Artificial Intelligence for Fracture Risk Prediction: A Bibliometric Analysis of Research Hotspots and Evolutionary Trends
DOI:
https://doi.org/10.65455/7tc70w72关键词:
Artificial Intelligence, Fracture Risk Prediction, Machine Learning, Bibliometric Analysis摘要
Artificial intelligence (AI) has emerged as a promising approach for improving fracture risk prediction. This study aimed to provide a comprehensive bibliometric overview of research on AI in fracture risk prediction by mapping its temporal evolution, collaborative structure, thematic framework, and disciplinary distribution. Publications were retrieved from the Web of Science Core Collection using a predefined search strategy covering January 2001 to December 2025, including only English-language articles and reviews. After screening and data cleaning, a total of 943 publications were analyzed. Bibliometric analyses were conducted using VOSviewer (v1.6.20) and the Bibliometrix R package (v4.5.1), examining annual publication trends, co-authorship networks at the author, institutional, and country levels, keyword co-occurrence clusters, and subject category distributions. The results showed that research output exhibited three developmental phases, with a marked acceleration after 2020. Collaboration networks demonstrated a clustered and moderately centralized structure, with core institutions and countries—particularly the United States and major European partners—occupying central positions. Keyword co-occurrence analysis identified four principal thematic clusters: AI-based predictive modeling, imaging-derived radiomics and opportunistic screening, FRAX-centered clinical risk assessment, and comorbidity- and pharmacotherapy-related applications. Subject category analysis further revealed progressive interdisciplinary integration, with increasing contributions from radiology and computer science alongside traditional clinical specialties. Overall, AI-based fracture risk prediction research has evolved from clinically grounded risk stratification toward computationally augmented, imaging-integrated, and translationally oriented predictive frameworks. The field demonstrates rapid growth, expanding international collaboration, and increasing interdisciplinary convergence, suggesting continued advancement toward real-world clinical implementation.
参考
[1]FOR THE INTERNATIONAL OSTEOPOROSIS FOUNDATION, BORGSTRÖM F, KARLSSON L, ORTSÄTER G, et al. Fragility fractures in Europe: burden, management and opportunities. Archives of Osteoporosis, 2020, 15(1): 59. DOI: https://doi.org/10.1007/s11657-020-0706-y
[2]BAI F, LENG M, ZHANG Y, et al. Effectiveness of intensive versus regular or no exercise in older adults after hip fracture surgery: A systematic review and meta-analysis. Brazilian Journal of Physical Therapy, 2023, 27(1): 100482. DOI: https://doi.org/10.1016/j.bjpt.2023.100482
[3]KIM H, KIM J H, KIM M J, et al. Low Predictive Value of FRAX Adjusted by Trabecular Bone Score for Osteoporotic Fractures in Korean Women: A Community-Based Cohort Study. Endocrinology and Metabolism, 2020, 35(2): 359–366. DOI: https://doi.org/10.3803/EnM.2020.35.2.359
[4]TOPOL E J. High-performance medicine: the convergence of human and artificial intelligence. Nature Medicine, 2019, 25(1): 44–56. DOI: https://doi.org/10.1038/s41591-018-0300-7
[5]SHEVROJA E, CAFARELLI F P, GUGLIELMI G, et al. DXA parameters, Trabecular Bone Score (TBS) and Bone Mineral Density (BMD), in fracture risk prediction in endocrine-mediated secondary osteoporosis. Endocrine, 2021, 74(1): 20–28. DOI: https://doi.org/10.1007/s12020-021-02806-x
[6]WANG J, WANG Y, REN J, et al. Emerging applications of feature selection in osteoporosis research: from biomarker discovery to clinical decision support. Journal of Bone and Mineral Research, 2025, 40(10): 1106–1113. DOI: https://doi.org/10.1093/jbmr/zjaf105
