{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T16:44:48Z","timestamp":1787503488114,"version":"build-2736575974"},"reference-count":32,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCM"],"abstract":"<jats:p>Background: Osteoporosis and osteopenia are prevalent bone diseases characterized by reduced bone mineral density (BMD) and an increased risk of fractures, particularly in postmenopausal women. While dual-energy X-ray absorptiometry (DXA) remains the gold standard for diagnosis, it has limitations regarding accessibility, cost, and predictive capacity for fracture risk. Machine learning (ML) approaches offer an opportunity to develop automated and more accurate diagnostic models by incorporating both BMD values and clinical variables. Method: This study retrospectively analyzed BMD data from 142 postmenopausal women, classified into 3 diagnostic groups: normal, osteopenia, and osteoporosis. Various supervised ML algorithms\u2014including Support Vector Machines (SVM), k-Nearest Neighbors (k-NN), Decision Trees (DT), Naive Bayes (NB), Linear Discriminant Analysis (LDA), and Artificial Neural Networks (ANN)\u2014were applied. Feature selection techniques such as ANOVA, CHI2, MRMR, and Kruskal\u2013Wallis were used to enhance model performance, reduce dimensionality, and improve interpretability. Model performance was evaluated using 10-fold cross-validation based on accuracy, true positive rate (TPR), false negative rate (FNR), and AUC values. Results: Among all models and feature selection combinations, SVM with ANOVA-selected features achieved the highest classification accuracy (94.30%) and 100% TPR for the normal class. Feature sets based on traditional diagnostic regions (L1\u2013L4, femoral neck, total femur) also showed high accuracy (up to 90.70%) but were generally outperformed by statistically selected features. CHI2 and MRMR methods also yielded robust results, particularly when paired with SVM and k-NN classifiers. The results highlight the effectiveness of combining statistical feature selection with ML to enhance diagnostic precision for osteoporosis and osteopenia. Conclusions: Machine learning algorithms, when integrated with data-driven feature selection strategies, provide a promising framework for automated classification of osteoporosis and osteopenia based on BMD data. ANOVA emerged as the most effective feature selection method, yielding superior accuracy across all classifiers. These findings support the integration of ML-based decision support tools into clinical workflows to facilitate early diagnosis and personalized treatment planning. Future studies should explore more diverse and larger datasets, incorporating genetic, lifestyle, and hormonal factors for further model enhancement.<\/jats:p>","DOI":"10.3390\/jcm15020549","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T12:52:17Z","timestamp":1767963137000},"page":"549","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Machine Learning-Based Automatic Diagnosis of Osteoporosis Using Bone Mineral Density Measurements"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5113-2287","authenticated-orcid":false,"given":"Nil\u00fcfer Ayg\u00fcn","family":"Bilecik","sequence":"first","affiliation":[{"name":"Department of Physical Therapy and Rehabilitation, Adana City Training and Research Hospital, Adana 01370, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Levent","family":"U\u011fur","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Faculty of Engineering, Amasya University, Amasya 05100, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8794-8202","authenticated-orcid":false,"given":"Erol","family":"\u00d6ten","sequence":"additional","affiliation":[{"name":"Department of Physical Therapy and Rehabilitation, Faculty of Medicine, Amasya University, Amasya 05100, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9586-6509","authenticated-orcid":false,"given":"Mustafa","family":"\u00c7apraz","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Faculty of Medicine, Amasya University, Amasya 05100, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"175","DOI":"10.11005\/jbm.2015.22.4.175","article-title":"Osteoporotic fracture: 2015 position statement of the Korean society for bone and mineral research","volume":"22","author":"Yoo","year":"2015","journal-title":"J. Bone Metab."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11657-013-0137-0","article-title":"Osteoporosis in the European Union: A compendium of country-specific reports","volume":"8","author":"Svedbom","year":"2013","journal-title":"Arch. Osteoporos."