Skip to main content

Advertisement

SpringerLink
Log in

Comparing three machine learning approaches to design a risk assessment tool for future fractures: predicting a subsequent major osteoporotic fracture in fracture patients with osteopenia and osteoporosis

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

Abstract

Summary

Four machine learning models were developed and compared to predict the risk of a future major osteoporotic fracture (MOF), defined as hip, wrist, spine and humerus fractures, in patients with a prior fracture. We developed a user-friendly tool for risk calculation of subsequent MOF in osteopenia patients, using the best performing model.

Introduction

Major osteoporotic fractures (MOFs), defined as hip, wrist, spine and humerus fractures, can have serious consequences regarding morbidity and mortality. Machine learning provides new opportunities for fracture prediction and may aid in targeting preventive interventions to patients at risk of MOF. The primary objective is to develop and compare several models, capable of predicting the risk of MOF as a function of time in patients seen at the fracture and osteoporosis outpatient clinic (FO-clinic) after sustaining a fracture.

Methods

Patients aged > 50 years visiting an FO-clinic were included in this retrospective study. We compared discriminative ability (concordance index) for predicting the risk on MOF with a Cox regression, random survival forests (RSF) and an artificial neural network (ANN)-DeepSurv model. Missing data was imputed using multiple imputations by chained equations (MICE) or RSF’s imputation function. Analyses were performed for the total cohort and a subset of osteopenia patients without vertebral fracture.

Results

A total of 7578 patients were included, 805 (11%) patients sustained a subsequent MOF. The highest concordance-index in the total dataset was 0.697 (0.664–0.730) for Cox regression; no significant difference was determined between the models. In the osteopenia subset, Cox regression outperformed RSF (p = 0.043 and p = 0.023) and ANN-DeepSurv (p = 0.043) with a c-index of 0.625 (0.562–0.689). Cox regression was used to develop a MOF risk calculator on this subset.

Conclusion

We show that predicting the risk of MOF in patients who already sustained a fracture can be done with adequate discriminative performance. We developed a user-friendly tool for risk calculation of subsequent MOF in patients with osteopenia.

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

Notes

  1. Determined with the CKD-EPI formula

References

  1. Odén A, McCloskey EV, Kanis JA, Harvey NC, Johansson H (2015) Burden of high fracture probability worldwide: secular increases 2010–2040. Osteoporos Int 26:2243–2248. https://doi.org/10.1007/s00198-015-3154-6

    Article  PubMed  Google Scholar 

  2. Johnell O, Kanis JA (2006) An estimate of the worldwide prevalence and disability associated with osteoporotic fractures. Osteoporos Int 17:1726–1733. https://doi.org/10.1007/s00198-006-0172-4

    Article  CAS  PubMed  Google Scholar 

  3. Briot K, Paternotte S, Kolta S, Eastell R, Felsenberg D, Reid DM, Glüer CC, Roux C (2013) FRAX®: prediction of major osteoporotic fractures in women from the general population: the OPUS study. PLoS One 8:e83436. https://doi.org/10.1371/journal.pone.0083436

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Jürisson M, Pisarev H, Kanis J, Borgström F, Svedbom A, Kallikorm R, Lember M, Uusküla A (2016) Quality of life, resource use, and costs related to hip fracture in Estonia. Osteoporos Int 27:2555–2566. https://doi.org/10.1007/s00198-016-3544-4

    Article  PubMed  Google Scholar 

  5. Goldacre MJ, Roberts SE, Yeates D (2002) Mortality after admission to hospital with fractured neck of femur: database study. BMJ 325:868–869. https://doi.org/10.1136/bmj.325.7369.868

    Article  PubMed  PubMed Central  Google Scholar 

  6. Warriner AH, Patkar NM, Yun H, Delzell E (2011) Minor, major, low-trauma, and high-trauma fractures: what are the subsequent fracture risks and how do they vary? Curr Osteoporos Rep 9:122–128. https://doi.org/10.1007/s11914-011-0064-1

    Article  PubMed  Google Scholar 

  7. CBO Richtlijn Osteoporose en Fractuurpreventie-2011. https://www.volksgezondheidenzorg.info/bestanden/documenten/cbo-richtlijn-osteoporose-en-fractuurpreventie-2011. Accessed 21 Oct 2019

  8. Weda M, Jansen ME, Vonk RAA (2017) Personalised medicine - Implementatie in de praktijk en data-infrastructuren. RIVM Briefrapport 2017–0006

  9. El-Hajj Fuleihan G, Chakhtoura M, Cauley JA, Chamoun N (2017) Worldwide fracture prediction. J Clin Densitom 20:397–424. https://doi.org/10.1016/j.jocd.2017.06.008

