Background
Predicting the risk of osteoporotic fractures is vital for prevention. Traditional methods such as the Fracture Risk Assessment Tool (FRAX) model use clinical factors. This study examined the predictive power of the FRAX score and machine-learning algorithms trained on FRAX parameters.
Methods
We analyzed the data of 2,147 female participants from the Ansan cohort study. The FRAX parameters employed in this study included age, sex (female), height and weight, current smoking status, excessive alcohol consumption (>3 units/d of alcohol), and diagnosis of rheumatoid arthritis. Osteoporotic fracture was defined as one or more fractures of the hip, spine, or wrist during a 10-year observation period. Machine-learning algorithms, such as gradient boosting, random forest, decision tree, and logistic regression, were employed to predict osteoporotic fractures with a 70:30 training-to-test set ratio. We evaluated the area under the receiver operating characteristic curve (AUROC) scores to assess and compare the performance of these algorithms with the FRAX score.
Results
Of the 2,147 participants, 3.5% experienced osteoporotic fractures. Those with fractures were older, shorter in height, and had a higher prevalence of rheumatoid arthritis, as well as higher FRAX scores. The AUROC for the FRAX was 0.617. The machine-learning algorithms showed AUROC values of 0.662, 0.652, 0.648, and 0.637 for gradient boosting, logistic regression, decision tree, and random forest, respectively.
Conclusion
This study highlighted the immense potential of machine-learning algorithms to improve osteoporotic fracture risk prediction in women when complete FRAX parameter information is unavailable.

Citations

• Machine learning is changing osteoporosis detection: an integrative review
  Yuji Zhang, Ming Ma, Xingchun Huang, Jinmin Liu, Cong Tian, Zhenkun Duan, Hongyin Fu, Lei Huang, Bin Geng
  Osteoporosis International.2025; 36(8): 1313.     CrossRef
• Artificial intelligence in nutrition and ageing research – A primer on the benefits
  Pol Grootswagers, Tijl Grootswagers
  Maturitas.2025; 200: 108662.     CrossRef
• Assessing the Risk of Osteoporotic Fracture Recurrence Using CT-based Radiomics and Machine Learning
  Xiaoyang Zheng, Caihong Zhu, Rui Zhang, Hongyu Sun
  Current Problems in Surgery.2025; : 101876.     CrossRef
• AI-driven Technologies for Wrist Fracture Prediction: A Narrative Review of Emerging Approaches
  Stefania Briano, Maria Cesarina May, Giacomo Demontis, Giulia Pachera, Vittoria Mazzola, Federico Vitali, Alessandra Galuppi, Emanuela Dapelo, Andrea Zanirato, Matteo Formica
  Journal of Wrist Surgery.2025;[Epub]     CrossRef
• Interpretable machine learning model for low bone density screening in older adults using demographic and anthropometric data: findings from 2005 to 2020 NHANES
  Weiyan Huang, Qimou Pan, Jiewei Peng, Yufeng Wu, Dawei Gao
  BMC Medical Informatics and Decision Making.2025;[Epub]     CrossRef
• Clinical Applicability of Machine Learning in Family Medicine
  Jungun Lee
  Korean Journal of Family Medicine.2024; 45(3): 123.     CrossRef
• Integrating Machine Learning for Personalized Fracture Risk Assessment: A Multimodal Approach
  Sheikh Mohd Saleem, Shah Sumaya Jan
  Korean Journal of Family Medicine.2024; 45(6): 356.     CrossRef

Background
Intermittent dosing regimens for oral risedronate (once-monthly and once-weekly) were developed for patient convenience. While several studies have reported the anti-fracture efficacy of weekly dosing, few have assessed monthly dosing. The lower efficacy of monthly dosing has been previously suggested. The aim of this study was to compare the anti-fracture efficacy of monthly and weekly dosing.
Methods
We obtained information from the Korea National Health Insurance Service database from 2012 to 2017 of Korean women of ≥50 years of age who used weekly or monthly risedronate. We compared the time of occurrence of the first osteoporotic fracture after the first prescription of risedronate. Using a Cox proportional model, we assessed incidence rate ratios (IRRs) with 95% confidence intervals (CIs) for fractures at any site, and the hip, vertebral, and non-vertebral sites between both regimens. Propensity score weighting was used to balance the treatment groups.
Results
The study populations were distributed according to dosing frequency (monthly, 27,329; weekly, 47,652). There was no significant difference in the incidence rate of new fractures in any site (IRR, 1.008; 95% CI,0.963– 1.055; P=0.737), hip (IRR, 0.999; 95% CI, 0.769–1.298; P=0.996), vertebral (IRR, 0.962; 95% CI, 0.890–1.040; P=0.330), or non-vertebral (1.022; 95% CI, 0.968–1.078; P=0.439) sites between monthly and weekly risedronate.
Conclusion
The anti-fracture efficacy at any site and the examined individual sites was similar for the monthly and weekly risedronate regimens. Large-scale randomized controlled trials are required for confirmation.