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2023","DOI":"10.1007\/s00198-017-4009-0","article-title":"Identification and management of patients at increased risk of osteoporotic fracture: Outcomes of an ESCEO expert consensus meeting","volume":"28","author":"Kanis","year":"2017","journal-title":"Osteoporos. Int."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.1213\/ANE.0000000000002011","article-title":"Computational and in vitro experimental investigation of intrathecal drug distribution: Parametric study of the effect of injection volume, cerebrospinal fluid pulsatility, and drug uptake","volume":"124","author":"Tangen","year":"2017","journal-title":"Anesth. Analg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1007\/BF01622200","article-title":"Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: Synopsis of a WHO report","volume":"4","author":"Kanis","year":"1994","journal-title":"Osteoporos. Int."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/j.jocd.2020.10.004","article-title":"Machine learning can improve clinical detection of low BMD: The DXA-HIP study","volume":"24","author":"Erjiang","year":"2021","journal-title":"J. Clin. Densitom."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kang, J.-W., Park, C., Lee, D.-E., Yoo, J.-H., and Kim, M. (2023). Prediction of bone mineral density in CT using deep learning with explainability. Front. Physiol., 13.","DOI":"10.3389\/fphys.2022.1061911"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6355","DOI":"10.1007\/s00330-019-06263-z","article-title":"Bone mineral density measurements derived from dual-layer spectral CT enable opportunistic screening for osteoporosis","volume":"29","author":"Roski","year":"2019","journal-title":"Eur. Radiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"751","DOI":"10.7326\/0003-4819-155-11-201112060-00007","article-title":"Cost-effectiveness of different screening strategies for osteoporosis in postmenopausal women","volume":"155","author":"Nayak","year":"2011","journal-title":"Ann. Intern. Med."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liu, Y., Meng, X.-H., Wu, C., Su, K.-J., Liu, A., Tian, Q., Zhao, L.-J., Qiu, C., Luo, Z., and I Gonzalez-Ramirez, M. (2024). Variability in performance of genetic-enhanced DXA-BMD prediction models across diverse ethnic and geographic populations: A risk prediction study. PLoS Med., 21.","DOI":"10.1371\/journal.pmed.1004451"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"396","DOI":"10.1007\/s10439-023-03387-8","article-title":"Osteoporosis prediction using machine-learned optical bone densitometry data","volume":"52","author":"Miura","year":"2024","journal-title":"Ann. Biomed. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"14604582241295930","DOI":"10.1177\/14604582241295930","article-title":"BoneScore: A natural language processing algorithm to extract bone mineral density data from DXA scans","volume":"30","author":"Fodeh","year":"2024","journal-title":"Health Inform. J."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Bezerra, G.M., Ohata, E.F., Loureiro, L.L., Bittencourt, V.Z., Capistrano, V.L.M., da Rocha, A.R., and Filho, P.P.R. (2024, January 26\u201328). Estimation of Bone Mineral Density using Machine Learning and SHapley Additive exPlanations. Proceedings of the 2024 IEEE 37th International Symposium on Computer-Based Medical Systems (CBMS), Guadalajara, Mexico.","DOI":"10.1109\/CBMS61543.2024.00076"},{"key":"ref_14","first-page":"71","article-title":"Prediction of bone mineral density based on computer tomography images using deep learning model","volume":"71","author":"Li","year":"2025","journal-title":"Gerontology"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2359","DOI":"10.1007\/s00198-014-2794-2","article-title":"Clinician\u2019s guide to prevention and treatment of osteoporosis","volume":"25","author":"Cosman","year":"2014","journal-title":"Osteoporos. Int."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1136\/annrheumdis-2014-eular.3250","article-title":"OP0292 The Diagnosis of osteoporosis using BMD and T score measurements at specific skeletal sites","volume":"73","author":"Sinha","year":"2014","journal-title":"Ann. Rheum. Dis."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1385\/JCD:3:4:319","article-title":"Dual X-ray absorptiometry T-score concordance and discordance between hip and spine measurement sites","volume":"3","author":"Woodson","year":"2000","journal-title":"J. Clin. Densitom."