine learning and inclusion of diet-gut microbiome interactions improve disease risk prediction? Case study: coronary artery disease. Front Microbiol 13:627892. https:\/\/doi.org\/10.3389\/fmicb.2022.627892","journal-title":"Front Microbiol"},{"key":"572_CR3","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1097\/MEG.0B013E3282F198A0","volume":"19","author":"E Grossi","year":"2007","unstructured":"Grossi E, Buscema M (2007) Introduction to artificial neural networks. Eur J Gastroenterol Hepatol 19:1046\u20131054. https:\/\/doi.org\/10.1097\/MEG.0B013E3282F198A0","journal-title":"Eur J Gastroenterol Hepatol"},{"key":"572_CR4","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/S0165-0114(97)00077-8","volume":"90","author":"LA Zadeh","year":"1997","unstructured":"Zadeh LA (1997) Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy Sets Syst 90:111\u2013127. https:\/\/doi.org\/10.1016\/S0165-0114(97)00077-8","journal-title":"Fuzzy Sets Syst"},{"key":"572_CR5","doi-asserted-by":"publisher","unstructured":"Grossi E (2005) Medical concepts related to individual risk are better explained with \u201cplausibility\u201d rather than \u201cprobability.\u201d BMC Cardiovasc Disord. https:\/\/doi.org\/10.1186\/1471-2261-5-31","DOI":"10.1186\/1471-2261-5-31"},{"key":"572_CR6","doi-asserted-by":"publisher","unstructured":"Benedetti M, Ventura E (2023) Training neural networks with structured noise improves classification and generalization. J Phys A Math Theor. https:\/\/doi.org\/10.1088\/1751-8121\/ad7b8f","DOI":"10.1088\/1751-8121\/ad7b8f"},{"key":"572_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00198-018-4704-5","volume":"30","author":"JA Kanis","year":"2019","unstructured":"Kanis JA, Cooper C, Rizzoli R, Reginster JY (2019) European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporos Int 30:3\u201344. https:\/\/doi.org\/10.1007\/s00198-018-4704-5","journal-title":"Osteoporos Int"},{"key":"572_CR8","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.jocd.2015.06.008","volume":"18","author":"BC Silva","year":"2015","unstructured":"Silva BC, Broy SB, Boutroy S et al (2015) Fracture risk prediction by non-BMD DXA measures: the 2015 ISCD official positions part 2: trabecular bone score. J Clin Densitom 18:309\u2013330. https:\/\/doi.org\/10.1016\/j.jocd.2015.06.008","journal-title":"J Clin Densitom"},{"key":"572_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4081\/reumatismo.2016.870","volume":"68","author":"M Rossini","year":"2016","unstructured":"Rossini M, Adami S, Bertoldo F et al (2016) Guidelines for the diagnosis, prevention and management of osteoporosis. Reumatismo 68:1\u201339. https:\/\/doi.org\/10.4081\/reumatismo.2016.870","journal-title":"Reumatismo"},{"key":"572_CR10","doi-asserted-by":"publisher","unstructured":"Ulivieri FM, Piodi LP, Grossi E et al (2018) 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. PLoS One. https:\/\/doi.org\/10.1371\/journal.pone.0190477","DOI":"10.1371\/journal.pone.0190477"},{"key":"572_CR11","doi-asserted-by":"publisher","first-page":"e0245967","DOI":"10.1371\/journal.pone.0245967","volume":"16","author":"FM Ulivieri","year":"2021","unstructured":"Ulivieri FM, Rinaudo L, Piodi LP et al (2021) Bone strain index as a predictor of further vertebral fracture in osteoporotic women: an artificial intelligence-based analysis. PLoS One 16:e0245967. https:\/\/doi.org\/10.1371\/journal.pone.0245967","journal-title":"PLoS One"},{"key":"572_CR12","doi-asserted-by":"publisher","first-page":"e0229820","DOI":"10.1371\/journal.pone.0229820","volume":"15","author":"C Messina","year":"2020","unstructured":"Messina C, Piodi LP, Grossi E et al (2020) Artificial neural network analysis of bone quality DXA parameters response to teriparatide in fractured osteoporotic patients. PLoS One 15:e0229820. https:\/\/doi.org\/10.1371\/journal.pone.0229820","journal-title":"PLoS One"},{"key":"572_CR13","doi-asserted-by":"publisher","first-page":"1279","DOI":"10.1007\/S00198-021-05887-6","volume":"32","author":"L Gao","year":"2021","unstructured":"Gao L, Jiao T, Feng Q, Wang W (2021) Application of artificial intelligence in diagnosis of osteoporosis using medical images: a systematic review and meta-analysis. Osteoporos Int 32:1279\u20131286. https:\/\/doi.org\/10.1007\/S00198-021-05887-6","journal-title":"Osteoporos