[7]LI Y, LIANG Z, LI Y, et al. Machine learning value in the diagnosis of vertebral fractures: A systematic review and meta-analysis. European Journal of Radiology, 2024, 181: 111714. DOI: https://doi.org/10.1016/j.ejrad.2024.111714
[8]VAN DER VELDEN B H M, KUIJF H J, GILHUIJS K G A, et al. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis. Medical Image Analysis, 2022, 79: 102470. DOI: https://doi.org/10.1016/j.media.2022.102470
[9]BOYACK K W, KLAVANS R. Co‐citation analysis, bibliographic coupling, and direct citation: Which citation approach represents the research front most accurately? Journal of the American Society for Information Science and Technology, 2010, 61(12): 2389–2404. DOI: https://doi.org/10.1002/asi.21419
[10]TSENG W J, HUNG L W, SHIEH J S, et al. Hip fracture risk assessment: artificial neural network outperforms conditional logistic regression in an age- and sex-matched case control study. BMC Musculoskeletal Disorders, 2013, 14(1): 207. DOI: https://doi.org/10.1186/1471-2474-14-207
[11]WRIGHT N C, SAAG K G. From Fracture Risk Prediction to Evaluating Fracture Patterns: Recent Advances in the Epidemiology of Osteoporosis. Current Rheumatology Reports, 2012, 14(3): 205–211. DOI: https://doi.org/10.1007/s11926-012-0251-9
[12]FERIZI U, BESSER H, HYSL P, et al. Artificial Intelligence Applied to Osteoporosis: A Performance Comparison of Machine Learning Algorithms in Predicting Fragility Fractures From MRI Data. Journal of Magnetic Resonance Imaging, 2019, 49(4): 1029–1038. DOI: https://doi.org/10.1002/jmri.26280
[13]MUEHLEMATTER U J, MANNIL M, BECKER A S, et al. Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning. European Radiology, 2019, 29(5): 2207–2217. DOI: https://doi.org/10.1007/s00330-018-5846-8
[14]KONG S H. Incorporating Artificial Intelligence into Fracture Risk Assessment: Using Clinical Imaging to Predict the Unpredictable. Endocrinology and Metabolism, 2025, 40(4): 499–507. DOI: https://doi.org/10.3803/EnM.2025.2518
[15]WANG A, MA Z, WANG T, et al. Deep Learning–Assisted Automated Diagnosis of Osteoporosis Based on Computed Tomography Scans: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 2025, 27: e77155. DOI: https://doi.org/10.2196/77155
[16]KANIS J A, HARVEY N C, MCCLOSKEY E, et al. Algorithm for the management of patients at low, high and very high risk of osteoporotic fractures. Osteoporosis International, 2020, 31(1): 1–12. DOI: https://doi.org/10.1007/s00198-019-05176-3
[17]HONG N, CHO S W, LEE Y H, et al. Deep learning-based identification of vertebral fracture and osteoporosis in lateral spine radiographs and DXA vertebral fracture assessment to predict incident fracture. Journal of Bone and Mineral Research, 2025, 40(5): 628–638. DOI: https://doi.org/10.1093/jbmr/zjaf050
[18]XU J, WEN X, SUN L, et al. Large Model Era: Deep Learning in Osteoporosis Drug Discovery. Journal of Chemical Information and Modeling, 2025, 65(5): 2232–2244. DOI: https://doi.org/10.1021/acs.jcim.4c02264
[19]LEI M, FENG T, CHEN M, et al. Establishment and validation of an artificial intelligence web application for predicting postoperative in-hospital mortality in patients with hip fracture: a national cohort study of 52 707 cases. International Journal of Surgery, 2024, 110(8): 4876–4892. DOI: https://doi.org/10.1097/JS9.0000000000001599
[20]OOSTERHOFF J H F, SAVELBERG A B M C, KARHADE A V, et al. 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. European Journal of Trauma and Emergency Surgery, 2022, 48(6): 4669–4682. DOI: https://doi.org/10.1007/s00068-022-01981-4
[21]OOSTERHOFF J H F, KARHADE A V, GROOT O Q, et al. Intercontinental validation of a clinical prediction model for predicting 90-day and 2-year mortality in an Israeli cohort of 2033 patients with a femoral neck fracture aged 65 or above. European Journal of Trauma and Emergency Surgery, 2023, 49(3): 1545–1553. DOI: https://doi.org/10.1007/s00068-023-02237-5
