{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T04:58:28Z","timestamp":1793422708347,"version":"4.5.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100024075","name":"Region Syddanmark","doi-asserted-by":"publisher","award":["22\/26197"],"award-info":[{"award-number":["22\/26197"]}],"id":[{"id":"10.13039\/501100024075","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006356","name":"University of Southern Denmark","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006356","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Arch Osteoporos"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>This study used explainable AI to improve the Danish FREM model for predicting one-year risk of major osteoporotic fractures in over 2.4 million individuals aged\u2009\u2265\u200945. A DART boosting algorithm improved performance (AUC 0.77), with explainable outputs aiding clinical interpretation and guiding referrals for fracture risk assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aimed to use explainable artificial intelligence to improve the Fracture Risk Evaluation Model (FREM), in the prediction of imminent (one-year) risk of major osteoporotic fractures (MOFs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      FREM\n                      <jats:sub>ML<\/jats:sub>\n                      was trained and validated using complete registry data extracted for the Danish population\u2009\u2265\u200945\u00a0years without previous osteoporosis diagnoses or treatment (N\u2009=\u20092,438,140). A Dropouts meet multiple Additive Regression Tree (DART) boosting algorithm was used. Predictors of MOFs (2022), automatically extracted for the 15-year lookback period (2007\u20132021), included hospital diagnoses, filled medication prescriptions, days since the last redemption of medications specific to fall and osteoporosis risk, as well as markers of polypharmacy and multi-morbidity. Stratified analyses were carried out, and model outputs were evaluated in the context of explainable artificial intelligence (AI).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      FREM\n                      <jats:sub>ML<\/jats:sub>\n                      displayed an overall area under the curve (95% confidence interval) of 0.77 (0.76, 0.77) \u2013 making it superior to previous versions of FREM. While age and sex were the most relevant predictors of MOF events, advanced feature engineering, including temporal information, contributed to model performance. Importantly, stratified analyses highlighted changing model performance across age groups and poorer prediction performance in males. Shapley Additive exPlanations values, a feature importance metric in explainable AI, facilitated clinical interpretation of relative MOF risk.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      The publicly available FREM\n                      <jats:sub>ML<\/jats:sub>\n                      boosting model, combined with explainable AI, may be an effective decision support approach in a physician\u2019s referral of individuals at high imminent risk of fractures to dual-energy X-ray absorptiometry.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11657-025-01613-5","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:30:51Z","timestamp":1762342251000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Introducing FREMML: a decision-support approach for automated identification of individuals at high imminent fracture risk"],"prefix":"10.1007","volume":"20","author":[{"given":"Marlene","family":"Rietz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan C.","family":"Br\u00f8nd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S\u00f6ren","family":"M\u00f6ller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"S\u00f8ndergaard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Abrahamsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katrine Hass","family":"Rubin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"issue":"1","key":"1613_CR1","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1080\/21556660.2019.1677674","volume":"8","author":"DT Gold","year":"2019","unstructured":"Gold DT et al (2019) Impact of fractures on quality of life in patients with osteoporosis: a US cross-sectional survey. J Drug Assess 8(1):175\u2013183","journal-title":"J Drug