{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:00:08Z","timestamp":1785214808373,"version":"3.55.0"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Medical Science Research Project of Hebei","award":["20231592"],"award-info":[{"award-number":["20231592"]}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Osteoporosis (OP) represents a significant public health challenge in the aging population, often leading to debilitating fractures. Early identification of high-risk individuals through routine clinical data is vital for preventive care. This study aimed to develop and validate a robust machine learning-based framework to predict OP in older people using comprehensive physical examination indicators.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We analyzed a retrospective single-center cohort of 852 participants (age \u2267 60\u202fyears) from a physical examination center. The cohort was randomly partitioned into a training set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f598) and an internal validation set (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f254) at a 7:3 ratio. Nineteen potential predictors, including demographics (Age, Sex, BMI), lifestyle habits, comorbidities, and biochemical markers (e.g., SUA, Hb, LDL), were evaluated. After feature selection via LASSO regression, five algorithms-Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), and XGBoost-were constructed. Hyperparameter tuning was performed only within the training set using 5-fold cross-validation and grid search, and the internal validation set was kept separate for final performance assessment. Model performance was evaluated using the Area Under the Curve (AUC), calibration curves, and Decision Curve Analysis (DCA). Restricted cubic spline (RCS) analysis was further employed to evaluate dose\u2013response associations between selected variables and osteoporosis risk.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The prevalence of OP in the study population was 28.87% (246\/852). LASSO regression identified 12 optimal features for model development. While ensemble methods (RF and XGBoost) exhibited high discriminative power, they showed signs of potential overfitting with perfect training set performance. In contrast, the LR model demonstrated superior robustness and stability, achieving an AUC of 0.809 in the training set and 0.782 in the internal validation set. In the validation cohort, the LR model maintained balanced performance with a sensitivity of 0.767 and a specificity of 0.702. Calibration curves indicated agreement between predicted and observed risks, and DCA suggested clinical net benefit across a broad range of threshold probabilities. SHAP (SHapley Additive exPlanations) analysis indicated that Sex, Age, and BMI were the most influential predictors. Lower levels of serum creatinine (Scr), serum uric acid (SUA), and fasting plasma glucose (FPG) were also associated with higher predicted osteoporosis risk. Multivariable-adjusted RCS analysis suggested an upward trend between HDL-C and OP risk, particularly in the female subgroup (OR\u202f=\u202f3.35, 95% CI: 0.86\u201313.04;\n                      <jats:italic>p<\/jats:italic>\n                      =\u202f0.081), but this finding did not reach conventional statistical significance and should be interpreted cautiously.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Compared with complex ensemble algorithms, the LR model provides a stable and interpretable approach for identifying older people who may warrant DXA assessment or closer bone-health evaluation. Because this study used a retrospective single-center cohort and internal validation only, external multi-center validation is required before routine clinical deployment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1840631","type":"journal-article","created":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:26:29Z","timestamp":1785212789000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of a robust logistic regression model for predicting osteoporosis in older people"],"prefix":"10.3389","volume":"13","author":[{"given":"Hongxia","family":"Xue","sequence":"first","affiliation":[{"name":"Health Management Center, The Third Hospital of Shijiazhuang City","place":["Shijiazhuang, Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuewei","family":"Hao","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, The People\u2019s Hospital of Shijiazhuang City","place":["Shijiazhuang, Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dandan","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, The People\u2019s Hospital of Shijiazhuang City","place":["Shijiazhuang, Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Health Management Center, The First Hospital of Hebei Medical