Skip to main content

Advertisement

SpringerLink
Log in

Artificial Intelligence-enabled Chest X-ray Classifies Osteoporosis and Identifies Mortality Risk

  • Original Paper
  • Published:
Journal of Medical Systems Aims and scope Submit manuscript

Abstract

A deep learning model was developed to identify osteoporosis from chest X-ray (CXR) features with high accuracy in internal and external validation. It has significant prognostic implications, identifying individuals at higher risk of all-cause mortality. This Artificial Intelligence (AI)-enabled CXR strategy may function as an early detection screening tool for osteoporosis. The aim of this study was to develop a deep learning model (DLM) to identify osteoporosis via CXR features and investigate the performance and clinical implications. This study collected 48,353 CXRs with the corresponding T score according to Dual energy X-ray Absorptiometry (DXA) from the academic medical center. Among these, 35,633 CXRs were used to identify CXR- Osteoporosis (CXR-OP). Another 12,720 CXRs were used to validate the performance, which was evaluated by the area under the receiver operating characteristic curve (AUC). Furthermore, CXR-OP was tested to assess the long-term risks of mortality, which were evaluated by Kaplan‒Meier survival analysis and the Cox proportional hazards model. The DLM utilizing CXR achieved AUCs of 0.930 and 0.892 during internal and external validation, respectively. The group that underwent DXA with CXR-OP had a higher risk of all-cause mortality (hazard ratio [HR] 2.59, 95% CI: 1.83–3.67), and those classified as CXR-OP in the group without DXA also had higher all-cause mortality (HR: 1.67, 95% CI: 1.61–1.72) in the internal validation set. The external validation set produced similar results. Our DLM uses CXRs for early detection of osteoporosis, aiding physicians to identify those at risk. It has significant prognostic implications, improving life quality and reducing mortality. AI-enabled CXR strategy may serve as a screening tool.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data availability

The data analyzed in this study is not publicly available due to privacy and security concerns. The data may be shared with a third party upon execution of data sharing agreement for reasonable requests, such requests should be addressed to WHF (e-mail: rumaf.fang@gmail.com) or DJT.

Abbreviations

AI:

Artificial Intelligence

AUC:

Area Under the Curve

AMI:

Acute Myocardial Infarction

Afib:

Atrial fibrillation

BMD:

Bone Mineral Density

CT:

Computed Tomography

CXR:

Chest X-Ray

CVD :

Cardiovascular Disease

CV:

Cardiovascular

CAD:

Coronary Artery Disease

DXA:

Dual energy X-ray Absorptiometry

DLM:

Deep Learning Model

DICOM:

Digital Imaging and Communications in Medicine

HR:

Hazard Ratio

HF:

Heart failure

ICD:

International Classification of Diseases

NPV:

Negative Predictive Value

OP:

Osteoporosis

PPV:

Positive Predictive Value

ROC:

Receiver Operating Characteristic

STK:

Stroke

Sens.:

Sensitivity

Spec.:

Specificity

WHO:

World Health Organization

References

  1. Gharib, H., et al., Associazione Medici Endocrinologi, and European Thyroid Association medical guidelines for clinical practice for the diagnosis and management of thyroid nodules. Endocr Pract, 2010. 16(Suppl 1): p. 1-43.

    Article  PubMed  Google Scholar 

  2. Organization, W.H. WHO scientific group on the assessment of osteoporosis at primary health care level. in Summary meeting report. 2004.

  3. Curry, S.J., et al., Screening for osteoporosis to prevent fractures: US Preventive Services Task Force recommendation statement. Jama, 2018. 319(24): p. 2521-2531.

    Article  PubMed  Google Scholar 

  4. Shao, C.-J., et al., A nationwide seven-year trend of hip fractures in the elderly population of Taiwan. Bone, 2009. 44(1): p. 125-129.

    Article  PubMed  Google Scholar 

  5. Wooltorton, E., Osteoporosis treatment: raloxifene (Evista) and stroke mortality. Cmaj, 2006. 175(2): p. 147.

    Article  PubMed  PubMed Central  Google Scholar 

  6. Bliuc, D., et al., Mortality risk associated with low-trauma osteoporotic fracture and subsequent fracture in men and women. Jama, 2009. 301(5): p. 513-21.

