Article Text

PDF

Correspondence
Risk of vascular disease with gout: overadjustment of the statistical analyses?
  1. Caroline M van Durme1,2,
  2. Bart Spaetgens1,
  3. Annelies Boonen1,
  4. Frank de Vries3
  1. 1Department of Internal Medicine, Maastricht University Medical Centre+, Maastricht, The Netherlands
  2. 2Service de Rhumatologie, Centre hospitalier Universitaire de Liège, Belgium
  3. 3Department of Clinical Pharmacy & Toxicology, Maastricht University Medical Centre+, Maastricht, The Netherlands
  1. Correspondence to Dr Caroline M van Durme, Department of Internal Medicine/Rheumatology, Maastricht University Medical Centre, P. Debyelaan 25, Maastricht 6229 HX, The Netherlands; carolinevd{at}gmail.com

Statistics from Altmetric.com

An increase of 6% in the risk of vascular disease among men with gout (adj. HR 1.06 95% CI 1.01 to 1.12) and of 25% among women with gout (adj. HR 1.25 95%CI 1.15 to 1.35) was reported when analysing data of the world's largest primary care database, the UK Clinical Practice Research Datalink.1 However, the statistical analyses are likely to suffer from overadjustment, which probably have resulted in an imprecise relative risk with reduced statistical significance which often biases towards the null-hypothesis.2 Cox regression analyses adjusted for both comorbidity using the Charlson Comorbidity Index (CCI) and specific potential confounders, such as hypertension, hyperlipidaemia and chronic kidney disease. The CCI classifies various comorbid conditions which might alter the risk of mortality.3 As moderate and severe renal diseases are already taken into account in the CCI, they should not be used as a separate covariate (chronic kidney disease).

Overadjustment bias can be easily dealt with: the variables that are overadjusted for should be removed from the multivariate analyses. We would therefore be interested in the results from a multivariate analysis that is unlikely to suffer from overadjustment. Dealing correctly with comorbidities is especially important when assessing the cardiovascular risk in patients with gout, as comorbidities such as chronic kidney disease are known to be more prevalent in individuals with gout compared with healthy individuals.4

References

View Abstract

Footnotes

  • Competing interests None.

  • Provenance and peer review Not commissioned; internally peer reviewed.

Request permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Linked Articles