Int"},{"key":"572_CR14","doi-asserted-by":"publisher","unstructured":"Vigna L, Tirelli AS, Grossi E et al (2023) Metal body burden as cardiovascular risk factor in adults with metabolic syndrome and overweight-obesity analysed with an artificial neural network: the role of hair mineralograms. Metabolites. https:\/\/doi.org\/10.3390\/METABO13060679","DOI":"10.3390\/METABO13060679"},{"key":"572_CR15","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1002\/JBMR.4292","volume":"36","author":"J Smets","year":"2021","unstructured":"Smets J, Shevroja E, H\u00fcgle T et al (2021) Machine learning solutions for osteoporosis\u2014a review. J Bone Min Res 36:833\u2013851. https:\/\/doi.org\/10.1002\/JBMR.4292","journal-title":"J Bone Min Res"},{"key":"572_CR16","doi-asserted-by":"publisher","first-page":"928","DOI":"10.3803\/ENM.2021.1111","volume":"36","author":"SH Kong","year":"2021","unstructured":"Kong SH, Shin CS (2021) Applications of machine learning in bone and mineral research. Endocrinol Metab 36:928\u2013937. https:\/\/doi.org\/10.3803\/ENM.2021.1111","journal-title":"Endocrinol Metab"},{"key":"572_CR17","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1016\/S0895-4356(98)00026-2","volume":"51","author":"AR Feinstein","year":"1998","unstructured":"Feinstein AR (1998) More history of medical statistics. J Clin Epidemiol 51:651\u2013655. https:\/\/doi.org\/10.1016\/S0895-4356(98)00026-2","journal-title":"J Clin Epidemiol"},{"key":"572_CR18","doi-asserted-by":"publisher","unstructured":"Yu AC, Mohajer B, Eng J (2022) External validation of deep learning algorithms for radiologic diagnosis: a systematic review. Radiol Artif Intell. https:\/\/doi.org\/10.1148\/RYAI.210064","DOI":"10.1148\/RYAI.210064"},{"key":"572_CR19","doi-asserted-by":"publisher","unstructured":"Mody E, Sellmeyer DE, Joy E et al (2024) Testing generalizability of crystal bone, an AI\/ML osteoporotic fracture risk prediction algorithm, using real-world evidence from three US health systems. Preprint at https:\/\/doi.org\/10.2196\/PREPRINTS.56967","DOI":"10.2196\/PREPRINTS.56967"},{"key":"572_CR20","doi-asserted-by":"publisher","unstructured":"Khanna VV, Chadaga K, Sampathila N et al (2023) A decision support system for osteoporosis risk prediction using machine learning and explainable artificial intelligence. Heliyon. https:\/\/doi.org\/10.1016\/J.HELIYON.2023.E22456","DOI":"10.1016\/J.HELIYON.2023.E22456"},{"key":"572_CR21","doi-asserted-by":"publisher","unstructured":"Massatith J, Boonnam N, Hama R (2023) Osteoporosis prognosis through machine learning analysis of X-ray films. Int Comput Sci Eng Conf. https:\/\/doi.org\/10.1109\/ICSEC59635.2023.10329706","DOI":"10.1109\/ICSEC59635.2023.10329706"},{"key":"572_CR22","doi-asserted-by":"publisher","unstructured":"Li Z, Zhao W, Lin X, Li F (2023) AI algorithms for accurate prediction of osteoporotic fractures in patients with diabetes: an up-to-date review. J Orthop Surg Res. https:\/\/doi.org\/10.1186\/S13018-023-04446-5","DOI":"10.1186\/S13018-023-04446-5"},{"key":"572_CR23","doi-asserted-by":"publisher","first-page":"e27277","DOI":"10.1371\/journal.pone.0027277","volume":"6","author":"C Eller-Vainicher","year":"2011","unstructured":"Eller-Vainicher C, Chiodini I, Santi I et al (2011) Recognition of morphometric vertebral fractures by artificial neural networks: analysis from GISMO lombardia database. PLoS One 6:e27277. https:\/\/doi.org\/10.1371\/journal.pone.0027277","journal-title":"PLoS One"},{"key":"572_CR24","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1002\/JBMR.5650080915","volume":"8","author":"HK Genant","year":"1993","unstructured":"Genant HK, Wu CY, van Kuijk C, Nevitt MC (1993) Vertebral fracture assessment using a semiquantitative technique. J Bone Min Res 8:1137\u20131148. https:\/\/doi.org\/10.1002\/JBMR.5650080915","journal-title":"J Bone Min Res"},{"key":"572_CR25","unstructured":"Chapman P, Clinton J, Kerber R et al (2000) CRISP-DM 1.0 step by step data mining guide. Available at https:\/\/the-modeling-agency.com\/crisp-dm.pdf"},{"key":"572_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/s0933-3657(02)00049-0","volume":"26","author":"KJMG Cios","year":"2002","unstructured":"Cios KJMG (2002) Uniqueness of medical data mining. Artif Intell Med 