Assess"},{"issue":"4","key":"1613_CR2","doi-asserted-by":"publisher","DOI":"10.1136\/rmdopen-2023-003524","volume":"9","author":"ER Christensen","year":"2023","unstructured":"Christensen ER et al (2023) Excess mortality following a first and subsequent osteoporotic fracture: a Danish nationwide register-based cohort study on the mediating effects of comorbidities. RMD Open 9(4):e003524","journal-title":"RMD Open"},{"key":"1613_CR3","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-020-01621-9","author":"M Immonen","year":"2020","unstructured":"Immonen M et al (2020) Association between chronic diseases and falls among a sample of older people in Finland. BMC Geriatr. https:\/\/doi.org\/10.1186\/s12877-020-01621-9","journal-title":"BMC Geriatr"},{"issue":"4","key":"1613_CR4","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1177\/2042098613486829","volume":"4","author":"MR de Jong","year":"2013","unstructured":"de Jong MR, Van der Elst M, Hartholt KA (2013) Drug-related falls in older patients: implicated drugs, consequences, and possible prevention strategies. Ther Adv Drug Saf 4(4):147\u2013154","journal-title":"Ther Adv Drug Saf"},{"key":"1613_CR5","unstructured":"Rosen HN. Drugs that affect bone metabolism [Internet]. Waltham (MA): UpToDate; 2025 Aug 11 [cited 2025 Sep 29]. Available from https:\/\/www.uptodate.com\/contents\/drugs-that-affect-bone-metabolism"},{"issue":"8","key":"1613_CR6","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1002\/jbmr.5650090802","volume":"9","author":"JA Kanis","year":"1994","unstructured":"Kanis JA et al (1994) The diagnosis of osteoporosis. J Bone Miner Res 9(8):1137\u20131141","journal-title":"J Bone Miner Res"},{"issue":"3","key":"1613_CR7","first-page":"201","volume":"11","author":"R Bernabei","year":"2014","unstructured":"Bernabei R et al (2014) Screening, diagnosis and treatment of osteoporosis: a brief review. Clin Cases Miner Bone Metab 11(3):201\u2013207","journal-title":"Clin Cases Miner Bone Metab"},{"issue":"3","key":"1613_CR8","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/s40618-023-02219-9","volume":"47","author":"M Schini","year":"2024","unstructured":"Schini M et al (2024) An overview of the use of the fracture risk assessment tool (FRAX) in osteoporosis. J Endocrinol Invest 47(3):501\u2013511","journal-title":"J Endocrinol Invest"},{"issue":"1","key":"1613_CR9","doi-asserted-by":"publisher","first-page":"e6","DOI":"10.1016\/S2666-7568(22)00293-8","volume":"4","author":"CL Gregson","year":"2023","unstructured":"Gregson CL (2023) Cfracture, an alternative to QFracture that accounts for mortality to better predict fragility fracture risk. Lancet Healthy Longev 4(1):e6\u2013e7","journal-title":"Lancet Healthy Longev"},{"issue":"3","key":"1613_CR10","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s00198-021-06252-3","volume":"33","author":"A Agarwal","year":"2022","unstructured":"Agarwal A et al (2022) Predictive performance of the Garvan Fracture Risk Calculator: a registry-based cohort study. Osteoporos Int 33(3):541\u2013548","journal-title":"Osteoporos Int"},{"issue":"11","key":"1613_CR11","doi-asserted-by":"publisher","first-page":"1967","DOI":"10.1002\/jbmr.3528","volume":"33","author":"KH Rubin","year":"2018","unstructured":"Rubin KH et al (2018) A new fracture risk assessment tool (FREM) based on public health registries. J Bone Miner Res 33(11):1967\u20131979","journal-title":"J Bone Miner Res"},{"key":"1613_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2021.115934","volume":"147","author":"MK Skj\u00f8dt","year":"2021","unstructured":"Skj\u00f8dt MK et al (2021) Validation of the fracture risk evaluation model (FREM) in predicting major osteoporotic fractures and hip fractures using administrative health data. Bone 147:115934","journal-title":"Bone"},{"issue":"1","key":"1613_CR13","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s00198-021-06165-1","volume":"33","author":"S M\u00f6ller","year":"2022","unstructured":"M\u00f6ller S et al (2022) Prediction of imminent fracture risk in Canadian women and men aged 45 years or older: external validation of the fracture risk evaluation model (FREM). Osteoporos Int 33(1):57\u201366","journal-title":"Osteoporos Int"},{"key":"1613_CR14","doi-asserted-by":"publisher","unstructured":"M\u00f6ller S, Rietz M, Petersen FL, Br\u00f8nd JC, Skj\u00f8dt MK, S\u00f8ndergaard J, Abrahamsen B, Rubin KH (2025). An enhanced Fracture Risk Evaluation