{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T10:18:16Z","timestamp":1793441896059,"version":"4.5.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"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":["International Orthopaedics (SICOT)"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Secondary fragility fractures remain a major complication after hip fracture surgery in older adults, yet individualized postoperative risk stratification remains challenging. We aimed to identify factors associated with secondary fragility fracture and internally validate an interpretable machine-learning model for three\u00a0year refracture risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed adults aged\u2009\u2265\u200965\u00a0years who underwent surgery for a first low-energy hip fracture between 2014 and 2021. Patients were followed for three\u00a0years for secondary fragility fracture. Demographic, clinical, functional, and rehabilitation variables were extracted from electronic medical records. Cox regression with multiple imputation was performed to evaluate time-to-event associations. XGBoost was developed as the primary prediction model and compared with SVM and Cox regression. Model performance was assessed using a held-out test set and decision curve analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 4,418 patients, 594 (13.4%) sustained a secondary fragility fracture. Increased refracture risk was associated with older age, osteoporosis, low BMI, female sex, cardiovascular disease, visual impairment, syncope, non-standard rehabilitation, and postoperative Harris hip score\u2009&lt;\u200980. In the test set, XGBoost achieved an AUC of 0.701 (95% CI, 0.657\u20130.743), with 61.8% sensitivity and 67.2% specificity at the default threshold. Decision curve analysis demonstrated the highest net benefit for XGBoost across threshold probabilities of approximately 7%\u201332%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Secondary fragility fractures were associated with skeletal fragility, fall-related vulnerability, and impaired postoperative recovery. The interpretable XGBoost model showed moderate discrimination and potential clinical utility as an adjunctive screening tool to identify patients who may benefit from intensified secondary prevention. External validation and prospective evaluation are required before routine clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00264-026-07002-y","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T21:06:57Z","timestamp":1788815217000},"page":"2705-2717","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Secondary fragility fractures after hip fracture surgery in four thousand, four hundred and eighteen older adults: risk factors and internal validation of an interpretable machine-learning model"],"prefix":"10.1007","volume":"50","author":[{"given":"Shizan","family":"He","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3217-4606","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dajun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuquan","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huipeng","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weitao","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"issue":"8","key":"7002_CR1","doi-asserted-by":"publisher","first-page":"e552","DOI":"10.1016\/S2666-7568(24)00062-X","volume":"5","author":"E Armstrong","year":"2024","unstructured":"Armstrong E et al (2024) Time from injury to hip-fracture surgery in low-income and middle-income regions: a secondary analysis of data from the International Orthopaedic Multicentre Study in Fracture Care (INORMUS). Lancet Healthy Longev 5(8):e552\u2013e562","journal-title":"Lancet Healthy Longev"},{"issue":"8","key":"7002_CR2","doi-asserted-by":"publisher","first-page":"1064","DOI":"10.1002\/jbmr.4821","volume":"38","author":"CW Sing","year":"2023","unstructured":"Sing CW et al (2023) Global epidemiology of hip fractures: secular trends in incidence rate, post-fracture treatment, and all-cause mortality. J Bone Miner Res 38(8):1064\u20131075","journal-title":"J Bone Miner Res"},{"issue":"8","key":"7002_CR3","doi-asserted-by":"publisher","first-page":"e360","DOI":"10.1016\/S2666-7568(23)00102-2","volume":"4","author":"E Liu","year":"2023","unstructured":"Liu E (2023) Hip fractures: mortality, economic burden, and organisational factors for improved patient outcomes. Lancet Healthy Longev 4(8):e360\u2013e361","journal-title":"Lancet Healthy Longev"},{"issue":"8","key":"7002_CR4","doi-asserted-by":"publisher","first-page":"e386","DOI":"10.1016\/S2666-7568(23)00086-7","volume":"4","author":"P Baji","year":"2023","unstructured":"Baji P et al (2023) Organisational factors associated with hospital costs and patient mortality in the 365 days following hip fracture in England and Wales (REDUCE): a record-linkage cohort study. Lancet Healthy Longev 4(8):e386\u2013e398","journal-title":"Lancet Healthy Longev"},{"issue":"10225","key":"7002_CR5","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/S0140-6736(20)30058-1","volume":"395","author":"Investigators HA","year":"2020","unstructured":"Investigators HA (2020) Accelerated surgery versus standard care in hip fracture (HIP ATTACK): an international, randomised, controlled trial. Lancet 395(10225):698\u2013708","journal-title":"Lancet"},{"issue":"22","key":"7002_CR6","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1056\/NEJMoa2113514","volume":"385","author":"MD Neuman","year":"2021","unstructured":"Neuman MD et al (2021) Spinal anesthesia