University","place":["Shijiazhuang, Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiquan","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Orthopedics, The First Hospital of Hebei Medical University","place":["Shijiazhuang, Hebei, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1001\/jama.2025.6003","article-title":"Osteoporosis: a review","volume":"334","author":"Morin","year":"2025","journal-title":"JAMA"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1007\/s00198-022-06454-3","article-title":"Global, regional prevalence, and risk factors of osteoporosis according to the World Health Organization diagnostic criteria: a systematic review and meta-analysis","volume":"33","author":"Xiao","year":"2022","journal-title":"Osteoporos Int"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"e71378","DOI":"10.1002\/hsr2.71378","article-title":"Global health effects of osteopenia and osteoporosis, 1990-2021","volume":"8","author":"Safiri","year":"1990","journal-title":"Health Sci Rep"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1159\/000544781","article-title":"Antiresorptive therapy for osteoporosis in older subjects","volume":"71","author":"S\u00f8lling","year":"2025","journal-title":"Gerontology"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11926-025-01205-9","article-title":"Updates on the role of DXA in the evaluation and monitoring of osteoporosis","volume":"27","author":"Anupama","year":"2025","journal-title":"Curr Rheumatol Rep"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"615","DOI":"10.3949\/ccjm.88a.20199","article-title":"DXA and clinical challenges of fracture risk assessment in primary care","volume":"88","author":"Williams","year":"2021","journal-title":"Cleve Clin J Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"5785","DOI":"10.3390\/jcm14165785","article-title":"Bone health in metabolic syndrome-is it a neglected aspect of dysmetabolic-related diseases?","volume":"14","author":"Biamonte","year":"2025","journal-title":"J Clin Med"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"3667","DOI":"10.2147\/dmso.s275560","article-title":"Relationship between metabolic syndrome and bone health-an evaluation of epidemiological studies and mechanisms involved","volume":"13","author":"Chin","year":"2020","journal-title":"Diabetes Metab Syndr Obes"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"bvae 112","DOI":"10.1210\/jendso\/bvae112","article-title":"Bone health in patients with type 2 diabetes","volume":"8","author":"Forner","year":"2024","journal-title":"J Endocr Soc"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"28302","DOI":"10.1038\/s41598-025-12925-4","article-title":"The association between glycemic indicators and bone mineral density and osteoporosis: a cross-sectional study","volume":"15","author":"Hou","year":"2025","journal-title":"Sci Rep"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1639","DOI":"10.3390\/ijms23031639","article-title":"Bone health in patients with dyslipidemias: an underestimated aspect","volume":"23","author":"Anagnostis","year":"2022","journal-title":"Int J Mol Sci"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1002\/jbmr.4862","article-title":"Nonalcoholic fatty liver disease is associated with decreased bone mineral density in adults: a systematic review and meta-analysis","volume":"38","author":"Su","year":"2023","journal-title":"J Bone Miner Res"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/978-3-030-85292-4","article-title":"A discussion of machine learning approaches for clinical prediction modeling","volume":"134","author":"Jin","year":"2022","journal-title":"Acta Neurochir Suppl"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"104405","DOI":"10.1016\/j.medengphy.2025.104405","article-title":"Explainable deep learning framework for brain tumor detection: integrating LIME, grad-CAM, and SHAP for enhanced accuracy","volume":"144","author":"Akg\u00fcndo\u011fdu","year":"2025","journal-title":"Med Eng Phys"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1739898","DOI":"10.3389\/fendo.2026.1739898","article-title":"Association between neutrophil to lymphocyte ratio and the risk of vertebral fracture in patients with osteoporosis: a systematic review and meta-analysis","volume":"17","author":"Xu","year":"2026","journal-title":"Front Endocrinol (Lausanne)"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2417","DOI":"10.14336\/ad.2023.1115","article-title":"Consequences of aging on bone","volume":"15","author":"Zhang","year":"2023","journal-title":"Aging Dis"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1486188","DOI":"10.3389\/fendo.2024.1486188","article-title":"Mendelian randomization studies of risk and protective factors for osteoporosis: a systematic review and meta-analysis","volume":"15","author":"Ji","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1154927","DOI":"10.3389\/fendo.2023.1154927","article-title":"Low BMI, blood calcium