26:1\u201324. https:\/\/doi.org\/10.1016\/s0933-3657(02)00049-0","journal-title":"Artif Intell Med"},{"key":"572_CR27","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/S11135-012-9746-8\/METRICS","volume":"48","author":"E Grossi","year":"2014","unstructured":"Grossi E, Compare A, Buscema M (2014) The concept of individual semantic maps in clinical psychology: a feasibility study on a new paradigm. Qual Quant 48:15\u201335. https:\/\/doi.org\/10.1007\/S11135-012-9746-8\/METRICS","journal-title":"Qual Quant"},{"key":"572_CR28","doi-asserted-by":"crossref","unstructured":"Buscema M, Tastle WJ (2013) Intelligent data mining in law enforcement analytics: new neural networks applied to real problems. Springer, New York","DOI":"10.1007\/978-94-007-4914-6"},{"key":"572_CR29","unstructured":"Agrawal D, Bernstein P, Bertino E et al (2012) Challenges and opportunities with big data: a white paper prepared for the computing community consortium committee of the computing research association. Available online at: https:\/\/docs.lib.purdue.edu\/cctech\/1\/"},{"key":"572_CR30","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0012-365X(00)00224-7","volume":"233","author":"J Nesetril","year":"2001","unstructured":"Nesetril J, Milkova ENH (2001) Otakar Boruvka on minimum spanning tree problem: translation of both the 1926 papers, comments, history. Discret Math 233:3\u201336. https:\/\/doi.org\/10.1016\/S0012-365X(00)00224-7","journal-title":"Discret Math"},{"key":"572_CR31","doi-asserted-by":"publisher","unstructured":"Kruskal J (1956) On the shortest spanning subtree of a graph and the traveling salesman problem. In: Proceedings of the American Mathematical Society 48\u201350. Scientific Research. Available via https:\/\/doi.org\/10.1090\/S0002-9939-1956-0078686-7","DOI":"10.1090\/S0002-9939-1956-0078686-7"},{"key":"572_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41747-021-00242-0","volume":"5","author":"FM Ulivieri","year":"2021","unstructured":"Ulivieri FM, Rinaudo L, Messina C et al (2021) Bone Strain Index predicts fragility fracture in osteoporotic women: an artificial intelligence-based study. Eur Radio Exp 5:1\u201311. https:\/\/doi.org\/10.1186\/s41747-021-00242-0","journal-title":"Eur Radio Exp"},{"key":"572_CR33","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1504\/IJDMB.2008.022159","volume":"2","author":"M Buscema","year":"2008","unstructured":"Buscema M, Grossi E (2008) The semantic connectivity map: an adapting self-organising knowledge discovery method in data bases. Experience in gastro-oesophageal reflux disease. Int J Data Min Bioinform 2:362\u2013404","journal-title":"Int J Data Min Bioinform"},{"key":"572_CR34","doi-asserted-by":"publisher","unstructured":"Rinaudo L, Cuttone S, Messina C et al (2024) Generation and validation of normative, age-specific reference curves for bone strain index in women. Diagnostics. https:\/\/doi.org\/10.3390\/DIAGNOSTICS14101046","DOI":"10.3390\/DIAGNOSTICS14101046"},{"key":"572_CR35","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1056\/NEJM200105103441904","volume":"344","author":"RM Neer","year":"2001","unstructured":"Neer RM, Arnaud CD, Zanchetta JR et al (2001) Effect of parathyroid hormone (1\u201334) on fractures and bone mineral density in postmenopausal women with osteoporosis. N. Engl J Med 344:1434\u20131441. https:\/\/doi.org\/10.1056\/NEJM200105103441904","journal-title":"N. Engl J Med"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00572-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-025-00572-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00572-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T18:08:47Z","timestamp":1750788527000},"score":1,"resource":{"primary":{"URL":"https:\/\/eurradiolexp.springeropen.com\/articles\/10.1186\/s41747-025-00572-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["572"],"URL":"https:\/\/doi.org\/10.1186\/s41747-025-00572-3","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,24]]},"assertion":[{"value":"18 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"FMU is a member of the Scientific Editorial Board for European Radiology Experimental (section: musculoskeletal), and as such did not participate in the selection nor review processes for this article. The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"62"}}