Iranian Journal of Nuclear Medicine

Iranian Journal of Nuclear Medicine

A machine learning study on prediction of osteopenia/osteoporosis from demographic and clinical data

Articles in Press

Document Type : Original Article

Authors
Hassan Zohrevand 1
Mahdi Ghorbani 2
Sajjad Yazdanpanah 2
Fahimeh Faghihi Moghadam 2
Ahmad Shalbaf 2
Mohammad Reza Asgari 2
Hasan Langari 3
Faraj Tabei 4
1 Student Research Committee, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
2 Biomedical Engineering and Medical Physics Department, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
3 Radiology Department, Taleghani Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
4 Nuclear Medicine Department, Taleghani Hospital, Shahid Beheshti University of Medical Sciences, Tehran, Iran
10.22034/irjnm.2026.130533.1763
Abstract
Introduction: Osteoporosis is a major public health problem worldwide. Patients with osteoporosis are at higher risk of bone fractures, pain, and immobilization. The aim of the present study was to predict osteopenia/osteoporosis from demographic, clinical and laboratory data using machine learning (ML) algorithms.
Methods: Demographic, clinical, and laboratory data from 239 cases (101 normal and 138 with osteopenia/osteoporosis) were collected. Thirteen features were included: age, sex, weight, height, smoking status, glucocorticoids use, chemotherapy, insulin use, levothyroxine usage, history of bone fracture, premature menopause, calcium usage, and vitamin D usage. The Python programming language was used for preprocessing and modeling. Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), MultiLayer Perceptron (MLP), and eXtreme Gradient Boosting (XGBoost) models were trained and evaluated. Accuracy, precision, recall, F1-score, and Area under the curve (AUC) were calculated.
Results: The XGBoost model showed better performance in terms of accuracy, precision and AUC.For the test group, the accuracy, precision, and AUC achieved by the XGBoost model were 0.68, 0.71, and 0.73, respectively.
Conclusion: The results of this study indicate that using the 13 selected features, it is possible to perform an initial prediction to distinguish between normal individuals and those with osteopenia or osteoporosis. Among the evaluated features, sex, age, and smoking had the highest importance. The proposed model may serve as a low-cost preliminary risk prediction model for identifying individuals at increased risk of low bone mineral density, particularly in settings with limited access to  DEXA scanning.
Keywords
Machine learning
Osteopenia
Osteoporosis
Demographic data
Subjects
  1. Clynes MA, Harvey NC, Curtis EM, Fuggle NR, Dennison EM, Cooper C. The epidemiology of osteoporosis. Br Med Bull. 2020 May;133(1):105-17.
  2. Ford MA, Bass M, Zhao Y, Bai JB, Zhao Y. Osteoporosis knowledge, self-efficacy, and beliefs among college students in the USA and China. J Osteoporos. 2011;2011: 729219.
  3. Kanis JA, Melton LJ 3rd, Christiansen C, Johnston CC, Khaltaev N. The diagnosis of osteoporosis. J Bone Miner Res. 1994 Aug;9(8):1137-41.
  4. Melton LJ. Epidemiology worldwide. Endocrinol Metab Clin North Am. 2003 Mar;32(1):1-13.
  5. Kasai S, Li F, Shiraishi J, Li Q, Doi K. Computerized detection of vertebral compression fractures on lateral chest radiographs: preliminary results with a tool for early detection of osteoporosis. Med Phys. 2006 Dec;33(12):4664-74.