and vitamin D, kyphosis time, and outdoor activity time are independent risk factors for osteoporosis in postmenopausal women","volume":"14","author":"Tang","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"156115","DOI":"10.1016\/j.prp.2025.156115","article-title":"Mechanisms of aging-related secretory phenotype regulation in osteoporosis: network regulation, trade-offs and homeostasis","volume":"272","author":"Wang","year":"2025","journal-title":"Pathol Res Pract"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2292","DOI":"10.3390\/biomedicines12102292","article-title":"The pathogenetic role of RANK\/RANKL\/OPG signaling in osteoarthritis and related targeted therapies","volume":"12","author":"Di Cicco","year":"2024","journal-title":"Biomedicine"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1038\/s41413-023-00306-4","article-title":"Insights and implications of sexual dimorphism in osteoporosis","volume":"12","author":"Zhang","year":"2024","journal-title":"Bone Res"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1611932","DOI":"10.3389\/fimmu.2025.1611932","article-title":"Oxidative stress and inflammation: roles in osteoporosis","volume":"16","author":"Luo","year":"2025","journal-title":"Front Immunol"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"600181","DOI":"10.3389\/fcell.2020.600181","article-title":"Obesity and bone health: a complex link","volume":"8","author":"Hou","year":"2020","journal-title":"Front Cell Dev Biol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"544","DOI":"10.3390\/ijerph13060544","article-title":"BMI and BMD: the potential interplay between obesity and bone fragility","volume":"13","author":"Palermo","year":"2016","journal-title":"Int J Environ Res Public Health"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1682231","DOI":"10.3389\/fendo.2025.1682231","article-title":"Metabolic impact of endogenously produced estrogens by adipose tissue in females and males across the lifespan","volume":"16","author":"Lee","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"2457","DOI":"10.1016\/j.clnu.2023.10.013","article-title":"The effect of overweight or obesity on osteoporosis: a systematic review and meta-analysis","volume":"42","author":"Liu","year":"2023","journal-title":"Clin Nutr"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"6640796","DOI":"10.1155\/2024\/6640796","article-title":"Potential metabolic pathways involved in osteoporosis and evaluation of fracture risk in individuals with diabetes","volume":"2024","author":"Liu","year":"2024","journal-title":"Biomed Res Int"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"8718","DOI":"10.3390\/ijerph19148718","article-title":"Protein intake and sarcopenia in older adults: a systematic review and meta-analysis","volume":"19","author":"Coelho-Junior","year":"2022","journal-title":"Int J Environ Res Public Health"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1046\/j.1365-2265.2001.01278.x","article-title":"Low serum concentrations of insulin-like growth factor I are associated with femoral bone loss in a population-based sample of postmenopausal women","volume":"55","author":"Seck","year":"2001","journal-title":"Clin Endocrinol"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"4257","DOI":"10.1210\/jcem.83.12.5308","article-title":"Association between insulin-like growth factor I and bone mineral density in older women and men: the Framingham heart study","volume":"83","author":"Langlois","year":"1998","journal-title":"J Clin Endocrinol Metab"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s11914-022-00721-2","article-title":"Bioenergetic metabolism in osteoblast differentiation","volume":"20","author":"Shen","year":"2022","journal-title":"Curr Osteoporos Rep"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"3123","DOI":"10.3390\/nu14153123","article-title":"Malnutrition in older adults-effect on falls and fractures: a narrative review","volume":"14","author":"Kupisz-Urbanska","year":"2022","journal-title":"Nutrients"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.bone.2018.11.002","article-title":"Use it or lose it to age: a review of bone and muscle communication","volume":"120","author":"Bonewald","year":"2019","journal-title":"Bone"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1016\/j.cell.2015.05.029","article-title":"Glucose uptake and Runx 2 synergize to orchestrate osteoblast differentiation and bone formation","volume":"161","author":"Wei","year":"2015","journal-title":"Cell"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.bone.2017.08.008","article-title":"Glucose metabolism in bone","volume":"115","author":"Karner","year":"2018","journal-title":"Bone"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1210\/jc.2002-021380","article-title":"Serum insulin-like growth factor (IGF)-I and IGF-binding protein-1 in elderly people: relationships