Citations

• Associations between multiple metals exposure and bone mineral density: a population-based study in U.S. children and adolescents
  Jian Han, Jiaqing Sun, Lin Yuan, Luyao Lou, Xiaofeng Jiang
  BMC Musculoskeletal Disorders.2025;[Epub]     CrossRef
• Metals accumulation affects bone and muscle in osteoporotic patients: A pilot study
  Beatrice Battistini, Chiara Greggi, Virginia Veronica Visconti, Marco Albanese, Alessandra Messina, Patrizia De Filippis, Beatrice Gasperini, Angela Falvino, Prisco Piscitelli, Leonardo Palombi, Umberto Tarantino
  Environmental Research.2024; 250: 118514.     CrossRef
• Trends in the prevalence of osteoporosis and effects of heavy metal exposure using interpretable machine learning
  Hewei Xiao, Xueyan Liang, Huijuan Li, Xiaoyu Chen, Yan Li
  Ecotoxicology and Environmental Safety.2024; 286: 117238.     CrossRef
• Association of blood mercury levels with bone mineral density in adolescents aged 12–19
  Ke Xu, Bingqian Gao, Tingfeng Liu, Jiayi Li, Yixin Xiang, Yicheng Fu, Mingyi Zhao
  Environmental Science and Pollution Research.2023; 30(16): 46933.     CrossRef
• Relationship of blood heavy metals and osteoporosis among the middle-aged and elderly adults: A secondary analysis from NHANES 2013 to 2014 and 2017 to 2018
  Zengfa Huang, Xiang Wang, Hui Wang, Shutong Zhang, Xinyu Du, Hui Wei
  Frontiers in Public Health.2023;[Epub]     CrossRef
• Associations of blood trace elements with bone mineral density: a population-based study in US adults
  Chunli Wu, Yao Xiao, Yuexia Jiang
  Journal of Orthopaedic Surgery and Research.2023;[Epub]     CrossRef
• Normal concentration range of blood mercury and bone mineral density: a cross-sectional study of National Health and Nutrition Examination Survey (NHANES) 2005–2010
  Yuchen Tang, Qiong Yi, Shenghong Wang, Yayi Xia, Bin Geng
  Environmental Science and Pollution Research.2022; 29(5): 7743.     CrossRef
• Associations of multiple metals with bone mineral density: A population-based study in US adults
  Mu-hong Wei, Yuan Cui, Hao-long Zhou, Wen-jing Song, Dong-sheng Di, Ru-yi Zhang, Qin Huang, Jun-an Liu, Qi Wang
  Chemosphere.2021; 282: 131150.     CrossRef
• Occurrence of mercury in the knee joint tissues
  Magdalena Babuśka-Roczniak, Barbara Brodziak-Dopierała, Joanna Bem, Anna Kruczek, Elżbieta Cipora, Wojciech Roczniak
  Polish Annals of Medicine.2021;[Epub]     CrossRef
• Exposure to heavy metals and the risk of osteopenia or osteoporosis: a systematic review and meta-analysis
  C. Jalili, M. Kazemi, E. Taheri, H. Mohammadi, B. Boozari, A. Hadi, S. Moradi
  Osteoporosis International.2020; 31(9): 1671.     CrossRef
• Relationship between heavy metal accumulation and histological alterations in voles from alpine and forest habitats of the West Carpathians
  Zuzana Kompišová Ballová, Filip Korec, Katarína Pinterová
  Environmental Science and Pollution Research.2020; 27(29): 36411.     CrossRef
• Long-Term Accumulation of Metals in the Skeleton as Related to Osteoporotic Derangements
  Geir Bjørklund, Lyudmila Pivina, Maryam Dadar, Yuliya Semenova, Salvatore Chirumbolo, Jan Aaseth
  Current Medicinal Chemistry.2020; 27(40): 6837.     CrossRef

Background
: As the average lifespan of human increases, osteoporosis and osteoporosis-related fractures have become major health care problems. Despite recent advances in medical treatment, few studies have assessed the recognition of osteoporosis in general adults. This study examined the recognition of osteoporosis and analysed the relating factors.

Methods : We made a survey in a rural area called Chunjunlee in Chunchon city. The questionnaire contained general characteristics of people, sociocultural factors, questions constructed to know the recognition of osteoporosis and factors that were presumed to influence people's recognition of osteoporosis. DEXA was performed on those who visited our medical office free of charge.

Results : The total number of people who responded to the questionnaire was 204. They were composed of 81 men and 123 women. Among the total, 83% of women and 72.8% of men said that they had heard about osteoporosis. There was no significant recognition score difference between men and women. In the items of recognition, wrong answer rate concerning the association between osteoporosis and musculoskeletal disorders such as osteoarthritis and low back pain was above 90%. The significant factors that influenced its recognition were age, education level, menopause state and newspaper/ magazine subscription. All men who were diagnosed with osteoporosis on DEXA initially said that they did not have osteoporosis.

Conclusion : Many people had a conceptual confusion between osteoporosis and other muscular skeletal disorders such as osteoarthritis and low back pain. Physicians played no significant role in improvement of people's recognition of osteoporosis. Generally, men thought that osteoporosis was a problem in women only.