J Shanghai Jiaotong Univ Sci

Journal of Shanghai Jiaotong University(Science) >

2026 , Vol. 31 >Issue 3: 759 - 770

DOI: https://doi.org/10.1007/s12204-026-2923-z

Celebrating 30 Years

Predicting Fracture Risk in Elderly Patients with Osteoporosis: Advances in Clinical Prediction Tools and Machine Learning Techniques

Expand
  • 1. School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China; 2. Department of Clinical Pharmacy, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200092, China; 3. Department of Science and Information, Hospital Management Service Center of Wuhou District, Chengdu, Chengdu 610041, China; 4. Department of Nuclear Medicine, Xinhua Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200092, China; 5. Shanghai Key Laboratory of Scalable Computing and Systems; School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China)

Received date: 2025-10-10

  Revised date: 2025-12-25

  Accepted date: 2025-12-26

  Online published: 2026-05-16

Fold

Abstract

Osteoporotic fractures pose a growing public health burden in aging populations with chronic comorbidities. Current fracture risk tools (e.g., FRAX and QFracture) remain limited by static assessment frameworks and inadequate racial adaptation. Artificial intelligence (AI), particularly multimodal deep learning and temporal modeling, demonstrates superior predictive accuracy in elderly patients with osteoporosis by integrating dynamic physiological, genetic, and clinical variables. This review critically evaluates the clinical applicability of existing prediction tools and synthesizes advances in AI-driven modeling, highlighting four transformative frontiers: multimodal data fusion (imaging, genomics, and real-world monitoring), temporal analysis, meta-learning for cross-population generalization, and interpretable AI for clinical transparency.

Cite this article

Zhang Xinxin, Yang Rui, Huang Yanli, Fu Hongliang, Jin Lei, Chen Ting, Niu Pei, Cheng Yunlong, Fu Wanting, Yuan Yue, Cheng Yunzhang, Zhang Jian, Xu Ajing . Predicting Fracture Risk in Elderly Patients with Osteoporosis: Advances in Clinical Prediction Tools and Machine Learning Techniques[J]. Journal of Shanghai Jiaotong University(Science), 2026 , 31(3) : 759 -770 . DOI: 10.1007/s12204-026-2923-z

