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.
Similar content being viewed by others
Notes
Determined with the CKD-EPI formula
References
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
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
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
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
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
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
CBO Richtlijn Osteoporose en Fractuurpreventie-2011. https://www.volksgezondheidenzorg.info/bestanden/documenten/cbo-richtlijn-osteoporose-en-fractuurpreventie-2011. Accessed 21 Oct 2019
Weda M, Jansen ME, Vonk RAA (2017) Personalised medicine - Implementatie in de praktijk en data-infrastructuren. RIVM Briefrapport 2017–0006
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
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
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
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
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
DIS open data. https://www.opendisdata.nl/. Accessed 7 Feb 2020
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
R Core Team (2019) R: a language and environment for statistical computing. R Foundation for Statistical Computing, Vienna URL http://www.R-project.org/
Cox DR (1972) Regression models and life-tables. J R Stat Soc Ser B 34:187–220
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
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
Schoenfeld D (1982) Partial residuals for the proportional hazards regression model. Biometrika 69:239. https://doi.org/10.2307/2335876
Steyerberg EW (2019) Clinical prediction models. Springer International Publishing, Cham
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
Breiman L (2001) Random forest. Mach Learn 45:5–32. https://doi.org/10.1017/CBO9781107415324.004
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
Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. 3rd Int Conf Learn Represent ICLR 2015 - Conf Track Proc 1–15
Moradi R, Berangi R, Minaei B (2020) A survey of regularization strategies for deep models. Springer, Netherlands
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
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
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
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
Nissinen T (2019) Convolutional neural networks in osteoporotic fracture risk prediction using spine DXA images - Master’s thesis Computer Sciences, University of Eastern Finland
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
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
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
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
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
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
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
Zhao D, Cheng P, Zhu B (2016) Epilepsy and fracture risk: a meta-analysis. Int J Clin Exp Med 9:564–569
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
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
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
Corresponding author
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
About this article
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
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00198-020-05735-z