Model (FREM) using national health data on morbidity and medications. J Bone Miner Res. https:\/\/doi.org\/10.1093\/jbmr\/zjaf156","DOI":"10.1093\/jbmr\/zjaf156"},{"issue":"10","key":"1613_CR15","doi-asserted-by":"publisher","DOI":"10.2196\/22550","volume":"22","author":"YA Almog","year":"2020","unstructured":"Almog YA et al (2020) Deep learning with electronic health records for short-term fracture risk identification: crystal bone algorithm development and validation. J Med Internet Res 22(10):e22550","journal-title":"J Med Internet Res"},{"key":"1613_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2024.102877","author":"P Nordstr\u00f6m","year":"2024","unstructured":"Nordstr\u00f6m P et al (2024) A novel clinical prediction model for hip fractures: a development and validation study in the total population of Sweden. eClinicalMedicine. https:\/\/doi.org\/10.1016\/j.eclinm.2024.102877","journal-title":"eClinicalMedicine"},{"issue":"5","key":"1613_CR17","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2023-076640","volume":"14","author":"M Bruun-Jensen","year":"2024","unstructured":"Bruun-Jensen M et al (2024) DARE-ISC model for prediction of 1-year ischaemic stroke risk in the general population and atrial fibrillation patients: a Danish nationwide cohort study. BMJ Open 14(5):e076640","journal-title":"BMJ Open"},{"issue":"8","key":"1613_CR18","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1016\/S2213-8587(24)00153-0","volume":"12","author":"N Hong","year":"2024","unstructured":"Hong N et al (2024) The potential role for artificial intelligence in fracture risk prediction. Lancet Diabetes Endocrinol 12(8):596\u2013600","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"8","key":"1613_CR19","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s10654-014-9930-3","volume":"29","author":"M Schmidt","year":"2014","unstructured":"Schmidt M (2014) The danish civil registration system as a tool in epidemiology. Eur J Epidemiol 29(8):541\u2013549","journal-title":"Eur J Epidemiol"},{"issue":"3","key":"1613_CR20","first-page":"798","volume":"46","author":"A Potteg\u00e5rd","year":"2017","unstructured":"Potteg\u00e5rd A, Schmidt SA, Wallach-Kildemoes H, S\u00f8rensen HT, Hallas J, Schmidt M (2017) Data resource profile: the danish national prescription registry. Int J Epidemiol 46(3):798","journal-title":"Int J Epidemiol"},{"key":"1613_CR21","doi-asserted-by":"publisher","first-page":"449","DOI":"10.2147\/CLEP.S91125","volume":"17","author":"M Schmidt","year":"2015","unstructured":"Schmidt M, Schmidt SA, Sandegaard JL, Ehrenstein V, Pedersen L, S\u00f8rensen HT (2015) The danish national patient registry: a review of content, data quality, and research potential. Clinic Epidemiol 17:449\u201390","journal-title":"Clinic Epidemiol"},{"issue":"1","key":"1613_CR22","doi-asserted-by":"publisher","DOI":"10.1186\/s41512-023-00158-w","volume":"7","author":"SB Kristensen","year":"2023","unstructured":"Kristensen SB et al (2023) An enhanced version of FREM (fracture risk evaluation model) using national administrative health data: analysis protocol for development and validation of a multivariable prediction model. Diagn Progn Res 7(1):19","journal-title":"Diagn Progn Res"},{"key":"1613_CR23","doi-asserted-by":"publisher","first-page":"257","DOI":"10.2147\/CLEP.S444447","volume":"16","author":"A Clausen","year":"2024","unstructured":"Clausen A et al (2024) Validity of major osteoporotic fracture diagnoses in the Danish National Patient Registry. Clin Epidemiol 16:257\u2013266","journal-title":"Clin Epidemiol"},{"key":"1613_CR24","doi-asserted-by":"publisher","DOI":"10.1186\/s12891-018-2060-4","author":"M-T Puth","year":"2018","unstructured":"Puth M-T et al (2018) Prevalence and comorbidity of osteoporosis\u2013 a cross-sectional analysis on 10,660 adults aged 50 years and older in Germany. BMC Musculoskelet Disord. https:\/\/doi.org\/10.1186\/s12891-018-2060-4","journal-title":"BMC Musculoskelet Disord"},{"issue":"6","key":"1613_CR25","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1093\/aje\/kwq433","volume":"173","author":"H Quan","year":"2011","unstructured":"Quan H et al (2011) Updating and validating the Charlson comorbidity index and score for risk adjustment in hospital discharge abstracts using data from 6 countries. Am J Epidemiol 173(6):676\u2013682","journal-title":"Am J Epidemiol"},{"key":"1613_CR26","unstructured":"Kuhn