References

[1] Consensus development conference: Diagnosis, prophylaxis, and treatment of osteoporosis [J]. The American Journal of Medicine, 1993, 94(6): 646-650.
[2] Kanis J A, McCloskey E V, Harvey N C, et al. Intervention thresholds and the diagnosis of osteoporosis [J]. Journal of Bone and Mineral Research, 2015, 30(10): 1747-1753.
[3] Johnston C B, Dagar M. Osteoporosis in older adults [J]. Medical Clinics of North America, 2020, 104(5): 873-884.
[4] Chinese Society of Osteoporosis and Bone Mineral Research. Guidelines for the diagnosis and management of primary osteoporosis (2017) [J]. Chinese Journal of Osteoporosis, 2019, 25(3): 281-309 (in Chinese).
[5] Chinese Society of Osteoporosis and Bone Mineral Research. Epidemiological investigation of osteoporosis in China and the release of the results of the special action of “healthy bones” [J]. Chinese Journal of Osteoporosis and Bone Mineral Research, 2019, 12(4): 317-318 (in Chinese).
[6] Wadhwa H, Isakoff K J, Pham N S, et al. Under-prescribed and underutilized: National trends in osteoporosis medication use after fragility fracture [J]. Bone, 2026, 206: 117835.
[7] Aibar-Almazán A, Voltes-Martínez A, Castellote-Caballero Y, et al. Current status of the diagnosis and management of osteoporosis [J]. International Journal of Molecular Sciences, 2022, 23(16): 9465.
[8] Strong K, Mathers C, Leeder S, et al. Preventing chronic diseases: How many lives can we save? [J]. The Lancet, 2005, 366(9496): 1578-1582.
[9] Boyd C M, Darer J, Boult C, et al. Clinical practice guidelines and quality of care for older patients with multiple comorbid diseases: Implications for pay for performance [J]. JAMA, 2005, 294(6): 716-724.
[10] Todorov G, Brook S, Quah Qin Xian N, et al. Comparison of fracture risk calculators in elderly fallers: A hospital-based cross-sectional study [J]. BMJ Open, 2022, 12(7): e060282.
[11] Li Z T, Zhao W, Lin X H, et al. AI algorithms for accurate prediction of osteoporotic fractures in patients with diabetes: An up-to-date review [J]. Journal of Orthopaedic Surgery and Research, 2023, 18(1): 956.
[12] National Institute for Health and Care Excellence. Osteoporosis: Assessing the risk of fragility fracture. Clinical guideline [EB/OL]. (2017-02-07) [2025-10-08]. https://www.nice.org.uk/guidance/cg146/resources/osteoporosis-assessing-the-risk-of-fragility-fracture-pru-df-35109574194373.
[13] Cozadd A J, Schroder L K, Switzer J A. Fracture risk assessment: An update [J]. Journal of Bone and Joint Surgery, 2021, 103(13): 1238-1246.
[14] Kanis J A, Johnell O, Oden A, et al. FRAX™ and the assessment of fracture probability in men and women from the UK [J]. Osteoporosis International, 2008, 19(4): 385-397.
[15] Dagan N, Cohen-Stavi C, Leventer-Roberts M, et al. External validation and comparison of three prediction tools for risk of osteoporotic fractures using data from population based electronic health records: Retrospective cohort study [J]. BMJ, 2017, 356: i6755.
[16] Schini M, Johansson H, Harvey N C, et al. An overview of the use of the fracture risk assessment tool (FRAX) in osteoporosis [J]. Journal of Endocrinological Investigation, 2024, 47(3): 501-511.
[17] El Miedany Y. FRAX: re-adjust or re-think [J]. Archives of Osteoporosis, 2020, 15(1): 150.
[18] Kanis J A, Johansson H, Oden A, et al. Worldwide uptake of FRAX [J]. Archives of Osteoporosis, 2014, 9(1): 166.
[19] Chinese Society of Osteoporosis and Bone Mineral Research. Guidelines for the diagnosis and treatment of primary osteoporosis (2022) [J]. Chinese General Practice, 2023, 26(14): 1671-1691 (in Chinese).
[20] Johannesdottir F, Aspelund T, Mahar S, et al. The relationship between fall risk, trochanteric soft tissue thickness, and hip fracture risk in older adults [J]. Journal of Bone and Mineral Research, 2025: zjaf161.
[21] Hippisley-Cox J, Coupland C. Predicting risk of osteoporotic fracture in men and women in England and Wales: Prospective derivation and validation of QFractureScores [J]. BMJ, 2009, 339: b4229.
[22] Hippisley-Cox J, Coupland C. Derivation and validation of updated QFracture algorithm to predict risk of osteoporotic fracture in primary care in the United Kingdom: Prospective open cohort study [J]. BMJ, 2012, 344: e3427.
[23] Agarwal A, Leslie W D. Fracture prediction tools in diabetes [J]. Current Opinion in Endocrinology, Diabetes, and Obesity, 2022, 29(4): 326-332.