[22]LIU F, LIU C, TANG X, et al. Predictive Value of Machine Learning Models in Postoperative Mortality of Older Adults Patients with Hip Fracture: A Systematic Review and Meta-analysis. Archives of Gerontology and Geriatrics, 2023, 115: 105120. DOI: https://doi.org/10.1016/j.archger.2023.105120
[23]OH J, PARK M, CHA Y, et al. Machine learning–based survival models for predicting rehospitalization of older hip fracture patients: a retrospective cohort study. BMC Musculoskeletal Disorders, 2025, 26(1): 451. DOI: https://doi.org/10.1186/s12891-025-08829-z
[24]HAN X, ZHANG J H, ZHAO X, et al. Interpretable machine learning for predicting optimal surgical timing in polytrauma patients with TBI and fractures to reduce postoperative infection risk. Scientific Reports, 2025, 15(1): 18347. DOI: https://doi.org/10.1038/s41598-025-04003-6
[25]HAYAT M T, ALLAWI Y M, ALAMRO W, et al. A Hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM)–Attention Model Architecture for Precise Medical Image Analysis and Disease Diagnosis. Diagnostics, 2025, 15(21): 2673. DOI: https://doi.org/10.3390/diagnostics15212673
[26]SALUNKE D, JOSHI G, INAMDAR S, et al. Osteoporosis classification using VGG-16 and logistic regression: A radiograph and BMD data approach. Intelligent Decision Technologies, 2025, 19(1): 395–413. DOI: https://doi.org/10.3233/IDT-240227
[27]SHANG P, LIU Q, MU H, et al. Enhanced risk prediction of femoral head osteonecrosis in the elderly: a comparative study of random forest and logistic regression models. Frontiers in Medicine, 2025, 12: 1640085. DOI: https://doi.org/10.3389/fmed.2025.1640085
[28]SUN D, WEN Y, YU Q, et al. Prediction models for adjacent vertebral fractures after vertebral augmentation: a systematic review and meta-analysis. European Spine Journal, 2025, 34(5): 1631–1640. DOI: https://doi.org/10.1007/s00586-025-08785-1
[29]DAI H, WANG Y, FU R, et al. Radiomics and stacking regression model for measuring bone mineral density using abdominal computed tomography. Acta Radiologica, 2023, 64(1): 228–236. DOI: https://doi.org/10.1177/02841851211068149
[30]RABINA A, MAHMUDA N, TANVIR R F. Machine learning based finite element analysis (FEA) surrogate for hip fracture risk assessment and visualization. Expert Systems with Applications, 2025, 264. DOI: https://doi.org/10.1016/j.eswa.2024.125916
[31]VALENTINITSCH A, TREBESCHI S, KAESMACHER J, et al. Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures. Osteoporosis International, 2019, 30(6): 1275–1285. DOI: https://doi.org/10.1007/s00198-019-04910-1
[32]ADAMI G, BIFFI A, PORCU G, et al. A systematic review on the performance of fracture risk assessment tools: FRAX, DeFRA, FRA-HS. Journal of Endocrinological Investigation, 2023, 46(11): 2287–2297. DOI: https://doi.org/10.1007/s40618-023-02082-8
[33]JAIN R K, LIU J Y, GRANT R W, et al. Biases in the performance of FRAX without BMD in predicting fracture risk in a multiethnic population with diabetes: the Diabetes and Aging Study. Journal of Bone and Mineral Research, 2025, 40(4): 478–491. DOI: https://doi.org/10.1093/jbmr/zjaf012
[34]CHRISTENSEN E R, LETH K W, PETERSEN F L, et al. Prediction of imminent osteoporotic fracture risk in Danish postmenopausal women—can the addition of self-reported clinical risk factors improve the prediction of the register-based FREM algorithm? Archives of Osteoporosis, 2025, 20(1): 21. DOI: https://doi.org/10.1007/s11657-024-01493-1
[35]ALESSANDRO D S, NICOLA M, EMANUELE P, et al. Influence of hand grip strength test and short physical performance battery on FRAX in post-menopausal women: a machine learning cross-sectional study. Journal of Sports Medicine and Physical Fitness, 2023, 64(3): 293–300. DOI: https://doi.org/10.23736/S0022-4707.23.15417-X
[36]HE Y, LIN J, ZHU S, et al. Deep learning in the radiologic diagnosis of osteoporosis: a literature review. Journal of International Medical Research, 2024, 52(4): 03000605241244754. DOI: https://doi.org/10.1177/03000605241244754
