Advertisement

European Journal of Nutrition

, Volume 57, Issue 5, pp 1969–1983 | Cite as

A comparison of principal component analysis, partial least-squares and reduced-rank regressions in the identification of dietary patterns associated with bone mass in ageing Australians

  • Yohannes Adama MelakuEmail author
  • Tiffany K. Gill
  • Anne W. Taylor
  • Robert Adams
  • Zumin Shi
Original Contribution

Abstract

Purpose

The relative advantages of dietary analysis methods, particularly in identifying dietary patterns associated with bone mass, have not been investigated. We evaluated principal component analysis (PCA), partial least-squares (PLS) and reduced-rank regressions (RRR) in determining dietary patterns associated with bone mass.

Methods

Data from 1182 study participants (45.9% males; aged 50 years and above) from the North West Adelaide Health Study (NWAHS) were used. Dietary data were collected using a food frequency questionnaire (FFQ). Dietary patterns were constructed using PCA, PLS and RRR and compared based on the performance to identify plausible patterns associated with bone mineral density (BMD) and content (BMC).

Results

PCA, PLS and RRR identified two, four and four dietary patterns, respectively. All methods identified similar patterns for the first two factors (factor 1, “prudent” and factor 2, “western” patterns). Three, one and none of the patterns derived by RRR, PLS and PCA were significantly associated with bone mass, respectively. The “prudent” and dairy (factor 3) patterns determined by RRR were positively and significantly associated with BMD and BMC. Vegetables and fruit pattern (factor 4) of PLS and RRR was negatively and significantly associated with BMD and BMC, respectively.

Conclusions

RRR was found to be more appropriate in identifying more (plausible) dietary patterns that are associated with bone mass than PCA and PLS. Nevertheless, the advantage of RRR over the other two methods (PCA and PLS) should be confirmed in future studies.

Keywords

Dietary analysis methods Principal component analysis Partial least-squares regression Reduced-rank regression Bone mass Ageing population 

Abbreviations

AIC

Akaike's information criterion

BMC

Bone mineral content

BMD

Bone mineral density

BMI

Body mass index

CATI

Computer assisted telephone interview

DQES

Dietary Questionnaire for Epidemiological Studies

DXA

Dual energy X-ray absorptiometry

EFA

Explanatory factor analyses

FFQ

Food frequency questionnaire

KMO

Kaiser–Mayer–Olkin

NHS

National Health Survey

NWAHS

North West Adelaide Health Study

PLS

Partial least-squares

PAL

Physical activity level

PCA

Principal component analysis

RRR

Reduced-rank regression

sTOFHLA

Short test of functional health literacy in adults

WHO

World Health Organization

Notes

Acknowledgements

We are thankful to NWAHS participants for their participation in the study. We are grateful for the support provided by Australian Government Research Training Program Scholarship. The NWAHS was funded by The University of Adelaide, the South Australian Department of Health and The Queen Elizabeth Hospital for which the authors are grateful.

Authors’ contribution

YAM, TKG, RA and ZS conceived the study. YAM conducted all analyses and wrote all drafts of the paper. ZS assisted with analysis and reviewed and provided comment on all drafts. TKG, AWT and RA reviewed and commented on all drafts. All authors read and approved the final manuscript.

Compliance with ethical standards

Conflict of interest

The authors have no financial or personal conflicts of interest to declare.

