"Big Data" in Rheumatology: Intelligent Data Modeling Improves the Quality of Imaging Data

Rheum Dis Clin North Am. 2018 May;44(2):307-315. doi: 10.1016/j.rdc.2018.01.007.


Analysis of imaging data in rheumatology is a challenge. Reliability of scores is an issue for several reasons. Signal-to-noise ratio of most imaging techniques is rather unfavorable (too little signal in relation to too much noise). Optimal use of all available data may help to increase credibility of imaging data, but knowledge of complicated statistical methodology and the help of skilled statisticians are required. Clinicians should appreciate the merits of sophisticated data modeling and liaise with statisticians to increase the quality of imaging results, as proper imaging studies in rheumatology imply more than a supersensitive imaging technique alone.

Keywords: Generalized estimating equations; Generalized linear mixed model; Imaging; Reliability; Statistical analysis; Variability.

Publication types

  • Review

MeSH terms

  • Big Data*
  • Diagnostic Imaging / standards*
  • Humans
  • Models, Statistical
  • Observer Variation
  • Reproducibility of Results
  • Rheumatic Diseases / diagnostic imaging*
  • Rheumatology / standards
  • Signal-To-Noise Ratio