with cardiovascular risk factors, body composition, size at birth, and childhood growth","volume":"88","author":"Kajantie","year":"2003","journal-title":"J Clin Endocrinol Metab"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/s41574-022-00649-8","article-title":"Skeletal disorders associated with the growth hormone-insulin-like growth factor 1 axis","volume":"18","author":"Mazziotti","year":"2022","journal-title":"Nat Rev Endocrinol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1210\/er.2007-0036","article-title":"Growth hormone, insulin-like growth factors, and the skeleton","volume":"29","author":"Giustina","year":"2008","journal-title":"Endocr Rev"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"101367","DOI":"10.1016\/j.mam.2025.101367","article-title":"The bone-muscle unit: from mechanical coupling to soluble factors-mediated signaling","volume":"103","author":"Malvandi","year":"2025","journal-title":"Mol Asp Med"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1715009","DOI":"10.3389\/fcell.2025.1715009","article-title":"Molecular communication from bone to skeletal muscle: an overview","volume":"13","author":"Li","year":"2025","journal-title":"Front Cell Dev Biol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"E305","DOI":"10.21037\/jtd.2016.03.62","article-title":"Serum creatinine level, a surrogate of muscle mass, predicts mortality in critically ill patients","volume":"8","author":"Thongprayoon","year":"2016","journal-title":"J Thorac Dis"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"620608","DOI":"10.3389\/fphys.2021.620608","article-title":"Irisin: a new code uncover the relationship of skeletal muscle and cardiovascular health during exercise","volume":"12","author":"Ma","year":"2021","journal-title":"Front Physiol"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.3390\/ijms21041259","article-title":"Recombinant irisin prevents the reduction of osteoblast differentiation induced by stimulated microgravity through increasing \u03b2-catenin expression","volume":"21","author":"Chen","year":"2020","journal-title":"Int J Mol Sci"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"e70013","DOI":"10.1111\/1756-185x.70013","article-title":"Association of serum uric acid level with bone mineral density and the risk of osteoporosis: a dose-response meta-analysis","volume":"28","author":"Shen","year":"2025","journal-title":"Int J Rheum Dis"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1111\/eci.12677","article-title":"Hyperuricemia protects against low bone mineral density, osteoporosis and fractures: a systematic review and meta-analysis","volume":"46","author":"Veronese","year":"2016","journal-title":"Eur J Clin Investig"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"e230040","DOI":"10.1530\/EC-23-0040","article-title":"Relationship between serum uric acid levels and osteoporosis","volume":"12","author":"Xu","year":"2023","journal-title":"Endocr Connect"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1271942","DOI":"10.3389\/fendo.2023.1271942","article-title":"The association of lipid metabolism with bone metabolism and the role of human traits: a Mendelian randomization study","volume":"14","author":"Kang","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/s00223-023-01160-6","article-title":"Lipid metabolism, methylation aberrant, and osteoporosis: a multi-omics study based on Mendelian randomization","volume":"114","author":"Zhang","year":"2024","journal-title":"Calcif Tissue Int"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"e1006944","DOI":"10.1371\/journal.pgen.1006944","article-title":"Genetic epidemiology and Mendelian randomization for informing disease therapeutics: conceptual and methodological challenges","volume":"13","author":"Paternoster","year":"2017","journal-title":"PLoS Genet"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1002\/jbmr.3194","article-title":"The ability of a single BMD and fracture history assessment to predict fracture over 25 years in postmenopausal women: the study of osteoporotic fractures","volume":"33","author":"Black","year":"2018","journal-title":"J Bone Miner Res"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1185\/030079903125003062","article-title":"Is bone mineral density predictive of fracture risk reduction?","volume":"20","author":"Cefalu","year":"2004","journal-title":"Curr Med Res Opin"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1840631\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:26:30Z","timestamp":1785212790000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1840631\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,28]]},"references-count":51,"alternative-id":["10.3389\/fmed.2026.1840631"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1840631","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,28]]},"article-number":"1840631"}}