Supplementary material

394_2017_1478_MOESM1_ESM.docx (27 kb)
Supplementary material 1 (DOCX 27 kb)
394_2017_1478_MOESM2_ESM.docx (35 kb)
Supplementary material 2 (DOCX 34 kb)

References

  1. 1.
    Waijers PM, Feskens EJ, Ocke MC (2007) A critical review of predefined diet quality scores. Br J Nutr 97:219–231CrossRefPubMedGoogle Scholar
  2. 2.
    Arvaniti F, Panagiotakos DB (2008) Healthy indexes in public health practice and research: a review. Crit Rev Food Sci Nutr 48:317–327CrossRefPubMedGoogle Scholar
  3. 3.
    Hoffmann K, Schulze MB, Schienkiewitz A, Nothlings U, Boeing H (2004) Application of a new statistical method to derive dietary patterns in nutritional epidemiology. Am J Epidemiol 159:935–944CrossRefPubMedGoogle Scholar
  4. 4.
    Newby PK, Tucker KL (2004) Empirically derived eating patterns using factor or cluster analysis: a review. Nutr Rev 62:177–203CrossRefPubMedGoogle Scholar
  5. 5.
    Cattell RB (1973) Factor analysis. Greenwood, WestportGoogle Scholar
  6. 6.
    Devlin UM, McNulty BA, Nugent AP, Gibney MJ (2012) The use of cluster analysis to derive dietary patterns: methodological considerations, reproducibility, validity and the effect of energy mis-reporting. Proc Nutr Soc 71:599–609CrossRefPubMedGoogle Scholar
  7. 7.
    Schulze MB, Hoffmann K (2006) Methodological approaches to study dietary patterns in relation to risk of coronary heart disease and stroke. Br J Nutr 95:860–869CrossRefPubMedGoogle Scholar
  8. 8.
    DiBello JR, Kraft P, McGarvey ST, Goldberg R, Campos H et al (2008) Comparison of 3 methods for identifying dietary patterns associated with risk of disease. Am J Epidemiol 168:1433–1443CrossRefPubMedPubMedCentralGoogle Scholar
  9. 9.
    de Jonge EA, Kiefte-de Jong JC, de Groot LC, Voortman T, Schoufour JD et al (2015) Development of a Food Group-Based Diet Score and Its Association with Bone Mineral Density in the Elderly: The Rotterdam Study. Nutrients 7:6974–6990CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    van den Hooven EH, Ambrosini GL, Huang R-C, Mountain J, Straker L et al (2015) Identification of a dietary pattern prospectively associated with bone mass in Australian young adults. Am J Clin Nutr 102(5):1035–1043CrossRefPubMedGoogle Scholar
  11. 11.
    Melaku YA, Gill TK, Adams R, Shi Z (2016) Association between dietary patterns and low bone mineral density among adults aged 50 years and above: findings from the North West Adelaide Health Study (NWAHS). Br J Nutr 116:1437–1446CrossRefPubMedGoogle Scholar
  12. 12.
    Grant JF, Taylor AW, Ruffin RE, Wilson DH, Phillips PJ et al (2009) Cohort profile: the North West Adelaide Health Study (NWAHS). Int J Epidemiol 38:1479–1486CrossRefPubMedGoogle Scholar
  13. 13.
    Hodge A, Patterson AJ, Brown WJ, Ireland P, Giles G (2000) The Anti Cancer Council of Victoria FFQ: relative validity of nutrient intakes compared with weighed food records in young to middle-aged women in a study of iron supplementation. Aust N Z J Public Health 24:576–583CrossRefPubMedGoogle Scholar
  14. 14.
    Schoenaker DAJM, Dobson AJ, Soedamah-Muthu SS, Mishra GD (2013) Factor analysis is more appropriate to identify overall dietary patterns associated with diabetes when compared with treelet transform analysis. J Nutr 143:392–398CrossRefPubMedGoogle Scholar
  15. 15.
    National Heart Foundation, Australian Institute of Health and Welfare (1989) Risk factor prevalence study, Survey no 3. NHF, CanberraGoogle Scholar
