{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T20:15:31Z","timestamp":1793477731452,"version":"4.5.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>Osteoporosis is a common complication in patients with type 2 diabetes mellitus (T2DM), yet its screening rate remains low. This study aimed to develop and validate a cost-effective and interpretable machine learning (ML) model to predict the risk of osteoporosis in patients with T2DM.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This retrospective study included 1560 inpatients who underwent dual-energy X-ray absorptiometry (DXA) between January 2022 and December 2023 at Panyu Hospital of Chinese Medicine. Demographic information and laboratory test results obtained within 24 hours of hospital admission were collected. Potential predictive features were identified using univariate analysis, least absolute shrinkage and selection operator (LASSO) regression, and the Boruta algorithm. Eight supervised ML algorithms were applied to construct predictive models. Model performance was evaluated based on the area under the receiver operating characteristic curve (AUC), calibration plots, decision curve analysis (DCA), accuracy, sensitivity, specificity, and F1 score. The SHapley Additive exPlanations (SHAP) method was used to interpret the model and visualize feature importance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Ten predictive features were selected based on the intersection of the three feature selection methods. Among the tested models, logistic regression achieved the best overall performance, with an AUC of 0.812, an accuracy of 0.762, a sensitivity of 0.809, a specificity of 0.761, and an F1 score of 0.771 in the validation set. Calibration plots and DCA curves demonstrated good agreement and the highest net clinical benefit. SHAP analysis identified age, sex, alkaline phosphatase, uric acid, hemoglobin, and neutrophil count as the six most influential features. An easy-to-use, web-based risk calculator was developed based on the logistic model and is available at: <jats:ext-link>https:\/\/t2dm.shinyapps.io\/t2dm-osteoporosis\/<\/jats:ext-link>.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>We developed an interpretable and accessible ML-based online tool that enables preliminary screening of osteoporosis risk in patients with T2DM using routine blood indicators. This tool may assist clinicians in early risk identification and reduce the underdiagnosis of osteoporosis.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fendo.2025.1611499","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:12:19Z","timestamp":1754539939000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Development and validation of an explainable machine learning model for predicting osteoporosis in patients with type 2 diabetes mellitus"],"prefix":"10.3389","volume":"16","author":[{"given":"Qipeng","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijun","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingyan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxiang","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiji","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongling","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.2337\/dc19-S002","article-title":"2. Classification and diagnosis of diabetes: standards of medical care in diabetes-2019","volume":"42","year":"2019","journal-title":"Diabetes Care"},{"key":"B2","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1186\/s12967-024-05191-x","article-title":"Type 2 diabetic mellitus related osteoporosis: focusing on ferroptosis","volume":"22","author":"Chen","year":"2024","journal-title":"J Transl Med"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000019762","article-title":"Prevalence of osteoporosis in patients with type 2 diabetes mellitus in the chinese mainland: a protocol of systematic review and\u00a0meta-analysis","volume":"99","author":"Si","year":"2020","journal-title":"Med (Baltimore)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"121300","DOI":"10.1016\/j.neuroimage.2025.121300","article-title":"Aphasia severity prediction using a multi-modal machine learning approach","author":"Hu","year":"2025","journal-title":"Neuroimage"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1007\/s00198-025-07541-x","article-title":"Machine learning is changing osteoporosis detection: an integrative review","author":"Zhang","year":"2025","journal-title":"Osteoporos Int"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.5312\/wjo.v16.i4.103572","article-title":"Accuracy of artificial intelligence in prediction of osteoporotic fractures in comparison with dual-energy x-ray absorptiometry and the fracture risk assessment tool: a systematic review","volume":"16","author":"Sadat-Ali","year":"2025","journal-title":"World J Orthop"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2147\/CIA.S478461","article-title":"The monocyte-to-high-density lipoprotein cholesterol ratio as a novel predictor of the prevalence of senile