Advertisement

Osteoporosis International

, Volume 29, Issue 6, pp 1437–1445 | Cite as

Predicting mortality and incident immobility in older Belgian men by characteristics related to sarcopenia and frailty

  • C. Kruse
  • S. Goemaere
  • S. De Buyser
  • B. Lapauw
  • P. Eiken
  • P. Vestergaard
Original Article

Abstract

Summary

There is an increasing awareness of sarcopenia in older people. We applied machine learning principles to predict mortality and incident immobility in older Belgian men through sarcopenia and frailty characteristics. Mortality could be predicted with good accuracy. Serum 25-hydroxyvitamin D and bone mineral density scores were the most important predictors.

Introduction

Machine learning principles were used to predict 5-year mortality and 3-year incident severe immobility in a population of older men by frailty and sarcopenia characteristics.

Methods

Using prospective data from 1997 on 264 older Belgian men (n = 152 predictors), 29 statistical models were developed and tuned on 75% of data points then validated on the remaining 25%. The model with the highest test area under the curve (AUC) was chosen as the best. From these, ranked predictor importance was extracted.

Results

Five-year mortality could be predicted with good accuracy (test AUC of .85 [.73; .97], sensitivity 78%, specificity 89% at a probability cut-off of 22.3%) using a Bayesian generalized linear model. Three-year incident severe immobility could be predicted with fair accuracy (test AUC .74 [.57; .91], sensitivity 67%, specificity 78% at a probability cut-off of 14.2%) using a multivariate adaptive regression splines model. Serum 25-hydroxyvitamin D levels and hip bone mineral density scores were the most important predictors of mortality, while biochemical androgen markers and Short-Form 36 Physical Domain questions were the most important predictors of immobility. Sarcopenia assessed by lean mass estimates was relevant to mortality prediction but not immobility prediction.

Conclusions

Using advanced statistical models and a machine learning approach 5-year mortality can be predicted with good accuracy using a Bayesian generalized linear model and 3-year incident severe immobility with fair accuracy using a multivariate adaptive regression splines model.

Keywords

Sarcopenia Osteoporosis Machine learning Big data Prediction 

Notes

Funding

This work was supported by the Obel Family Foundation of Aalborg, Denmark, which is funding the 3-year PhD fellowship of the corresponding author in full. The work was also supported by the Department of Clinical Medicine of Aalborg University, Denmark, which co-funds the activities inherent in the PhD fellowship of the corresponding author. Grant numbers are not maintained in Denmark.

Compliance with ethical standards

Conflicts of interest

CK has received travel grants from Eli Lilly, Otsuka Pharmaceutical and is a speaker for Novartis and Otsuka Pharmaceutical. PE is an advisory board member with Amgen, MSD, and Eli Lilly and at the speaker’s bureau with Amgen and Eli Lilly, stocks from Novo Nordisk A/S. PV has received unrestricted grants from MSD and Servier, and travel grants from Amgen, Eli Lilly, Novartis, Sanofi-Aventis, and Servier.

Supplementary material

198_2018_4467_MOESM1_ESM.docx (18 kb)
ESM 1 (DOCX 17 kb)
198_2018_4467_MOESM2_ESM.docx (19 kb)
ESM 2 (DOCX 18 kb)
198_2018_4467_MOESM3_ESM.docx (18 kb)
ESM 3 (DOCX 18 kb)