  16. 16.
    World Health Organization (1995). Physical status: the use and interpretation of anthropometry. Report of a WHO Expert Committee. WHO Technical Report Series 854, GenevaGoogle Scholar
  17. 17.
    Australian Bureau of Statistics (2012/13) National nutrition and physical activity survey questionnaire. http://www.abs.gov.au/AUSSTATS/abs@.nsf/DetailsPage/4363.0.55.0012011-13?OpenDocument. Accessed 29 Jan 2016
  18. 18.
    D’Onise R, Shanahan EM, Gill T, Hill CL (2010) Does leisure time physical activity protect against shoulder pain at work? Occup Med 60:383–388CrossRefGoogle Scholar
  19. 19.
    Weiss BD, Mays MZ, Martz W, Castro KM, DeWalt DA et al (2005) Quick assessment of literacy in primary care: the newest vital sign. Ann Fam Med 3:514–522CrossRefPubMedPubMedCentralGoogle Scholar
  20. 20.
    Baker DW, Williams MV, Parker RM, Gazmararian JA, Nurss J (1999) Development of a brief test to measure functional health literacy. Patient Educ Couns 38:33–42CrossRefPubMedGoogle Scholar
  21. 21.
    Appleton SL, Seaborn CJ, Visvanathan R, Hill CL, Gill TK et al (2013) Diabetes and cardiovascular disease outcomes in the metabolically healthy obese phenotype: a cohort study. Diabetes Care 36:2388–2394CrossRefPubMedPubMedCentralGoogle Scholar
  22. 22.
    World Health Organization (1994) Assessment of fracture risk and its application to screening for postmenopausal osteoporosis. Report of a WHO Study Group. WHO Tech Rep Ser 843:1–129Google Scholar
  23. 23.
    Jesudason D, Clifton P (2011) The interaction between dietary protein and bone health. J Bone Miner Metab 29:1–14CrossRefPubMedGoogle Scholar
  24. 24.
    Rajatanavin R, Chailurkit L, Saetung S, Thakkinstian A, Nimitphong H (2013) The efficacy of calcium supplementation alone in elderly Thai women over a 2-year period: a randomized controlled trial. Osteoporosis Int 24:2871–2877CrossRefGoogle Scholar
  25. 25.
    Tucker KL, Hannan MT, Chen H, Cupples LA, Wilson PW et al (1999) Potassium, magnesium, and fruit and vegetable intakes are associated with greater bone mineral density in elderly men and women. Am J Clin Nutr 69:727–736CrossRefPubMedGoogle Scholar
  26. 26.
    Zhou W, Langsetmo L, Berger C, Poliquin S, Kreiger N et al (2013) Longitudinal changes in calcium and vitamin D intakes and relationship to bone mineral density in a prospective population-based study: the Canadian Multicentre Osteoporosis Study (CaMos). J Musculoskelet Neuronal Interact 13:470–479PubMedPubMedCentralGoogle Scholar
  27. 27.
    Ward KA, Prentice A, Kuh DL, Adams JE, Ambrosini GL (2016) Life course dietary patterns and bone health in later life in a British Birth Cohort Study. J Bone Miner Res 31:1167–1176CrossRefPubMedPubMedCentralGoogle Scholar
  28. 28.
    Ocke MC (2013) Evaluation of methodologies for assessing the overall diet: dietary quality scores and dietary pattern analysis. Proc Nutr Soc 72:191–199CrossRefPubMedGoogle Scholar
  29. 29.
    Rizzoli R (2014) Dairy products, yogurts, and bone health. Am J Clin Nutr 99:1256S–1262SCrossRefPubMedGoogle Scholar
  30. 30.
    Shin S, Joung H (2013) A dairy and fruit dietary pattern is associated with a reduced likelihood of osteoporosis in Korean postmenopausal women. The Br J Nutr 110:1926–1933CrossRefPubMedGoogle Scholar
  31. 31.
    de Jonge EA, Kiefte-de Jong JC, Hofman A, Uitterlinden AG, Kieboom BC et al (2016) Dietary patterns explaining differences in bone mineral density and hip structure in the elderly: the Rotterdam Study. Am J Clin Nutr 102(5):1035–1043Google Scholar