osteoporosis","volume":"19","author":"Lin","year":"2024","journal-title":"Clin Interv Aging"},{"key":"B8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1186\/s13098-025-01642-7","article-title":"Association of triglyceride-glucose index with bone mineral density and fracture: a systematic review","volume":"17","author":"Yousefiasl","year":"2025","journal-title":"Diabetol Metab Syndr"},{"key":"B9","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1186\/s12891-025-08440-2","article-title":"Association of neutrophil to high-density lipoprotein cholesterol ratio with fragility fracture in osteoporotic patients: a case-control study","volume":"26","author":"Wang","year":"2025","journal-title":"BMC Musculoskelet Disord"},{"key":"B10","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1186\/s12944-024-02291-x","article-title":"Non-linear association of the platelet\/high-density lipoprotein cholesterol ratio with bone mineral density a cross-sectional study","volume":"23","author":"Ye","year":"2024","journal-title":"Lipids Health Dis"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcte.2024.100369","article-title":"Correlation study of multiple inflammatory indices and vertebral compression fracture: a cross-sectional study","volume":"37","author":"Fu","year":"2024","journal-title":"J Clin Transl Endocrinol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1186\/s12944-024-02152-7","article-title":"The association between the non-high-density lipoprotein cholesterol to high-density lipoprotein cholesterol ratio and the risk of osteoporosis among u.s. Adults: analysis of nhanes data","volume":"23","author":"Wang","year":"2024","journal-title":"Lipids Health Dis"},{"key":"B13","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1186\/s12933-025-02675-y","article-title":"Cholesterol, high-density lipoprotein, and glucose index versus triglyceride-glucose index in predicting cardiovascular disease risk: a cohort study","volume":"24","author":"Mo","year":"2025","journal-title":"Cardiovasc Diabetol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.05.006","article-title":"Comparison of variable selection methods for clinical predictive modeling","volume":"116","author":"Sanchez-Pinto","year":"2018","journal-title":"Int J Med Inform"},{"key":"B15","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Crit Care"},{"key":"B16","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1186\/s12931-024-02874-3","article-title":"An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease","volume":"25","author":"Huang","year":"2024","journal-title":"Respir Res"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106156","article-title":"Explanatory classification of cxr images into covid-19, pneumonia and tuberculosis using deep learning and xai","volume":"150","author":"Bhandari","year":"2022","journal-title":"Comput Biol Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"112158","DOI":"10.1016\/j.diabres.2025.112158","article-title":"Idf global clinical practice recommendations for managing type 2 diabetes - 2025","author":"Schwarz","year":"2025","journal-title":"Diabetes Res Clin Pract"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.7596","article-title":"Prevalence and ethnic pattern of diabetes and prediabetes in China in 2013","volume":"317","author":"Wang","year":"2017","journal-title":"Jama"},{"key":"B20","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.diabres.2017.03.024","article-title":"Idf diabetes atlas: global estimates for the prevalence of diabetes for 2015 and 2040","volume":"128","author":"Ogurtsova","year":"2017","journal-title":"Diabetes Res Clin Pract"},{"key":"B21","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s12933-024-02265-4","article-title":"Association between the stress hyperglycemia ratio and 28-day all-cause mortality in critically ill patients with sepsis: a retrospective cohort study and predictive model establishment based on machine learning","volume":"23","author":"Yan","year":"2024","journal-title":"Cardiovasc Diabetol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e383","DOI":"10.1016\/j.athoracsur.2022.02.009","article-title":"Alas, the return of the lasso","volume":"114","author":"Gerdisch","year":"2022","journal-title":"Ann Thorac Surg"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.23876\/j.krcp.25.046","article-title":"Statistical consideration in nephrology research","author":"Xu","year":"2025","journal-title":"Kidney Res Clin Pract"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-023-03353-3","article-title":"The associations between uric acid with bmds and risk of the 10-year probability of fractures in chinese patients with t2dm stratified by age and gender","volume":"80","author":"Xu","year":"2023","journal-title":"Endocrine"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1483512","article-title":"Molecular insights into the interplay between type 2 diabetes mellitus and osteoporosis: implications for endocrine health","volume":"15","author":"Jiang","year":"2024","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.1062999","article-title":"Monocyte