[37]TU J B, LIAO W J, LIU W C, et al. Using machine learning techniques to predict the risk of osteoporosis based on nationwide chronic disease data. Scientific Reports, 2024, 14(1): 5245. DOI: https://doi.org/10.1038/s41598-024-56114-1
[38]SCHOUSBOE J T, LIX L M, MORIN S N, et al. Vertebral Fracture Assessment Increases Use of Pharmacologic Therapy for Fracture Prevention in Clinical Practice. Journal of Bone and Mineral Research, 2019, 34(12): 2205–2212. DOI: https://doi.org/10.1002/jbmr.3836
[39]ANSARI H, FUNG K, CHEUNG A M, et al. Outcomes following hip fracture surgery in adults with schizophrenia in Ontario, Canada: A 10-year population-based retrospective cohort study. General Hospital Psychiatry, 2024, 89: 60–68. DOI: https://doi.org/10.1016/j.genhosppsych.2024.05.010
[40]MASAYUKI I, RENAUD W, J T, et al. Predictive ability of novel volumetric and geometric indices derived from dual-energy X-ray absorptiometric images of the proximal femur for hip fracture compared with conventional areal bone mineral density: the Japanese Population-based Osteoporosis (JPOS) Cohort Study. Osteoporosis International, 2021, 32(11): 2289–2299. DOI: https://doi.org/10.1007/s00198-021-06013-2
[41]LU S, FUGGLE N R, WESTBURY L D, et al. Machine learning applied to HR-pQCT images improves fracture discrimination provided by DXA and clinical risk factors. Bone, 2023, 168: 116653. DOI: https://doi.org/10.1016/j.bone.2022.116653
[42]ZHENG B, YU P, ZHU Z, et al. Machine learning integration of multi-modal radiomics and clinical factors predicts refracture risk after percutaneous kyphoplasty in postmenopausal women. Scientific Reports, 2025, 15(1): 38016. DOI: https://doi.org/10.1038/s41598-025-21894-7
[43]FAN S T, LU M, DONG J L, et al. Application of artificial intelligence in osteoporosis: a review. Frontiers in Medicine, 2025, 12: 1718554. DOI: https://doi.org/10.3389/fmed.2025.1718554
[44]NAMKI H, DANIELLE E W, CLAUS-C G, et al. The potential role for artificial intelligence in fracture risk prediction. The Lancet Diabetes & Endocrinology, 2024, 12(8): 596–600. DOI: https://doi.org/10.1016/S2213-8587(24)00153-0
[45]KAYAN K, JOHANSSON H, ODEN A, et al. Can fall risk be incorporated into fracture risk assessment algorithms: a pilot study of responsiveness to clodronate. Osteoporosis International, 2009, 20(12): 2055–2061. DOI: https://doi.org/10.1007/s00198-009-0942-x
[46]MCCLOSKEY E V, JOHANSSON H, ODEN A, et al. Ten-year fracture probability identifies women who will benefit from clodronate therapy—additional results from a double-blind, placebo-controlled randomised study. Osteoporosis International, 2009, 20(5): 811–817. DOI: https://doi.org/10.1007/s00198-008-0786-9
[47]THEVENOT J, HIRVASNIEMI J, PULKKINEN P, et al. Assessment of Risk of Femoral Neck Fracture with Radiographic Texture Parameters: A Retrospective Study. Radiology, 2014, 272(1): 184–191. DOI: https://doi.org/10.1148/radiol.14131390
[48]PICKHARDT P J, GRAFFY P M, ZEA R, et al. Automated Abdominal CT Imaging Biomarkers for Opportunistic Prediction of Future Major Osteoporotic Fractures in Asymptomatic Adults. Radiology, 2020, 297(1): 64–72. DOI: https://doi.org/10.1148/radiol.2020200466
[49]SCHILCHER J, NILSSON A, ANDLID O, et al. Fusion of electronic health records and radiographic images for a multimodal deep learning prediction model of atypical femur fractures. Computers in Biology and Medicine, 2024, 168: 107704. DOI: https://doi.org/10.1016/j.compbiomed.2023.107704
[50]ALSHRAIDEH M, AL-DHAQM A, ALSHAMMARI A, et al. Advanced Prediction of Recurrent Fragility Fractures Using Large Language Models. IEEE Access, 2025, 13: 71503–71520. DOI: https://doi.org/10.1109/ACCESS.2025.3562259
##submission.downloads##
已出版
##submission.license##
##submission.copyrightStatement##
##submission.license.cc.by4.footer##