  32. 32.
    Kontogianni MD, Melistas L, Yannakoulia M, Malagaris I, Panagiotakos DB et al (2009) Association between dietary patterns and indices of bone mass in a sample of Mediterranean women. Nutrition 25:165–171CrossRefPubMedGoogle Scholar
  33. 33.
    Heaney RP (2007) Effects of protein on the calcium economy. Int Congr Ser 1297:191–197CrossRefGoogle Scholar
  34. 34.
    Hayhoe RP, Lentjes MA, Luben RN, Khaw KT, Welch AA (2015) Dietary magnesium and potassium intakes and circulating magnesium are associated with heel bone ultrasound attenuation and osteoporotic fracture risk in the EPIC-Norfolk cohort study. Am J Clin Nutr 102:376–384CrossRefPubMedGoogle Scholar
  35. 35.
    van Dam RM, Grievink L, Ocke MC, Feskens EJ (2003) Patterns of food consumption and risk factors for cardiovascular disease in the general Dutch population. Am J Clin Nutr 77:1156–1163CrossRefPubMedGoogle Scholar
  36. 36.
    Slattery ML (2010) Analysis of dietary patterns in epidemiological research. Appl Physiol Nutr Metab 35:207–210CrossRefPubMedGoogle Scholar
  37. 37.
    Willett W (2013) Nutritional epidemiology. Oxford University, New WorkGoogle Scholar
  38. 38.
    Pedone C, Napoli N, Pozzilli P, Rossi FF, Lauretani F et al (2011) Dietary pattern and bone density changes in elderly women: a longitudinal study. J Am Coll Nutr 30:149–154CrossRefPubMedPubMedCentralGoogle Scholar
  39. 39.
    de Franca NA, Camargo MB, Lazaretti-Castro M, Peters BS, Martini LA (2015) Dietary patterns and bone mineral density in Brazilian postmenopausal women with osteoporosis: a cross-sectional study. Eur J Nutr 70(1):85–90CrossRefGoogle Scholar
  40. 40.
    de Jonge EAL, Rivadeneira F, Erler NS, Hofman A, Uitterlinden AG et al (2016) Dietary patterns in an elderly population and their relation with bone mineral density: the Rotterdam Study. Eur J Nutr. doi: 10.1007/s00394-016-1297-7 CrossRefPubMedPubMedCentralGoogle Scholar
  41. 41.
    Jankovic N, Steppel MT, Kampman E, de Groot LC, Boshuizen H et al (2014) Stability of dietary patterns assessed with reduced rank regression; the Zutphen Elderly Study. Nutr J. doi: 10.1186/1475-2891-13-30 CrossRefPubMedPubMedCentralGoogle Scholar
  42. 42.
    Smith W, Mitchell P, Reay EM, Webb K, Harvey PWJ (1998) Validity and reproducibility of a self-administered food frequency questionnaire in older people. Aust N Z J Public Health 22:456–463CrossRefGoogle Scholar
  43. 43.
    National Cancer Institute. Dietary assessment primer, Effects of measurement error. https://dietassessmentprimer.cancer.gov/concepts/error/error-effects.html. Accessed 1 Feb 2016
  44. 44.
    Blackwell M, Honaker J, King G (2015) A unified approach to measurement error and missing data overview and applications. Sociol Methods Res. doi: 10.1177/0049124115585360 CrossRefGoogle Scholar
  45. 45.
    Brenner H, Loomis D (1994) Varied forms of bias due to nondifferential error in measuring exposure. Epidemiology 5:510–517PubMedGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany 2017

Authors and Affiliations

  1. 1.Population Research and Outcome Studies, Adelaide Medical SchoolThe University of Adelaide, SAHMRIAdelaideAustralia
  2. 2.Health Observatory, Discipline of MedicineThe Queen Elizabeth Hospital Campus, The University of AdelaideAdelaideAustralia

Personalised recommendations