Fusing Data Mining, Machine Learning and Traditional Statistics to Detect Biomarkers Associated with Depression.

Journal: PloS one
PMID: 26848571

Abstract

BACKGROUND: Atheoretical large-scale data mining techniques using machine learning algorithms have promise in the analysis of large epidemiological datasets. This study illustrates the use of a hybrid methodology for variable selection that took account of missing data and complex survey design to identify key biomarkers associated with depression from a large epidemiological study.

Authors

  • Joanna F Dipnall
    IMPACT Strategic Research Centre, School of Medicine, Deakin University, Geelong, VIC, Australia.
  • Julie A Pasco
    IMPACT Strategic Research Centre, School of Medicine, Deakin University, Geelong, VIC, Australia.
  • Michael Berk
    IMPACT Strategic Research Centre, School of Medicine, Deakin University, Geelong, VIC, Australia.
  • Lana J Williams
    IMPACT Strategic Research Centre, School of Medicine, Deakin University, Geelong, VIC, Australia.
  • Seetal Dodd
    IMPACT Strategic Research Centre, School of Medicine, Deakin University, Geelong, VIC, Australia.
  • Felice N Jacka
    IMPACT Strategic Research Centre, School of Medicine, Deakin University, Geelong, VIC, Australia.
  • Denny Meyer
    Department of Statistics, Data Science and Epidemiology, Swinburne University of Technology, Melbourne, Victoria, Australia.

Keywords

External Resources

Popular Topics
Recent Journals