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1016\/j.jocd.2008.04.009","article-title":"Use of lowest single lumbar spine vertebra bone mineral density T-score and other T-score approaches for diagnosing osteoporosis and relationships with vertebral fracture status","volume":"11","author":"Chen","year":"2008","journal-title":"J. Clin. Densitom."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"105","DOI":"10.4274\/tod.22448","article-title":"Evaluation of Concordance between Hip and Spine T Scores in the Diagnosis of Osteoporosis in Men Over Age of Fifty","volume":"21","author":"Yasrebi","year":"2015","journal-title":"Turk. Osteoporoz. Derg. Turk. J. Osteoporos."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"101406","DOI":"10.1016\/j.jocd.2023.101406","article-title":"Comparison between Horizon A System and Lunar iDXA in Bone Assessment and Osteoporosis Diagnosis: The OsteoLaus Cohort","volume":"26","author":"Vendrami","year":"2023","journal-title":"J. Clin. Densitom."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1007\/s00198-016-3829-7","article-title":"The lumbar spine age-related degenerative disease influences the BMD not the TBS: The Osteolaus cohort","volume":"28","author":"Padlina","year":"2017","journal-title":"Osteoporos. Int."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1177\/1550059420966436","article-title":"An evaluation of the channel effect on detecting the preictal stage in patients with epilepsy","volume":"52","author":"Bergil","year":"2021","journal-title":"Clin. EEG Neurosci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"176","DOI":"10.56158\/jpte.2023.56.2.02","article-title":"Application of Dimension Reduction Methods for Stress Detection","volume":"2","author":"Bergil","year":"2023","journal-title":"Int. J. Pioneer. Technol. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kumar, A., Kaur, A., Singh, P., Driss, M., and Boulila, W. (2023). Efficient Multiclass Classification Using Feature Selection in High-Dimensional Datasets. Electronics, 12.","DOI":"10.3390\/electronics12102290"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"119266","DOI":"10.1016\/j.ins.2023.119266","article-title":"Fuzzy rough dimensionality reduction: A feature set partition-based approach","volume":"644","author":"Wang","year":"2023","journal-title":"Inf. Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2663","DOI":"10.1109\/TUFFC.2022.3195477","article-title":"Improvement of patient classification using feature selection applied to bidirectional axial transmission","volume":"69","author":"Miranda","year":"2022","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e22456","DOI":"10.1016\/j.heliyon.2023.e22456","article-title":"A decision support system for osteoporosis risk prediction using machine learning and explainable artificial intelligence","volume":"9","author":"Khanna","year":"2023","journal-title":"Heliyon"},{"key":"ref_28","unstructured":"Calitis, M. (2024). Risk Factor Identification in Osteoporosis Using Unsupervised Machine Learning Techniques. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"263","DOI":"10.11005\/jbm.2023.30.3.263","article-title":"Osteoporosis feature selection and risk prediction model by machine learning using a cross-sectional database","volume":"30","author":"Cha","year":"2023","journal-title":"J. Bone Metab."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1507\/endocrj.EJ17-0331","article-title":"Fracture risk assessment tool (FRAX) and for the diagnosis of osteoporosis in Japanese middle-aged and elderly women: Chiba bone survey","volume":"65","author":"Oka","year":"2018","journal-title":"Endocr. J."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"101742","DOI":"10.1016\/j.bonr.2024.101742","article-title":"Real world fracture prediction of fracture risk assessment tool (FRAX), osteoporosis self-assessment tool for Asians (OSTA) and one-minute osteoporosis risk test: An 11-year longitudinal study","volume":"20","author":"Sheng","year":"2024","journal-title":"Bone Rep."},{"key":"ref_32","first-page":"1103","article-title":"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","volume":"39","author":"Lehmann","year":"2024","journal-title":"J. Bone Miner. Res."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/2\/549\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T05:21:04Z","timestamp":1768454464000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/2\/549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":32,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["jcm15020549"],"URL":"https:\/\/doi.org\/10.3390\/jcm15020549","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]}}}