    Article  PubMed  Google Scholar 

  10. Tseng WJ, Hung LW, Shieh JS, Abbod MF, Lin J (2013) Hip fracture risk assessment: artificial neural network outperforms conditional logistic regression in an age- and sex-matched case control study. BMC Musculoskelet Disord 14:1. https://doi.org/10.1186/1471-2474-14-207

    Article  Google Scholar 

  11. Ho-Le TP, Center JR, Eisman JA et al (2017) Prediction of hip fracture in post-menopausal women using artificial neural network approach. Conf Proc Annu Int Conf IEEE Eng Med Biol Soc IEEE Eng Med Biol Soc Annu Conf 2017:4207–4210. https://doi.org/10.1109/EMBC.2017.8037784

    Article  Google Scholar 

  12. Ferizi U, Honig S, Chang G (2019) Artificial intelligence, osteoporosis and fragility fractures. Curr Opin Rheumatol 31:368–375. https://doi.org/10.1097/BOR.0000000000000607

    Article  PubMed  PubMed Central  Google Scholar 

  13. Hegeman JH, Willemsen G, van Nieuwpoort J, Kreeftenberg HG, van der Veer E, Slaets JP, ten Duis H (2004) Effective tracing of osteoporosis at a fracture and osteoporosis clinic in Groningen; an analysis of the first 100 patients. Ned Tijdschr Geneeskd 148:2180–2185

    CAS  PubMed  Google Scholar 

  14. DIS open data. https://www.opendisdata.nl/. Accessed 7 Feb 2020

  15. Dziak JJ, Henry KL (2017) Two-part predictors in regression models. Multivar Behav Res 52:551–561. https://doi.org/10.1080/00273171.2017.1333404

    Article  Google Scholar 

  16. R Core Team (2019) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna URL http://www.R-project.org/

    Google Scholar 

  17. Cox DR (1972) Regression models and life-tables. J R Stat Soc Ser B 34:187–220

    Google Scholar 

  18. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS (2008) Random survival forests. Ann Appl Stat 2:841–860. https://doi.org/10.1214/08-AOAS169

    Article  Google Scholar 

  19. Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y (2018) DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med Res Methodol 18:24. https://doi.org/10.1186/s12874-018-0482-1

    Article  PubMed  PubMed Central  Google Scholar 

  20. Schoenfeld D (1982) Partial residuals for the proportional hazards regression model. Biometrika 69:239. https://doi.org/10.2307/2335876

    Article  Google Scholar 

  21. Steyerberg EW (2019) Clinical prediction models. Springer International Publishing, Cham

    Book  Google Scholar 

  22. Shepherd BE, Rebeiro PF (2017) Assessing and interpreting the association between continuous covariates and outcomes in observational studies of HIV using splines. J Acquir Immune Defic Syndr 74:e60–e63. https://doi.org/10.1097/QAI.0000000000001221

    Article  PubMed  PubMed Central  Google Scholar 

  23. Breiman L (2001) Random forest. Mach Learn 45:5–32. https://doi.org/10.1017/CBO9781107415324.004

    Article  Google Scholar 

  24. Claesen M, De Moor B (2015) Hyperparameter search in machine learning. https://ftp.esat.kuleuven.be/pub/SISTA/claesenm/reports/14-188.pdf. Accessed 21 Oct 2019

  25. Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. 3rd Int Conf Learn Represent ICLR 2015 - Conf Track Proc 1–15

  26. Moradi R, Berangi R, Minaei B (2020) A survey of regularization strategies for deep models. Springer, Netherlands

    Google Scholar 

  27. Pedregosa F, Varoquaux G, Gramfort A et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830. https://doi.org/10.1145/2786984.2786995

    Article  Google Scholar 

  28. Fotso S (2019) PySurvival: open source package for survival analysis modeling. https://square.github.io/pysurvival/#:~:text=PySurvival%20is%20an%20open%20source,compatible%20with%20Python%202.7%2D3.7. Accessed 14 Mar 2020

  29. Kim DW, Lee S, Kwon S, Nam W, Cha IH, Kim HJ (2019) Deep learning-based survival prediction of oral cancer patients. Sci Rep 9:6994. https://doi.org/10.1038/s41598-019-43372-7

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Forgetta V, Keller-Baruch J, Forest M et al (2018) Machine learning to predict osteoporotic fracture risk from genotypes. bioRxiv:413716. https://doi.org/10.1101/413716

  31. Nissinen T (2019) Convolutional neural networks in osteoporotic fracture risk prediction using spine DXA images - Master’s thesis Computer Sciences, University of Eastern Finland

  32. Kruse C, Eiken P, Vestergaard P (2017) Machine learning principles can improve hip fracture prediction. Calcif Tissue Int 100:348–360. https://doi.org/10.1007/s00223-017-0238-7