[24] Dong Y J, Liu J. Tools for assessing the risk of osteoporosis: The application and comparison of FRAX QFracture Garvan [J]. Advances in Clinical Medicine, 2021, 11(1): 143-149 (in Chinese).
[25] Nguyen N D, Frost S A, Center J R, et al. Development of prognostic nomograms for individualizing 5-year and 10-year fracture risks [J]. Osteoporosis International, 2008, 19(10): 1431-1444.
[26] Sandhu S K, Nguyen N D, Center J R, et al. Prognosis of fracture: Evaluation of predictive accuracy of the FRAX™ algorithm and Garvan nomogram [J]. Osteoporosis International, 2010, 21(5): 863-871.
[27] Agarwal A, Leslie W D, Nguyen T V, et al. Performance of the garvan fracture risk calculator in individuals with diabetes: A registry-based cohort study [J]. Calcified Tissue International, 2022, 110(6): 658-665.
[28] Lam M T, Sing C W, Li G H Y, et al. Development and validation of a risk score to predict the first hip fracture in the oldest old: A retrospective cohort study [J]. The Journals of Gerontology: Series A, 2020, 75(5): 980-986.
[29] Nguyen N D, Frost S A, Center J R, et al. Development of a nomogram for individualizing hip fracture risk in men and women [J]. Osteoporosis International, 2007, 18(8): 1109-1117.
[30] Bolland M J, Siu A T, Mason B H, et al. Evaluation of the FRAX and Garvan fracture risk calculators in older women [J]. Journal of Bone and Mineral Research, 2011, 26(2): 420-427.
[31] Sambrook P N, Flahive J, Hooven F H, et al. Predicting fractures in an international cohort using risk factor algorithms without BMD [J]. Journal of Bone and Mineral Research, 2011, 26(11): 2770-2777.
[32] Langsetmo L, Nguyen T V, Nguyen N D, et al. Independent external validation of nomograms for predicting risk of low-trauma fracture and hip fracture [J]. CMAJ, 2011, 183(2): E107-E114.
[33] Lydick E, Cook K, Turpin J, et al. Development and validation of a simple questionnaire to facilitate identification of women likely to have low bone density [J]. The American Journal of Managed Care, 1998, 4(1): 37-48.
[34] Cadarette S M, Jaglal S B, Murray T M. Validation of the simple calculated osteoporosis risk estimation (SCORE) for patient selection for bone densitometry [J]. Osteoporosis International, 1999, 10(1): 85-90.
[35] Ben sedrine W, Devogelaer J P, Kaufman J M, et al. Evaluation of the simple calculated osteoporosis risk estimation (SCORE) in a sample of white women from Belgium [J]. Bone, 2001, 29(4): 374-380.
[36] Karkucak M, Capkin E, Kerimoglu S, et al. Performance of simple calculated osteoporosis risk estimation in a sample of women with suspected osteoporosis in the Turkish population [J]. Rheumatology International, 2008, 28(9): 825-830.
[37] Elliott M E, Meek P D, Kanous N L, et al. Osteoporosis screening by community pharmacists: Use of national osteoporosis foundation resources [J]. Journal of the American Pharmaceutical Association (1996), 2002, 42(1): 101-111.
[38] Berry S D, Kiel D P, Donaldson M G, et al. Application of the National Osteoporosis Foundation Guidelines to postmenopausal women and men: The Framingham Osteoporosis Study [J]. Osteoporosis International, 2010, 21(1): 53-60.
[39] Koh L K, Sedrine W B, Torralba T P, et al. A simple tool to identify Asian women at increased risk of osteoporosis [J]. Osteoporosis International, 2001, 12(8): 699-705.
[40] Nguyen A T, Bui T T, Tran N T M, et al. Validation of an osteoporosis self-assessment tool for Vietnamese postmenopausal women and men over 50 years [J]. Journal of Bone and Mineral Metabolism, 2025, 43(3): 274-283.
[41] Keskinbora K, Güven F. Artificial intelligence and ophthalmology [J]. Turkish Journal of Ophthalmology, 2020, 50(1): 37-43.
[42] Smets J, Shevroja E, Hügle T, et al. Machine learning solutions for osteoporosis: A review [J]. Journal of Bone and Mineral Research, 2021, 36(5): 833-851.
[43] Mi L H, Yuan J Y, Zhou Y K, et al. Text structured algorithm of lung cancer cases based on deep learning [J]. Journal of Shanghai Jiao Tong University (Science), 2025, 30(4): 778-789.
[44] Fasihi L, Tartibian B, Eslami R, et al. Artificial intelligence used to diagnose osteoporosis from risk factors in clinical data and proposing sports protocols [J]. Scientific Reports, 2022, 12: 18330.
[45] Huang C B, Hu J S, Tan K, et al. Application of machine learning model to predict osteoporosis based on abdominal computed tomography images of the psoas muscle: A retrospective study [J]. BMC Geriatrics, 2022, 22(1): 796.
[46] Jang M, Kim M, Bae S J, et al. Opportunistic osteoporosis screening using chest radiographs with deep learning: Development and external validation with a cohort dataset [J]. Journal of Bone and Mineral Research, 2022, 37(2): 369-377.