or general anesthesia for hip surgery in older adults. N Engl J Med 385(22):2025\u20132035","journal-title":"N Engl J Med"},{"key":"7002_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2024.102677","volume":"73","author":"R Prieto-Moreno","year":"2024","unstructured":"Prieto-Moreno R et al (2024) Effects of the ActiveHip+ mHealth intervention on the recovery of older adults with hip fracture and their family caregivers: a multicentre open-label randomised controlled trial. EClinicalMedicine 73:102677","journal-title":"EClinicalMedicine"},{"issue":"9","key":"7002_CR8","doi-asserted-by":"publisher","first-page":"1753","DOI":"10.1007\/s00198-021-05877-8","volume":"32","author":"JE Tarride","year":"2021","unstructured":"Tarride JE et al (2021) Incremental costs of fragility fractures: a population-based matched -cohort study from Ontario, Canada. Osteoporos Int 32(9):1753\u20131761","journal-title":"Osteoporos Int"},{"issue":"6","key":"7002_CR9","doi-asserted-by":"publisher","first-page":"1209","DOI":"10.1097\/CORR.0000000000002465","volume":"481","author":"Y Dong","year":"2023","unstructured":"Dong Y et al (2023) What was the epidemiology and global burden of disease of hip fractures from 1990 to 2019? Results from and additional analysis of the Global Burden of Disease Study 2019. Clin Orthop Relat Res 481(6):1209\u20131220","journal-title":"Clin Orthop Relat Res"},{"key":"7002_CR10","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-025-06871-z","author":"Y Yuan","year":"2025","unstructured":"Yuan Y et al (2025) Subsequent fracture risk after hip fracture surgery in China: a three-year retrospective cohort study. BMC Geriatr. https:\/\/doi.org\/10.1186\/s12877-025-06871-z","journal-title":"BMC Geriatr"},{"issue":"7","key":"7002_CR11","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2021-058983","volume":"12","author":"L Vranken","year":"2022","unstructured":"Vranken L et al (2022) Association between incident falls and subsequent fractures in patients attending the fracture liaison service after an index fracture: a 3-year prospective observational cohort study. BMJ Open 12(7):e058983","journal-title":"BMJ Open"},{"key":"7002_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.bonr.2023.101732","volume":"20","author":"L Wang","year":"2024","unstructured":"Wang L et al (2024) Risk prediction of second hip fracture by bone and muscle density of the hip varies with time after first hip fracture: a prospective cohort study. Bone Rep 20:101732","journal-title":"Bone Rep"},{"issue":"10","key":"7002_CR13","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.38393","volume":"7","author":"WK Silverstein","year":"2024","unstructured":"Silverstein WK et al (2024) Antiosteoporosis medication prescriptions after fragility fractures. JAMA Netw Open 7(10):e2438393","journal-title":"JAMA Netw Open"},{"key":"7002_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bone.2020.115550","volume":"141","author":"ML Brance","year":"2020","unstructured":"Brance ML et al (2020) High bone mass from mutation of low-density lipoprotein receptor-related protein 6 (LRP6). Bone 141:115550","journal-title":"Bone"},{"issue":"6","key":"7002_CR15","doi-asserted-by":"publisher","first-page":"4669","DOI":"10.1007\/s00068-022-01981-4","volume":"48","author":"JHF Oosterhoff","year":"2022","unstructured":"Oosterhoff JHF et al (2022) Development and internal validation of a clinical prediction model using machine learning algorithms for 90 day and 2 year mortality in femoral neck fracture patients aged 65 years or above. Eur J Trauma Emerg Surg 48(6):4669\u20134682","journal-title":"Eur J Trauma Emerg Surg"},{"issue":"1","key":"7002_CR16","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.230614","volume":"310","author":"Y Kim","year":"2024","unstructured":"Kim Y et al (2024) A CT-based deep learning model for predicting subsequent fracture risk in patients with hip fracture. Radiology 310(1):e230614","journal-title":"Radiology"},{"key":"7002_CR17","doi-asserted-by":"publisher","first-page":"215145932094602","DOI":"10.1177\/2151459320946021","volume":"11","author":"SR Konda","year":"2020","unstructured":"Konda SR et al (2020) Can we accurately predict which geriatric and middle-aged hip fracture patients will experience a delay to surgery? Geriatr Orthop Surg Rehabil 11:2151459320946021","journal-title":"Geriatr Orthop Surg Rehabil"},{"issue":"2","key":"7002_CR18","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/s00068-020-01565-0","volume":"48","author":"A Kristan","year":"2022","unstructured":"Kristan A et al (2022) When does hip fracture surgery delay affects the length of hospital stay? Eur J Trauma Emerg Surg 48(2):701\u2013708","journal-title":"Eur J Trauma Emerg Surg"},{"key":"7002_CR19","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11072021","author":"H Shimizu","year":"2022","unstructured":"Shimizu H et al (2022) Machine learning algorithms: prediction and feature selection for clinical refracture after surgically treated fragility fracture. J Clin Med. https:\/\/doi.org\/10.3390\/jcm11072021","journal-title":"J Clin Med"},{"key":"7002_CR20","doi-asserted-by":"publisher","first-page":"521","DOI":"10.2340\/17453674.2025.44248","volume":"96","author":"H Dijkstra","year":"2025","unstructured":"Dijkstra H et al (2025) Machine learning-based prediction of short- and long-term mortality for shared decision-making in older hip fracture patients: the Dutch Hip Fracture Audit algorithms in 74,396 cases. Acta Orthop 96:521\u2013528","journal-title":"Acta