to high-density lipoprotein and apolipoprotein a1 ratios are associated with bone homeostasis imbalance caused by chronic inflammation in postmenopausal women with type 2 diabetes mellitus","volume":"13","author":"Huang","year":"2022","journal-title":"Front Pharmacol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2023.1278505","article-title":"Associations of metabolic dysfunction-associated fatty liver disease and hepatic fibrosis with bone mineral density and risk of osteopenia\/osteoporosis in t2dm patients","volume":"14","author":"Zhang","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1210\/jcem.80.4.7714089","article-title":"Influence of age, sex, and insulin on osteoblast function: osteoblast dysfunction in diabetes mellitus","volume":"80","author":"Bouillon","year":"1995","journal-title":"J Clin Endocrinol Metab"},{"key":"B29","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.semcdb.2021.05.014","article-title":"Interaction between bone and immune cells: implications for postmenopausal osteoporosis","volume":"123","author":"Fischer","year":"2022","journal-title":"Semin Cell Dev Biol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"373","DOI":"10.3390\/antiox12020373","article-title":"Oxidative stress and natural antioxidants in osteoporosis: novel preventive and therapeutic approaches","volume":"12","author":"Marcucci","year":"2023","journal-title":"Antioxidants (Basel)"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3346\/jkms.2021.36.e239","article-title":"Effects of advanced glycation end products on differentiation and function of osteoblasts and osteoclasts","volume":"36","author":"Park","year":"2021","journal-title":"J Korean Med Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/s0163-7258(02)00164-x","article-title":"Role of ca(2+) and vitamin d in the prevention and treatment of osteoporosis","volume":"93","author":"Rodriguez-Martinez","year":"2002","journal-title":"Pharmacol Ther"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1534232","article-title":"Evaluating the triglyceride glucose index as a predictive biomarker for osteoporosis in patients with type 2 diabetes","volume":"16","author":"Zhan","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.2174\/1389450120666190821161259","article-title":"Tnf-alpha and il-6: the link between immune and bone system","volume":"21","author":"Wang","year":"2020","journal-title":"Curr Drug Targets"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1038\/s41387-022-00198-z","article-title":"Hemoglobin level and osteoporosis in chinese elders with type 2 diabetes mellitus","volume":"12","author":"Xiu","year":"2022","journal-title":"Nutr Diabetes"},{"key":"B36","doi-asserted-by":"publisher","first-page":"8304","DOI":"10.1038\/s41598-025-92348-3","article-title":"Association between serum uric acid levels and bone mineral density in chinese and american: a cross-sectional study","volume":"15","author":"Li","year":"2025","journal-title":"Sci Rep"},{"key":"B37","doi-asserted-by":"publisher","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":"B38","doi-asserted-by":"publisher","DOI":"10.1007\/s10620-011-1707-x","article-title":"Serum vitamin d concentrations and unexplained elevation in alt among us adults","volume":"56","author":"Liangpunsakul","year":"2011","journal-title":"Dig Dis Sci"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1007\/s00394-014-0790-0","article-title":"Increased body fat mass and tissue lipotoxicity associated with ovariectomy or high-fat diet differentially affects bone and skeletal muscle metabolism in rats","volume":"54","author":"Tagliaferri","year":"2015","journal-title":"Eur J Nutr"},{"key":"B40","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1186\/s12877-023-04306-1","article-title":"Development and validation of a risk prediction model for osteoporosis in elderly patients with type 2 diabetes mellitus: a retrospective and multicenter study","volume":"23","author":"Tan","year":"2023","journal-title":"BMC Geriatr"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.3760\/cma.j.issn.1671-7368.2014.08.013","article-title":"Evaluation of osteoporosis self-assessment tool for asians in screening of osteoporosis for postmenopausal women in community","author":"Sun","year":"2014","journal-title":"Chin J Gen Practitioners"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(02)08761-5","article-title":"Diagnosis of osteoporosis and assessment of fracture risk","volume":"359","author":"Kanis","year":"2002","journal-title":"Lancet"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1611499\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T04:12:20Z","timestamp":1754539940000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1611499\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"references-count":42,"alternative-id":["10.3389\/fendo.2025.1611499"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1611499","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,7]]},"article-number":"1611499"}}