Skip to main content

Advertisement

SpringerLink
Log in

Establish and validate the reliability of predictive models in bone mineral density by deep learning as examination tool for women

  • Original Article
  • Published:
Osteoporosis International Aims and scope Submit manuscript

Abstract

Summary

While FRAX with BMD could be more precise in estimating the fracture risk, DL-based models were validated to slightly reduce the number of under- and over-treated patients when no BMD measurements were available. The validated models could be used to screen for patients at a high risk of fracture and osteoporosis.

Purpose

Fracture risk assessment tool (FRAX) is useful in classifying the fracture risk level, and precise prediction can be achieved by estimating both clinical risk factors and bone mineral density (BMD) using dual X-ray absorptiometry (DXA). However, DXA is not frequently feasible because of its cost and accessibility. This study aimed to establish the reliability of deep learning (DL)-based alternative tools for screening patients at a high risk of fracture and osteoporosis.

Methods

Participants were enrolled from the National Bone Health Screening Project of Taiwan in this cross-sectional study. First, DL-based models were built to predict the lowest T-score value in either the lumbar spine, total hip, or femoral neck and their respective BMD values. The Bland–Altman analysis was used to compare the agreement between the models and DXA. Second, the predictive model to classify patients with a high fracture risk was built according to the estimated BMD from the first step and the FRAX score without BMD. The performance of the model was compared with the classification based on FRAX with BMD.

Results

Approximately 10,827 women (mean age, 65.4 ± 9.4 years) were enrolled. In the prediction of the lumbar spine BMD, total hip BMD, femoral neck BMD, and lowest T-score, the root-mean-square error (RMSE) was 0.099, 0.089, 0.076, and 0.68, respectively. The Bland–Altman analysis revealed a nonsignificant difference between the predictive models and DXA. The FRAX score with femoral neck BMD for major osteoporotic fracture risk was 9.7% ± 6.7%, whereas the risk for hip fracture was 3.3% ± 4.6%. Comparison between the classification of FRAX with and without BMD revealed the accuracy rate, positive predictive value (PPV), and negative predictive value (NPV) of 78.8%, 64.6%, and 89.9%, respectively. The area under the receiver operating characteristic curve (AUROC), accuracy rate, PPV, and NPV of the classification model were 0.913 (95% confidence interval: 0.904–0.922), 83.5%, 71.2%, and 92.2%, respectively.

Conclusion

While FRAX with BMD could be more precise in estimating the fracture risk, DL-based models were validated to slightly reduce the number of under- and over-treated patients when no BMD measurements were available. The validated models could be used to screen for patients at a high risk of fracture and osteoporosis.

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

Similar content being viewed by others

Data Availability

The data that support the findings of this study are available from the corresponding author, CHW, upon reasonable request.

References

  1. Ammann P, Rizzoli R (2003) Bone strength and its determinants. Osteoporos Int 14:13–18

    Article  Google Scholar 

  2. Sànchez-Riera L, Wilson N, Kamalaraj N, Nolla JM, Kok C, Li Y, Macara M, Norman R, Chen JS, Smith EU (2010) Osteoporosis and fragility fractures. Best Pract Res Clin Rheumatol 24:793–810

    Article  PubMed  Google Scholar 

  3. Cooper C (1997) The crippling consequences of fractures and their impact on quality of life. Am J Med 103:S12–S19

    Article  Google Scholar 

  4. Chen I-J, Chiang C-Y, Li Y-H, Chang C-H, Hu C-C, Chen D, Chang Y, Yang W-E, Shih H-N, Ueng S-N (2015) Nationwide cohort study of hip fractures: time trends in the incidence rates and projections up to 2035. Osteoporos Int 26:681–688

    Article  PubMed  Google Scholar 

  5. Cheung EY, Tan KC, Cheung C-L, Kung AW (2016) Osteoporosis in East Asia: current issues in assessment and management. Osteoporos Sarcopenia 2:118–133