References

  1. 1.
    Fried LP, Tangen CM, Walston J, Newman AB, Hirsch C, Gottdiener J, Seeman T, Tracy R, Kop WJ, Burke G, McBurnie MA (2001) Frailty in older adults: evidence for a phenotype. J Gerontol A Biol Sci Med Sci 56(3):M146–M156CrossRefPubMedGoogle Scholar
  2. 2.
    Cruz-jentoft AJ, Baeyens JP, Bauer JM et al (2010) Sarcopenia: European consensus on definition and diagnosis: report of the European working group on sarcopenia in older people. Age Ageing 39(4):412–423CrossRefPubMedPubMedCentralGoogle Scholar
  3. 3.
    Patel HP, White MC, Westbury L, Syddall HE, Stephens PJ, Clough GF, Cooper C, Sayer AA (2015) Skeletal muscle morphology in sarcopenia defined using the EWGSOP criteria: findings from the Hertfordshire Sarcopenia Study (HSS). BMC Geriatr 15:171CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Bianchi L, Ferrucci L, Cherubini A, Maggio M, Bandinelli S, Savino E, Brombo G, Zuliani G, Guralnik JM, Landi F, Volpato S (2016) The predictive value of the EWGSOP definition of sarcopenia: results from the InCHIANTI study. J Gerontol A Biol Sci Med Sci 71(2):259–264CrossRefPubMedGoogle Scholar
  5. 5.
    De Buyser SL, Petrovic M, Taes YE, et al (2016) Validation of the FNIH sarcopenia criteria and SOF frailty index as predictors of long-term mortality in ambulatory older men. Age AgeingGoogle Scholar
  6. 6.
    Cawthon PM, Blackwell TL, Cauley J, Kado DM, Barrett-Connor E, Lee CG, Hoffman AR, Nevitt M, Stefanick ML, Lane NE, Ensrud KE, Cummings SR, Orwoll ES (2015) Evaluation of the usefulness of consensus definitions of sarcopenia in older men: results from the observational osteoporotic fractures in men cohort study. J Am Geriatr Soc 63(11):2247–2259CrossRefPubMedPubMedCentralGoogle Scholar
  7. 7.
    Gill TM, Allore HG, Hardy SE, Guo Z (2006) The dynamic nature of mobility disability in older persons. J Am Geriatr Soc 54(2):248–254CrossRefPubMedGoogle Scholar
  8. 8.
    Vanbillemont G, Bogaert V, De bacquer D et al (2009) Polymorphisms of the SHBG gene contribute to the interindividual variation of sex steroid hormone blood levels in young, middle-aged and elderly men. Clin Endocrinol 70(2):303–310CrossRefGoogle Scholar
  9. 9.
    Lapauw B, Goemaere S, Crabbe P, Kaufman JM, Ruige JB (2007) Is the effect of testosterone on body composition modulated by the androgen receptor gene CAG repeat polymorphism in elderly men? Eur J Endocrinol 156(3):395–401CrossRefPubMedGoogle Scholar
  10. 10.
    Lapauw B, Goemaere S, Zmierczak H, van Pottelbergh I, Mahmoud A, Taes Y, de Bacquer D, Vansteelandt S, Kaufman JM (2008) The decline of serum testosterone levels in community-dwelling men over 70 years of age: descriptive data and predictors of longitudinal changes. Eur J Endocrinol 159(4):459–468CrossRefPubMedGoogle Scholar
  11. 11.
    Van den Saffele JK, Goemaere S, De Bacquer D, Kaufman JM (1999) Serum leptin levels in healthy ageing men: are decreased serum testosterone and increased adiposity in elderly men the consequence of leptin deficiency? Clin Endocrinol 51(1):81–88CrossRefGoogle Scholar
  12. 12.
    Podsiadlo D, Richardson S (1991) The timed “Up & Go”: a test of basic functional mobility for frail elderly persons. J Am Geriatr Soc 39(2):142–148CrossRefPubMedGoogle Scholar
  13. 13.
    Linn MW, Linn BS (1982) The rapid disability rating scale-2. J Am Geriatr Soc 30(6):378–382CrossRefPubMedGoogle Scholar
  14. 14.
    Ware JE, Sherbourne CD (1992) The MOS 36-item short-form health survey (SF-36). I Conceptual framework and item selection. Med Care 30(6):473–483CrossRefPubMedGoogle Scholar
  15. 15.
    Kuhn M (2008) Building Predictive Models in R Using the caret Package. J Statist Softw 28(5):1–26Google Scholar
  16. 16.
    Youden WJ (1950) Index for rating diagnostic tests. Cancer 3(1):32–35CrossRefPubMedGoogle Scholar
  17. 17.
    Elith J, Leathwick JR, Hastie T (2008) A working guide to boosted regression trees. J Anim Ecol 77(4):802–813CrossRefPubMedGoogle Scholar

Copyright information

© International Osteoporosis Foundation and National Osteoporosis Foundation 2018

Authors and Affiliations

  1. 1.Steno Diabetes Center North Jutland (SDCN)AalborgDenmark
  2. 2.Department of Clinical MedicineAalborg University HospitalAalborgDenmark
  3. 3.Department of EndocrinologyAalborg University HospitalAalborgDenmark
  4. 4.Unit for Osteoporosis and Metabolic Bone Diseases, Department of EndocrinologyGhent University HospitalGhentBelgium
  5. 5.Department of GeriatricsGhent University HospitalGhentBelgium
  6. 6.Department of Cardiology, Nephrology, and EndocrinologyNordsjaellands HospitalHilleroedDenmark
  7. 7.Faculty of Health and Medical SciencesUniversity of CopenhagenCopenhagenDenmark

Personalised recommendations