Orthop"},{"key":"7002_CR21","doi-asserted-by":"publisher","DOI":"10.3390\/jpm11080727","author":"MP Forssten","year":"2021","unstructured":"Forssten MP et al (2021) Predicting 1-year mortality after hip fracture surgery: an evaluation of multiple machine learning approaches. J Pers Med. https:\/\/doi.org\/10.3390\/jpm11080727","journal-title":"J Pers Med"},{"key":"7002_CR22","doi-asserted-by":"publisher","DOI":"10.1177\/20552076251406311","volume":"11","author":"H Pu","year":"2025","unstructured":"Pu H et al (2025) Machine learning for predicting extended length of stay in elderly patients with hip fractures: an enhanced recovery after surgery perspective. Digit Health 11:20552076251406311","journal-title":"Digit Health"},{"issue":"1","key":"7002_CR23","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1186\/s12967-020-02620-5","volume":"18","author":"N Hou","year":"2020","unstructured":"Hou N et al (2020) Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost. J Transl Med 18(1):462","journal-title":"J Transl Med"},{"issue":"3","key":"7002_CR24","first-page":"207","volume":"29","author":"Z Yang","year":"2023","unstructured":"Yang Z et al (2023) Epidemiological investigation of 387 individuals over 65 years old with osteoporotic fractures. Altern Ther Health Med 29(3):207\u2013211","journal-title":"Altern Ther Health Med"},{"issue":"2","key":"7002_CR25","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1001\/jamaophthalmol.2023.5858","volume":"142","author":"JY Tsang","year":"2024","unstructured":"Tsang JY et al (2024) Risk of falls and fractures in individuals with cataract, age-related macular degeneration, or glaucoma. JAMA Ophthalmol 142(2):96\u2013106","journal-title":"JAMA Ophthalmol"},{"issue":"1","key":"7002_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-64170-w","volume":"14","author":"N Tang","year":"2024","unstructured":"Tang N et al (2024) Risk analysis for subsequent fracture of osteoporotic fractures in Chinese women over age 60: a nationwide cross-sectional study. Sci Rep 14(1):13319","journal-title":"Sci Rep"},{"issue":"1","key":"7002_CR27","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1186\/s13018-023-04030-x","volume":"18","author":"S Meng","year":"2023","unstructured":"Meng S et al (2023) The prevalence of osteoporotic fractures in the elderly in China: a systematic review and meta-analysis. J Orthop Surg Res 18(1):536","journal-title":"J Orthop Surg Res"},{"key":"7002_CR28","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1616923","volume":"12","author":"B Qi","year":"2025","unstructured":"Qi B et al (2025) Machine learning-driven prediction of risk factors for postoperative re-fractures in elderly OVCF patients with underlying diseases: model development and validation. Front Med (Lausanne) 12:1616923","journal-title":"Front Med (Lausanne)"},{"key":"7002_CR29","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2022.914002","volume":"14","author":"Y Yang","year":"2022","unstructured":"Yang Y et al (2022) Development and validation of a nomogram for predicting postoperative delirium in patients with elderly hip fracture based on data collected on admission. Front Aging Neurosci 14:914002","journal-title":"Front Aging Neurosci"},{"key":"7002_CR30","doi-asserted-by":"publisher","first-page":"1263930","DOI":"10.3389\/fmed.2023.1263930","volume":"10","author":"J Liang","year":"2023","unstructured":"Liang J et al (2023) Development and validation of a predictive nomogram for subsequent contralateral hip fracture in elderly patients within 2 years after hip fracture surgery. Front Med (Lausanne) 10:1263930","journal-title":"Front Med (Lausanne)"},{"key":"7002_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105738","volume":"195","author":"J Wu","year":"2025","unstructured":"Wu J et al (2025) Construction and evaluation of prediction model for postoperative re-fractures in elderly patients with hip fractures. Int J Med Inform 195:105738","journal-title":"Int J Med Inform"},{"key":"7002_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-025-07757-x","author":"X Li","year":"2025","unstructured":"Li X et al (2025) Postoperative osteoporosis therapy and risk of re-fracture in elderly patients with hip fractures: a multicenter retrospective cohort study. Osteoporos Int. https:\/\/doi.org\/10.1007\/s00198-025-07757-x","journal-title":"Osteoporos Int"},{"issue":"1","key":"7002_CR33","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1007\/s11657-023-01215-z","volume":"18","author":"P Chotiyarnwong","year":"2023","unstructured":"Chotiyarnwong P et al (2023) Three-year outcomes of a fracture liaison service model at a university-based tertiary care hospital in Thailand. Arch Osteoporos 18(1):26","journal-title":"Arch Osteoporos"}],"container-title":["International Orthopaedics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00264-026-07002-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00264-026-07002-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00264-026-07002-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:09:49Z","timestamp":1790640589000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00264-026-07002-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":33,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["7002"],"URL":"https:\/\/doi.org\/10.1007\/s00264-026-07002-y","relation":{},"ISSN":["0341-2695","1432-5195"],"issn-type":[{"value":"0341-2695","type":"print"},{"value":"1432-5195","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"assertion":[{"value":"24 June 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}