    Article  PubMed  PubMed Central  Google Scholar 

  6. Lorentzon M (2019) Treating osteoporosis to prevent fractures: current concepts and future developments. J Intern Med 285:381–394

    Article  PubMed  Google Scholar 

  7. Dimai HP (2017) Use of dual-energy X-ray absorptiometry (DXA) for diagnosis and fracture risk assessment; WHO-criteria, T-and Z-score, and reference databases. Bone 104:39–43

    Article  PubMed  Google Scholar 

  8. Marín F, López-Bastida J, Díez-Pérez A, Sacristán J (2004) Bone mineral density referral for dual-energy X-ray absorptiometry using quantitative ultrasound as a prescreening tool in postmenopausal women from the general population: a cost-effectiveness analysis. Calcif Tissue Int 74:277–283

    Article  PubMed  Google Scholar 

  9. WHO Study Group (1994) Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: report of a WHO study group. Osteoporos Int 4:368–81

    Article  Google Scholar 

  10. Panichkul S, Sripramote M, Sriussawaamorn N (2004) Diagnostic performance of quantitative ultrasound calcaneus measurement in case finding for osteoporosis in Thai postmenopausal women. J Obstet Gynaecol Res 30:418–426

    Article  PubMed  Google Scholar 

  11. Koh LK, Sedrine WB, Torralba TP et al (2001) A simple tool to identify asian women at increased risk of osteoporosis. Osteoporos Int 12:699–705

    Article  CAS  PubMed  Google Scholar 

  12. Kanis JA, Oden A, Johansson H, Borgström F, Ström O, McCloskey E (2009) FRAX® and its applications to clinical practice. Bone 44:734–743

    Article  PubMed  Google Scholar 

  13. Hwang JS, Chan DC, Chen JF, Cheng TT, Wu CH, Soong YK, Tsai KS, Yang RS (2014) Clinical practice guidelines for the prevention and treatment of osteoporosis in Taiwan: summary. J Bone Miner Metab 32:10–16

    Article  PubMed  Google Scholar 

  14. Liu IT, Liang FW, Li CC, Chang YF, Sun ZJ, Lu TH, Chang CS, Wu CH (2022) Validation of the Taiwan FRAX® calculator for the prediction of fracture risk. Arch Osteoporos 17:27

    Article  CAS  PubMed  Google Scholar 

  15. Teeratakulpisarn N, Charoensri S, Theerakulpisut D, Pongchaiyakul C (2021) FRAX score with and without bone mineral density: a comparison and factors affecting the discordance in osteoporosis treatment in Thais. Arch Osteoporos 16:44

    Article  PubMed  Google Scholar 

  16. Alpaydin E (2021) Machine learning. MIT Press, Cambridge

    Book  Google Scholar 

  17. Kelleher JD (2019) Deep learning. MIT press, Cambridge

    Book  Google Scholar 

  18. Bhandary A, Prabhu GA, Rajinikanth V, Thanaraj KP, Satapathy SC, Robbins DE, Shasky C, Zhang Y-D, Tavares JMR, Raja NSM (2020) Deep-learning framework to detect lung abnormality–a study with chest X-Ray and lung CT scan images. Pattern Recogn Lett 129:271–278

    Article  Google Scholar 

  19. Kose U, Deperlioglu O, Alzubi J, Patrut B (2021) Deep learning for medical decision support systems. Springer, Berlin

    Book  Google Scholar 

  20. Ali F, El-Sappagh S, Islam SR, Kwak D, Ali A, Imran M, Kwak K-S (2020) A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion. Inf Fusion 63:208–222

    Article  Google Scholar 

  21. Chiu JS, Li YC, Yu FC, Wang YF (2006) Applying an artificial neural network to predict osteoporosis in the elderly. Stud Health Technol Inform 124:609–614

    PubMed  Google Scholar 

  22. Smets J, Shevroja E, Hugle T, Leslie WD, Hans D (2021) Machine learning solutions for osteoporosis-a review. J Bone Min Res 36:833–851