M, For the caret package authors. Caret: classification and regression training [Internet]. Version 7.0-1; 2024 Dec 10 [cited 2025 Sep 29]. Available from https:\/\/cran.r-project.org\/web\/packages\/caret\/caret.pdf"},{"key":"1613_CR27","first-page":"3146","volume-title":"Advances in neural information processing systems 30 (NeurIPS 2017)","author":"G Ke","year":"2017","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu T-Y (2017) LightGBM: a highly efficient gradient boosting decision tree. In: Guyon I, Luxburg UV, Bengio S et al (eds) Advances in neural information processing systems 30 (NeurIPS 2017). Curran Associates, Inc., Red Hook (NY), pp 3146\u20133154"},{"key":"1613_CR28","first-page":"1","volume":"L168","author":"European Union","year":"2024","unstructured":"Union European (2024) Regulation (EU) 2024\/1689 (artificial intelligence act). Off J Eur Union L168:1\u2013178","journal-title":"Off J Eur Union"},{"issue":"1","key":"1613_CR29","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1007\/s11657-022-01061-5","volume":"17","author":"CL Gregson","year":"2022","unstructured":"Gregson CL et al (2022) UK clinical guideline for the prevention and treatment of osteoporosis. Arch Osteoporos 17(1):58","journal-title":"Arch Osteoporos"},{"issue":"7","key":"1613_CR30","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1136\/jech-2019-213435","volume":"74","author":"A H\u00f6hn","year":"2020","unstructured":"H\u00f6hn A et al (2020) Do men avoid seeking medical advice? A register-based analysis of gender-specific changes in primary healthcare use after first hospitalisation at ages 60+ in Denmark. J Epidemiol Community Health 74(7):573","journal-title":"J Epidemiol Community Health"},{"issue":"1","key":"1613_CR31","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1007\/s11657-020-00846-w","volume":"15","author":"WD Leslie","year":"2020","unstructured":"Leslie WD, Lix LM, Binkley N (2020) Comparison of screening tools for optimizing fracture prevention in Canada. Arch Osteoporos 15(1):170","journal-title":"Arch Osteoporos"},{"issue":"1","key":"1613_CR32","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/s11657-013-0126-3","volume":"8","author":"L Hansen","year":"2013","unstructured":"Hansen L et al (2013) A health economic analysis of osteoporotic fractures: who carries the burden? Arch Osteoporos 8(1):126","journal-title":"Arch Osteoporos"},{"issue":"10","key":"1613_CR33","doi-asserted-by":"publisher","first-page":"e635","DOI":"10.1016\/S2589-7500(23)00155-3","volume":"5","author":"UK Wiil","year":"2023","unstructured":"Wiil UK (2023) Important steps for artificial intelligence-based risk assessment of older adults. Lancet Digit Health 5(10):e635\u2013e636","journal-title":"Lancet Digit Health"},{"key":"1613_CR34","unstructured":"CHOICE - Continuous Healthcare in OsteoporosIs CasE-finding. Available from: https:\/\/choice.rsyd.dk\/about-the-project."}],"container-title":["Archives of Osteoporosis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11657-025-01613-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11657-025-01613-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11657-025-01613-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T21:17:02Z","timestamp":1766524622000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11657-025-01613-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1613"],"URL":"https:\/\/doi.org\/10.1007\/s11657-025-01613-5","relation":{},"ISSN":["1862-3514"],"issn-type":[{"value":"1862-3514","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"assertion":[{"value":"26 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 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":"Register-based studies do not require approval by an ethics committee according to Danish law. The study was approved by the Danish Data Protection Agency (journal number: 2008\u201358-0035).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"JS: Advisory boards for Abbott Rapid Diagnostics, Novo Nordisk, and Astra Zeneca. Given a lecture sponsored by Boehringer Ingelheim. All outside the current work. BA: Institutional research grants from UCB and Kyowa-Kirin and consulting fees from UCB, Kyowa-Kirin, and Pharmacosmos outside the current work. The other authors do not declare any conflicting interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"140"}}