  6. Gregson CL, Armstrong DJ, Bowden J, Cooper C, Edwards J, Gittoes NJL, Harvey N, Kanis J, Leyland S, Low R, McCloskey E, Moss K, Parker J, Paskins Z, Poole K, Reid DM, Stone M, Thomson J, Vine N, Compston J. UK clinical guideline for the prevention and treatment of osteoporosis. Arch Osteoporos. 2022 Apr;17(1):58.
  7. Park YS. Diagnosis and treatment of osteoporosis. J Korean Med Assoc. 2012;55(11):1083-1094.
  8. Sebro R, De la Garza-Ramos C. Opportunistic screening for osteoporosis and osteopenia from CT scans of the abdomen and pelvis using machine learning. Eur Radiol. 2023 Mar;33(3):1812-1823.
  9. Sangondimath G, Sen RK, Rehman TF. DEXA and Imaging in Osteoporosis. Indian J Orthop. 2023 Dec;57(Suppl 1):82-93. 
  10. Amani F, Tarighatnia A, Amanzadeh M, Asgarzadeh SA, Jalali S, Hamedan M, Nader N. Predicting osteoporosis with various machine learning algorithms using dual energy x-ray absorptiometry: A comparative analysis. Front Biomed Technol. 2026. (In press).
  11. Ahmad A, Crawford CH 3rd, Glassman SD, Dimar JR 2nd, Gum JL, Carreon LY. Correlation between bone density measurements on CT or MRI versus DEXA scan: A systematic review. N Am Spine Soc J. 2023 Mar;14:100204. 
  12. Harmer H, Radford S, Smail M. Feasibility study of using PCXMC 2.0 to estimate patient dose arising from DEXA scans. Radiat Prot Dosimetry 2018 Nov;181(4):418-422.
  13. Schini M, Johansson H, Harvey NC, Lorentzon M, Kanis JA, McCloskey EV. An overview of the use of the fracture risk assessment tool (FRAX) in osteoporosis. J Endocrinol Invest. 2024 Mar;47(3):501-511. 
  14. Scapicchio C, Gabelloni M, Barucci A, Cioni D, Saba L, Neri E. A deep look into radiomics. Radiol Med. 2021 Oct;126(10):1296-1311. 
  15. Mayerhoefer ME, Materka A, Langs G, Häggström I, Szczypiński P, Gibbs P, Cook G. Introduction to Radiomics. J Nucl Med. 2020 Apr;61(4):488-495. 
  16. Tamai K, Imanishi K, Terakawa M, Uematsu M, Kato M, Toyoda H, Suzuki A, Takahashi S, Yabu A, Sawada Y, Iwamae M, Kobayashi Y, Okamura Y, Taniwaki H, Kinoshita Y, Hoshino M, Tabuchi H, Nakamura H, Terai H. Deep learning algorithm for identifying osteopenia/osteoporosis using cervical radiography. Sci Rep. 2025 Jul;15(1):25274. 
  17. Wang J, He Y, Yan L, Chen S, Zhang K. Predicting osteoporosis and osteopenia by fusing deep transfer learning features and classical radiomics features based on single-source dual-energy CT imaging. Acad Radiol. 2024 Oct;31(10):4159-4170.
  18. Ghazizadeh M, Amoui M, Deevband MR, Aryana K, Karamian F, Divband A, Mahboubi-Fooladi Z, Montazerabadi A, Jafari E, Zirak A, Tavakoli M. Machine learning based radiomics analysis of SPECT images in predicting neuroendocrine tumors. Biomed Eng Adv. 2025;10:100197.
  19. Khajetash B, Mahdavi SR, Nikoofar A, Johnson L, Tavakoli M. Ensemble learning approach for prediction of early complications after radiotherapy for head and neck cancer using CT and MRI radiomic features. Sci Rep. 2025 Apr 24;15(1):14229. 
  20. Yasaka K, Akai H, Kunimatsu A, Kiryu S, Abe O. Prediction of bone mineral density from computed tomography: application of deep learning with a convolutional neural network. Eur Radiol. 2020 Jun;30(6):3549-3557. 
  21. Hu D, Ruan J, Liu C, Liang Z, Mu X. Quantitative CT imaging radiomics-based prediction of bone mineral density changes after sleeve gastrectomy. Obes Surg. 2025 Aug;35(8):3047-3056.
  22. Kalavakonda V, Madhivanan V, Lal A, Rithika S, Subramaniam SK, Sameer M. Unsupervised machine learning for osteoporosis diagnosis using singh index clustering on hip radiographs. arXiv preprint arXiv 2024:2411.15253.‏