    Article  Google Scholar 

  23. Marshall D, Johnell O, Wedel H (1996) Meta-analysis of how well measures of bone mineral density predict occurrence of osteoporotic fractures. BMJ (Clinical Research ed) 312:1254–1259

    Article  CAS  PubMed  Google Scholar 

  24. Kanis JA, McCloskey EV, Johansson H, Oden A, Melton LJ III, Khaltaev N (2008) A reference standard for the description of osteoporosis. Bone 42:467–475

    Article  CAS  PubMed  Google Scholar 

  25. van der Heijden GJ, Donders AR, Stijnen T, Moons KG (2006) Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example. J Clin Epidemiol 59:1102–1109

    Article  PubMed  Google Scholar 

  26. Azur MJ, Stuart EA, Frangakis C, Leaf PJ (2011) Multiple imputation by chained equations: what is it and how does it work? Int J Methods Psychiatr Res 20:40–49

    Article  PubMed  PubMed Central  Google Scholar 

  27. Efron B, Tibshirani R (1997) Improvements on cross-validation: the.632+ bootstrap method. J Am Stat Assoc 92:548–560

    Google Scholar 

  28. Wu Y-C, Feng J-W (2018) Development and application of artificial neural network. Wireless Pers Commun 102:1645–1656

    Article  Google Scholar 

  29. Baldassi C, Malatesta EM, Zecchina R (2019) Properties of the geometry of solutions and capacity of multilayer neural networks with rectified linear unit activations. Phys Rev Lett 123:170602

    Article  CAS  PubMed  Google Scholar 

  30. Arora S, Gupta A, Jain R, Nayyar A (2021) Optimization of the CNN model for hand sign language recognition using Adam optimization technique. Micro-electronics and Telecommunication Engineering. Springer, Singapore, pp 89–104

    Google Scholar 

  31. Gluer CC, Blake G, Lu Y, Blunt BA, Jergas M, Genant HK (1995) Accurate assessment of precision errors: how to measure the reproducibility of bone densitometry techniques. Osteoporos Int 5:262–270

    Article  CAS  PubMed  Google Scholar 

  32. Chen R-C, Caraka RE, Arnita NEG et al (2020) An end to end of scalable tree boosting system. Sylwan 165:1–11

    Google Scholar 

  33. Bland JM, Altman DG (1986) Statistical methods for assessing agreement between two methods of clinical measurement. Lancet (London, England) 1:307–310

    Article  CAS  PubMed  Google Scholar 

  34. Fluss R, Faraggi D, Reiser B (2005) Estimation of the Youden index and its associated cutoff point. Biom J Biom Z 47:458–472

    Article  Google Scholar 

  35. Dagan N, Elnekave E (2020) Automated opportunistic osteoporotic fracture risk assessment using computed tomography scans to aid in FRAX underutilization. Nat Med 26:77–82

    Article  CAS  PubMed  Google Scholar 

  36. Cadarette SM, Jaglal SB, Kreiger N, McIsaac WJ, Darlington GA, Tu JV (2000) Development and validation of the osteoporosis risk assessment instrument to facilitate selection of women for bone densitometry. CMAJ Can Med Assoc J 162:1289–1294

    CAS  Google Scholar 

  37. Lydick E, Cook K, Turpin J, Melton M, Stine R, Byrnes C (1998) Development and validation of a simple questionnaire to facilitate identification of women likely to have low bone density. Am J Manag Care 4:37–48

    CAS  PubMed  Google Scholar 

  38. Sedrine WB, Chevallier T, Zegels B, Kvasz A, Micheletti MC, Gelas B, Reginster JY (2002) Development and assessment of the osteoporosis index of risk (OSIRIS) to facilitate selection of women for bone densitometry. Gynecol Endocrinol 16:245–250

    Article  CAS  PubMed  Google Scholar 

  39. Dane C, Dane B, Cetin A, Erginbas M (2008) The role of quantitative ultrasound in predicting osteoporosis defined by dual-energy X-ray absorptiometry in pre- and postmenopausal women. Climacteric 11:296–303