    Article  CAS  PubMed  Google Scholar 

  7. Ganry, O., et al., Bone mass density and risk of breast cancer and survival in older women. Eur J Epidemiol, 2004. 19(8): p. 785-92.

    Article  CAS  PubMed  Google Scholar 

  8. Cai, S., et al., Bone mineral density and osteoporosis in relation to all-cause and cause-specific mortality in NHANES: A population-based cohort study. Bone, 2020. 141: p. 115597.

    Article  CAS  PubMed  Google Scholar 

  9. Yamamoto, N., et al., Deep learning for osteoporosis classification using hip radiographs and patient clinical covariates. Biomolecules, 2020. 10(11): p. 1534.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Mueller, D. and A. Gandjour, Cost‐effectiveness of using clinical risk factors with and without DXA for osteoporosis screening in postmenopausal women. Value in Health, 2009. 12(8): p. 1106-1117.

    Article  PubMed  Google Scholar 

  11. Orimo, H., et al., Japanese 2011 guidelines for prevention and treatment of osteoporosis—executive summary. Archives of osteoporosis, 2012. 7: p. 3-20.

    Article  PubMed  PubMed Central  Google Scholar 

  12. Sedlak, C.A., M.O. Doheny, and S.L. Jones, Osteoporosis education programs: changing knowledge and behaviors. Public health nursing, 2000. 17(5): p. 398-402.

    Article  CAS  PubMed  Google Scholar 

  13. Sato, M., et al., Bone fractures and feeling at risk for osteoporosis among women in Japan: patient characteristics and outcomes in the National Health and Wellness Survey. Archives of Osteoporosis, 2014. 9: p. 1-9.

    Article  Google Scholar 

  14. Compston, J.E., M.R. McClung, and W.D. Leslie, Osteoporosis. Lancet, 2019. 393(10169): p. 364-376.

    Article  CAS  PubMed  Google Scholar 

  15. Curtis, J.R., et al., Longitudinal trends in use of bone mass measurement among older americans, 1999-2005. J Bone Miner Res, 2008. 23(7): p. 1061-7.

    Article  PubMed  PubMed Central  Google Scholar 

  16. Davis, S.R., et al., Simplifying screening for osteoporosis in Australian primary care: the Prospective Screening for Osteoporosis; Australian Primary Care Evaluation of Clinical Tests (PROSPECT) study. Menopause, 2011. 18(1): p. 53-9.

    Article  PubMed  Google Scholar 

  17. Yasaka, K., et al., Prediction of bone mineral density from computed tomography: application of deep learning with a convolutional neural network. European radiology, 2020. 30: p. 3549-3557.

    Article  CAS  PubMed  Google Scholar 

  18. Pickhardt, P.J., et al., Opportunistic screening for osteoporosis using abdominal computed tomography scans obtained for other indications. Annals of internal medicine, 2013. 158(8): p. 588-595.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Krishnaraj, A., et al., Simulating dual-energy X-ray absorptiometry in CT using deep-learning segmentation cascade. Journal of the American College of Radiology, 2019. 16(10): p. 1473-1479.

    Article  PubMed  Google Scholar 

  20. Dagan, N., et al., Automated opportunistic osteoporotic fracture risk assessment using computed tomography scans to aid in FRAX underutilization. Nature medicine, 2020. 26(1): p. 77-82.

    Article  CAS  PubMed  Google Scholar 

  21. Benhamou, C.-L., et al., Fractal analysis of radiographic trabecular bone texture and bone mineral density: two complementary parameters related to osteoporotic fractures. Journal of bone and mineral research, 2001. 16(4): p. 697-704.

    Article  CAS  PubMed  Google Scholar 

  22. LeCun, Y., Y. Bengio, and G. Hinton, Deep learning. nature, 2015. 521(7553): p. 436–444.

  23. Lindsey, R., et al., Deep neural network improves fracture detection by clinicians. Proceedings of the National Academy of Sciences, 2018. 115(45): p. 11591-11596.

    Article  CAS  Google Scholar 

  24. He, K., et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. in Proceedings of the IEEE international conference on computer vision. 2015.

  25. Gulshan, V., et al., Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama, 2016. 316(22): p. 2402-2410.

    Article  PubMed  Google Scholar 

  26. Ardila, D., et al., End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature medicine, 2019. 25(6): p. 954-961.

    Article  CAS  PubMed  Google Scholar 

  27. Smets, J., et al., Machine learning solutions for osteoporosis—a review. Journal of bone and mineral research, 2021. 36(5): p. 833-851.