    https://doi.org/10.48550/arXiv.2411.15253
  23. Sato Y, Yamamoto N, Inagaki N, Iesaki Y, Asamoto T, Suzuki T, Takahara S. Deep Learning for bone mineral density and T-score prediction from chest X-rays: A multicenter study. Biomedicines. 2022 Sep;10(9):2323. 
  24. Küçükçiloğlu Y, Şekeroğlu B, Adalı T, Şentürk N. Prediction of osteoporosis using MRI and CT scans with unimodal and multimodal deep-learning models. Diagn Interv Radiol. 2024 Jan;30(1):9-20.
  25. Jang R, Choi JH, Kim N, Chang JS, Yoon PW, Kim CH. Prediction of osteoporosis from simple hip radiography using deep learning algorithm. Sci Rep. 2021 Oct;11(1):19997.
  26. Klontzas ME, Manikis GC, Nikiforaki K, Vassalou EE, Spanakis K, Stathis I, Kakkos GA, Matthaiou N, Zibis AH, Marias K, Karantanas AH. Radiomics and Machine Learning Can Differentiate Transient Osteoporosis from Avascular Necrosis of the Hip. Diagnostics (Basel). 2021 Sep;11(9):1686. 
  27. He L, Liu Z, Liu C, Gao Z, Ren Q, Lei L, Ren J. Radiomics based on lumbar spine magnetic resonance imaging to detect osteoporosis. Acad Radiol. 2021 Jun;28(6):e165-e171.
  28. Zhao Y, Zhao T, Chen S, Zhang X, Serrano Sosa M, Liu J, Mo X, Chen X, Huang M, Li S, Zhang X, Huang C. Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence. Quant Imaging Med Surg. 2022 Feb;12(2):1198-1213.
  29. Nam KH, Seo I, Kim DH, Lee JI, Choi BK, Han IH. Machine learning model to predict osteoporotic spine with hounsfield units on lumbar computed tomography. J Korean Neurosurg Soc. 2019 Jul;62(4):442-449.
  30. Xie Q, Chen Y, Hu Y, Zeng F, Wang P, Xu L, Wu J, Li J, Zhu J, Xiang M, Zeng F. Development and validation of a machine learning-derived radiomics model for diagnosis of osteoporosis and osteopenia using quantitative computed tomography. BMC Med Imaging. 2022 Aug;22(1):140. 
  31. Huang WC, Chen IS, Yu HC, Chen CS, Wu FZ, Hsu CL, Wu PC. A simple and user-friendly machine learning model to detect osteoporosis in health examination populations in Southern Taiwan. Bone Rep. 2025 Jan;24:101826.
  32. Scikit Learn. Available at:  https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html. Accessed on: 6 October 2026.
  33. Talebi A, Bitarafan-Rajabi A, Alizadeh-Asl A, Seilani P, Khajetash B, Hajianfar G, Tavakoli M. Machine learning based radiomics model to predict radiotherapy induced cardiotoxicity in breast cancer. J Appl Clin Med Phys. 2025 Apr;26(4):e14614. 
  34. Li XY, Duan GY, Li L, Gao YY, Sun LW, Zhu S, Diao X, Wang N, Huang H. Logistic regression and machine learning algorithms for the risk prediction of perioperative adverse cardiovascular events in elderly patients. Aging Med (Milton). 2025 Oct 3;8(5):398-411. 
  35. Rigatti SJ. Random Forest. J Insur Med. 2017;47(1):31-39. 
  36. Wang J, Wu H, Wang F, Wang Y, Gu J. A Machine learning model integrating preoperative blood-based indices for early and noninvasive detection of endometrial cancer. J Inflamm Res. 2025 Aug;18:10873-10884. 
  37. Rahmani AM, Yousefpoor E, Yousefpoor MS, Mehmood Z, Haider A, Hosseinzadeh M, Ali Naqvi R. Machine learning (ML) in medicine: review, applications, and challenges. Mathematics 2021;9:2970.
  38. Kanis JA, Harvey NC, Johansson H, Odén A, Leslie WD, McCloskey EV. FRAX Update. J Clin Densitom. 2017 Jul-Sep;20(3):360-367.
Iranian Journal of Nuclear Medicine

Articles in Press, Accepted Manuscript
Available Online from 17 August 2026