    Article  CAS  PubMed  Google Scholar 

  33. Ensrud KE, Lui L-Y, Taylor BC, Schousboe JT, Donaldson MG, Fink HA, Cauley JA, Hillier TA, Browner WS, Cummings SR, Study of Osteoporotic Fractures Research Group (2009) A comparison of prediction models for fractures in older women: is more better? Arch Intern Med 169:2087–2094. https://doi.org/10.1001/archinternmed.2009.404

    Article  PubMed  PubMed Central  Google Scholar 

  34. Johansson H, Siggeirsdóttir K, Harvey NC, Odén A, Gudnason V, McCloskey E, Sigurdsson G, Kanis JA (2017) Imminent risk of fracture after fracture Europe PMC funders group. Osteoporos Int 28:775–780. https://doi.org/10.1007/s00198-016-3868-0

    Article  CAS  PubMed  Google Scholar 

  35. Reber KC, König HH, Becker C, Rapp K, Büchele G, Mächler S, Lindlbauer I (2018) Development of a risk assessment tool for osteoporotic fracture prevention: a claims data approach. Bone 110:170–176. https://doi.org/10.1016/j.bone.2018.02.002

    Article  PubMed  Google Scholar 

  36. Egan M, Jaglal S, Byrne K, Wells J, Stolee P (2008) Factors associated with a second hip fracture: a systematic review. Clin Rehabil 22:272–282. https://doi.org/10.1177/0269215507081573

    Article  PubMed  Google Scholar 

  37. de Klerk G (2017) Osteoporosis, identification and treatment in fracture patients. de Klerk G. Osteoporosis, identification and treatment in fracture patients: an essential part of fracture management in elderly patients. Rijksuniversiteit Groningen, Groningen, p 144

  38. Haentjens P, Autier P, Collins J et al (2003) Colles fracture, spine fracture, and subsequent risk of hip fracture in men and women. A meta-analysis. J Bone Joint Surg Am 85:1936–1943. https://doi.org/10.2106/00004623-200310000-00011

    Article  PubMed  Google Scholar 

  39. Zhao D, Cheng P, Zhu B (2016) Epilepsy and fracture risk: a meta-analysis. Int J Clin Exp Med 9:564–569

    CAS  Google Scholar 

  40. Perna S, Avanzato I, Nichetti M, D’Antona G, Negro M, Rondanelli M (2017) Association between dietary patterns of meat and fish consumption with bone mineral density or fracture risk: a systematic literature. Nutrients 9. https://doi.org/10.3390/nu9091029

  41. Wells GA, Cranney A, Peterson J, Boucher M, Shea B, Welch V, Coyle D, Tugwell P, Cochrane Musculoskeletal Group (2008) Alendronate for the primary and secondary prevention of osteoporotic fractures in postmenopausal women. Cochrane Database Syst Rev. https://doi.org/10.1002/14651858.CD001155.pub2

Download references

Availability of data and materials

Supporting data cannot be made available due to the privacy regulations of our hospital. Further information about the data and the privacy regulations of our hospital are available upon request by the corresponding author.

Author information

Authors and Affiliations

  1. Department of Trauma Surgery, Ziekenhuisgroep Twente, Zilvermeeuw 1, 7609 PP, Almelo, The Netherlands

    B. C. S. de Vries, J. H. Hegeman & W. Nijmeijer

  2. Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, The Netherlands

    J. H. Hegeman & C. Seifert

  3. Department of Information & Organization, Ziekenhuisgroep Twente, Almelo, The Netherlands

    J. Geerdink

  4. Health Technology and Services Research, Techmed Centre, University of Twente, Enschede, The Netherlands

    C. G. M. Groothuis-Oudshoorn

Authors
  1. B. C. S. de Vries
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. J. H. Hegeman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. W. Nijmeijer
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. J. Geerdink
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. C. Seifert
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. C. G. M. Groothuis-Oudshoorn
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to B. C. S. de Vries.

Ethics declarations

Conflict of interest

None.

Code availability

https://github.com/bcsdevries/Research-Major-Osteoporotic-Fracture-Risk-calculator

Additional information

Publisher’s note

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

Supplementary information

ESM 1

(DOCX 105 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

de Vries, B.C.S., Hegeman, J.H., Nijmeijer, W. et al. Comparing three machine learning approaches to design a risk assessment tool for future fractures: predicting a subsequent major osteoporotic fracture in fracture patients with osteopenia and osteoporosis. Osteoporos Int 32, 437–449 (2021). https://doi.org/10.1007/s00198-020-05735-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00198-020-05735-z

Keywords

Search

Navigation