    Article  PubMed  Google Scholar 

  28. Nguyen, T.P., et al., A novel approach for evaluating bone mineral density of hips based on Sobel gradient-based map of radiographs utilizing convolutional neural network. Computers in Biology and Medicine, 2021. 132: p. 104298.

    Article  CAS  PubMed  Google Scholar 

  29. Hsieh, C.-I., et al., Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning. Nature communications, 2021. 12(1): p. 5472.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Zhang, B., et al., Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: A multicenter retrospective cohort study. Bone, 2020. 140: p. 115561.

    Article  CAS  PubMed  Google Scholar 

  31. Jang, M., et al., Opportunistic osteoporosis screening using chest radiographs with deep learning: Development and external validation with a cohort dataset. Journal of Bone and Mineral Research, 2022. 37(2): p. 369-377.

    Article  PubMed  Google Scholar 

  32. Sato, Y., et al., Deep Learning for Bone Mineral Density and T-Score Prediction from Chest X-rays: A Multicenter Study. Biomedicines, 2022. 10(9).

  33. Chang, C.H., et al., Electrocardiogram-based heart age estimation by a deep learning model provides more information on the incidence of cardiovascular disorders. Front Cardiovasc Med, 2022. 9: p. 754909.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  34. Liu, W.T., et al., A deep-learning algorithm-enhanced system integrating electrocardiograms and chest X-rays for diagnosing aortic dissection. Can J Cardiol, 2022. 38(2): p. 160-168.

    Article  PubMed  Google Scholar 

  35. Seok, H., et al., High prevalence of spine–femur bone mineral density discordance and comparison of vertebral fracture risk assessment using femoral neck and lumbar spine bone density in Korean patients. Journal of bone and mineral metabolism, 2014. 32: p. 405-410.

    Article  PubMed  Google Scholar 

  36. El Maghraoui, A., et al., Prevalence and risk factors of discordance in diagnosis of osteoporosis using spine and hip bone densitometry. Annals of the rheumatic diseases, 2007. 66(2): p. 271-272.

    Article  PubMed  PubMed Central  Google Scholar 

  37. Kumar, D.A. and M. Anburajan, The role of hip and chest radiographs in osteoporotic evaluation among south Indian women population: a comparative scenario with DXA. Journal of endocrinological investigation, 2014. 37: p. 429-440.

    Article  PubMed  Google Scholar 

  38. Holcombe, S.A., et al., Measuring rib cortical bone thickness and cross section from CT. Med Image Anal, 2018. 49: p. 27-34.

    Article  PubMed  Google Scholar 

  39. Chen, H., et al., Age-related changes in trabecular and cortical bone microstructure. Int J Endocrinol, 2013. 2013: p. 213234.

    Article  PubMed  PubMed Central  Google Scholar 

  40. Yao, W.J., et al., Differential Changes in Regional Bone Mineral Density in Healthy Chinese: Age-Related and Sex-Dependent. Calcified Tissue International, 2001. 68(6): p. 330-336.

    Article  CAS  PubMed  Google Scholar 

  41. Rajaei, A., et al., Correlating Whole-Body Bone Mineral Densitometry Measurements to Those From Local Anatomical Sites. Iran J Radiol, 2016. 13(1): p. e25609.

    Article  PubMed  PubMed Central  Google Scholar 

  42. Sato, Y., et al., Deep learning for bone mineral density and T-score prediction from chest X-rays: A multicenter study. Biomedicines, 2022. 10(9): p. 2323.

    Article  PubMed  PubMed Central  Google Scholar 

  43. Siris, E.S., et al., Bone mineral density thresholds for pharmacological intervention to prevent fractures. Archives of internal medicine, 2004. 164(10): p. 1108-1112.

    Article  PubMed  Google Scholar 

  44. Kanis, J.A., et al., European guidance for the diagnosis and management of osteoporosis in postmenopausal women. Osteoporosis international, 2013. 24(1): p. 23-57.

    Article  CAS  PubMed  Google Scholar 

  45. Camacho, P.M., et al., American Association of Clinical Endocrinologists/American College of Endocrinology clinical practice guidelines for the diagnosis and treatment of postmenopausal osteoporosis—2020 update. Endocrine Practice, 2020. 26: p. 1-46.