    Article  CAS  PubMed  Google Scholar 

  40. Hsieh CI, Zheng K, Lin C et al (2021) Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning. Nat Commun 12:5472

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Wu Q, Nasoz F, Jung J, Bhattarai B, Han MV, Greenes RA, Saag KG (2021) Machine learning approaches for the prediction of bone mineral density by using genomic and phenotypic data of 5130 older men. Sci Rep 11:4482

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  42. Shioji M, Yamamoto T, Ibata T, Tsuda T, Adachi K, Yoshimura N (2017) Artificial neural networks to predict future bone mineral density and bone loss rate in Japanese postmenopausal women. BMC Res Notes 10:590

    Article  PubMed  PubMed Central  Google Scholar 

  43. Fan B, Lu Y, Genant H, Fuerst T, Shepherd J (2010) Does standardized BMD still remove differences between Hologic and GE-Lunar state-of-the-art DXA systems? Osteoporos Int 21:1227–1236

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

The Taiwan Osteoporosis Association (TOA) conducted the national circuit program for BMD measurements, sponsored by Merck Sharp & Dohme Pharmaceutical Company. A bus installed with a DXA machine and a nurse and a radiology technician, both certified by the International Society of Clinical Densitometry, were sponsored by Merck Sharp & Dohme Pharmaceutical Company. E-Da hospital, the TOA, and Merck Sharp & Dohme Pharmaceutical Company had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; or the decision to submit the manuscript for publication.

Funding

This study was supported by the research project of E-Da Hospital, Taiwan (grant number: EDAHP110007).

Author information

Authors and Affiliations

  1. Department of Family Medicine and Community Medicine, E-Da Hospital, I-Shou University, Kaohsiung, Taiwan

    Wei- Chieh Hung & Wei-Leng Chin

  2. School of Medicine for International Students, College of Medicine, I-Shou University School, Kaohsiung, Taiwan

    Wei- Chieh Hung

  3. Institute of Biotechnology and Chemical Engineering, I-Shou University, Kaohsiung, Taiwan

    Wei- Chieh Hung

  4. Department of Computer Science and Information Engineering, National Yunlin University of Science and Technology, Douliu, Taiwan

    Yih-Lon Lin

  5. Department of Internal Medicine, Division of Rheumatology, Allergy and Immunology, Kaohsiung Chang Gung Memorial Hospital and School of Medicine, College of Medicine, Chang Gung University, Taoyuan, Taiwan

    Tien-Tsai Cheng

  6. Enterprise Resource Planning Technical Support and Research and Design Department, InfoChamp Systems Corporation, Kaohsiung, Taiwan

    Li-Te Tu & Chih-Kui Chen

  7. Departments of Biological Science and Technology, I-Shou University, Kaohsiung, Taiwan

    Chih-Hui Yang

  8. Institute of Gerontology, College of Medicine, National Cheng Kung University, Tainan, Taiwan

    Chih-Hsing Wu

  9. Department of Family Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan

    Chih-Hsing Wu

Authors
  1. Wei- Chieh Hung
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yih-Lon Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tien-Tsai Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Wei-Leng Chin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Li-Te Tu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chih-Kui Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Chih-Hui Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Chih-Hsing Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Chih-Hui Yang or Chih-Hsing Wu.

Ethics declarations

Ethical approval

This study was approved by the local institutional review board of Chang Gung Memorial Hospital (102-1878B) and the institutional review board of E-Da Hospital (EMRP-110–085). Informed consent was obtained from all individuals who participated in the study. All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Conflicts of interest

None.

Additional information

Publisher's Note

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

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

Hung, W.C., Lin, YL., Cheng, TT. et al. Establish and validate the reliability of predictive models in bone mineral density by deep learning as examination tool for women. Osteoporos Int 35, 129–141 (2024). https://doi.org/10.1007/s00198-023-06913-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00198-023-06913-5

Keywords

Search

Navigation