[47] Wang J F, Zhang Z H, Zhou Z R, et al. Clinical prediction models: Model validation [J]. Chinese Journal of Evidence-Based Cardiovascular Medicine, 2019, 11(2): 141-144 (in Chinese).
[48] Dong Q F, Luo G, Lane N E, et al. Deep learning classification of spinal osteoporotic compression fractures on radiographs using an adaptation of the genant semiquantitative criteria [J]. Academic Radiology, 2022, 29(12): 1819-1832.
[49] Bui H M, Ha M H, Pham H G, et al. Predicting the risk of osteoporosis in older Vietnamese women using machine learning approaches [J]. Scientific Reports, 2022, 12: 20160.
[50] Lehmann O, Mineeva O, Veshchezerova D, et al. Fracture risk prediction in postmenopausal women with traditional and machine learning models in a nationwide, prospective cohort study in Switzerland with validation in the UK Biobank [J]. Journal of Bone and Mineral Research, 2024, 39(8): 1103-1112.
[51] Chen R M, Huang Q, Chen L H. Development and validation of machine learning models for prediction of fracture risk in patients with elderly-onset rheumatoid arthritis [J]. International Journal of General Medicine, 2022, 15: 7817-7829.
[52] Chen Y X, Yang T Y, Gao X F, et al. Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis [J]. Frontiers of Medicine, 2022, 16(3): 496-506.
[53] Liu M H, Wei X, Xing X D, et al. Predicting fracture risk for elderly osteoporosis patients by hybrid machine learning model [J]. Digital Health, 2024, 10: 20552076241257456.
[54] Zhang H X, Yang Q Q, Dang C P, et al. Fracture risk prediction tools in elderly patients with osteoporosis: A scoping review [J]. Journal of Nursing, 2023, 30(3): 57-62 (in Chinese).
[55] Gao J, Wu J S, Ding J Y. Heterogeneous graph condensation [J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3126-3138.
[56] Tian Y Y, Jin Y R, Li Z Y, et al. Weighted heterogeneous graph-based incremental automatic disease diagnosis method [J]. Journal of Shanghai Jiao Tong University (Science), 2024, 29(1): 120-130.
[57] Phan T T H, Caillault É P, Lefebvre A, et al. Which DTW method applied to marine univariate time series imputation [C]//OCEANS 2017 - Aberdeen. Aberdeen: IEEE, 2017: 1-7.
[58] Zhang J L, Liu F, Xu J X, et al. Automated detection and classification of acute vertebral body fractures using a convolutional neural network on computed tomography [J]. Frontiers in Endocrinology, 2023, 14: 1132725.
[59] Hong N, Park H, Kim C O, et al. Bone radiomics score derived from DXA hip images enhances hip fracture prediction in older women [J]. Journal of Bone and Mineral Research, 2021, 36(9): 1708-1716.
[60] Lee C, Jang J, Lee S, et al. Classification of femur fracture in pelvic X-ray images using meta-learned deep neural network [J]. Scientific Reports, 2020, 10: 13694.
[61] Chen X J, Fu Z Z, Zhang P, et al. Intracortical brain–machine interfaces with high-performance neural decoding through efficient transfer meta-learning [J]. IEEE Transactions on Biomedical Engineering, 2026, 73(2): 518-529.
[62] Pei X H, Yang S, Huang J J, et al. Self-attention gated cognitive diagnosis for faster adaptive educational assessments [C]//2022 IEEE International Conference on Data Mining. Orlando: IEEE, 2023: 408-417.
[63] Solanki A, Kang S S, Singla S. Comprehensive analysis on image generation using quantum generative adversarial network [C]//2024 First International Conference on Technological Innovations and Advance Computing. Bali: IEEE, 2025: 302-307.
[64] Shirataki S, Yamaguchi S. A study on interpretability of decision of machine learning [C]//2017 IEEE International Conference on Big Data. Boston: IEEE, 2018: 4830-4831.
[65] Sanlum B, Kittithorn P, Yiangchaimongkol N, et al. SHAP-based feature selection method for uplift modeling [C]//2025 22nd International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology. Bangkok: IEEE, 2025: 1-5.
[66] Naik S, Kandelkar A, Agnihotri R, et al. Use of machine learning algorithms to assessment of drinking water quality in environment [C]//2025 International Conference on Intelligent and Cloud Computing. Bhubaneswar: IEEE, 2025: 1-6.
[67] Boukrouh I, Tayalati F, Azmani A. Comparative SHAP analysis on SVM and K-NN: Impacts of hyperparameter tuning on model explainability [C]//2024 IEEE International Conference on Artificial Intelligence in Engineering and Technology. Kota Kinabalu: IEEE, 2024: 194-198.

Options
Outlines

/

〈 〉