    Article  PubMed  Google Scholar 

  46. Molarius, A. and S. Janson, Self-rated health, chronic diseases, and symptoms among middle-aged and elderly men and women. Journal of Clinical Epidemiology, 2002. 55(4): p. 364-370.

    Article  PubMed  Google Scholar 

  47. Hallberg, I., et al., Health-related quality of life after osteoporotic fractures. Osteoporosis International, 2004. 15: p. 834-841.

    Article  CAS  PubMed  Google Scholar 

  48. Hannan, M.T., et al., Risk factors for longitudinal bone loss in elderly men and women: the Framingham Osteoporosis Study. Journal of Bone and Mineral Research, 2000. 15(4): p. 710-720.

    Article  CAS  PubMed  Google Scholar 

  49. De Laet, C.E. and H.A. Pols, Fractures in the elderly: epidemiology and demography. Best Practice & Research Clinical Endocrinology & Metabolism, 2000. 14(2): p. 171-179.

    Article  Google Scholar 

  50. Berry, S.D., et al., Competing risk of death: an important consideration in studies of older adults. J Am Geriatr Soc, 2010. 58(4): p. 783-7.

    Article  PubMed  PubMed Central  Google Scholar 

  51. Kanis, J.A., et al., FRAX® and its applications to clinical practice. Bone, 2009. 44(5): p. 734-743.

    Article  PubMed  Google Scholar 

  52. Nguyen, N.D., et al., Development of a nomogram for individualizing hip fracture risk in men and women. Osteoporosis International, 2007. 18: p. 1109-1117.

    Article  CAS  PubMed  Google Scholar 

  53. Assessment of fracture risk and its application to screening for postmenopausal osteoporosis. Report of a WHO Study Group. World Health Organ Tech Rep Ser, 1994. 843: p. 1–129.

Download references

Funding

National Science and Technology Council,NSTC 112-2222-E-030 -002 -MY2,NSTC 112-2321-B-016-003,Ministry of Science and Technology,Taiwan,MOST110-2314-B-016-010-MY3.

Author information

Authors and Affiliations

  1. Department of Statistics and Information Science, Fu Jen Catholic University, New Taipei City, Taiwan, R.O.C.

    Dung-Jang Tsai

  2. Medical Technology Education Center, School of Medicine, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Dung-Jang Tsai & Chin Lin

  3. Artificial Intelligence of Things Center, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Dung-Jang Tsai, Chin Lin & Wen-Hui Fang

  4. School of Public Health, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Chin Lin

  5. Division of Cardiology, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Chin-Sheng Lin

  6. Medical Informatics Office, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Chia-Cheng Lee

  7. Division of Colorectal Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Chia-Cheng Lee

  8. Department of Otolaryngology-Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Chih-Hung Wang

  9. Graduate Institute of Medical Sciences, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Chih-Hung Wang

  10. Department of Family and Community Medicine, Department of Internal Medicine, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan, R.O.C.

    Wen-Hui Fang

Authors
  1. Dung-Jang Tsai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chin Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chin-Sheng Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chia-Cheng Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chih-Hung Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Wen-Hui Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors participated in designing the study, generating hypotheses, interpreting the data, and critically reviewing the paper. DJT and WHF wrote the first draft, and CL, CSL, CCL, and CHW contributed substantially to writing subsequent versions. DJT designed and conducted statistical analyses with support from CL. All authors had full access to all the data in the study and accepted responsibility for the decision to submit for publication. DJT and WHF verified all the data used in this study. The corresponding author (WHF) attests that all listed authors meet authorship criteria and that no others meeting the criteria have been omitted.

Corresponding author

Correspondence to Wen-Hui Fang.

Ethics declarations

Ethics approval

The Tri-Service General Hospital, Taipei, Taiwan, conducted the ethical review of this study (IRB No. C202105049). The institutional review board agreed to waive individual consent since the data were collected retrospectively and analyzed on the intranet.

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 2887 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tsai, DJ., Lin, C., Lin, CS. et al. Artificial Intelligence-enabled Chest X-ray Classifies Osteoporosis and Identifies Mortality Risk. J Med Syst 48, 12 (2024). https://doi.org/10.1007/s10916-023-02030-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10916-023-02030-2

Keywords

Search

Navigation