Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks.

Journal: PloS one
PMID: 35862421

Abstract

BACKGROUND: Approaching epidemiological data with flexible machine learning algorithms is of great value for understanding disease-specific association patterns. However, it can be difficult to correctly extract and understand those patterns due to the lack of model interpretability.

Authors

  • Ann-Kristin Becker
    Institute of Bioinformatics, University Medicine Greifswald, Greifswald, Germany.
  • Till Ittermann
    Institute for Community Medicine, SHIP/Clinical-Epidemiological Research, University Medicine Greifswald, Greifswald, Germany.
  • Markus Dörr
    DZHK (German Centre for Cardiovascular Research), Partner Site Greifswald, Greifswald, Germany.
  • Stephan B Felix
    Department of Internal Medicine, Cardiology, University Medicine Greifswald, Greifswald, Germany.
  • Matthias Nauck
    DZHK (German Centre for Cardiovascular Research), Partner Site Greifswald, Greifswald, Germany.
  • Alexander Teumer
    Institute for Community Medicine, SHIP/Clinical-Epidemiological Research, University Medicine Greifswald, Greifswald, Germany.
  • Uwe Völker
    DZHK (German Centre for Cardiovascular Research), Partner Site Greifswald, Greifswald, Germany.
  • Henry Völzke
    Institute for Community Medicine, University Medicine Greifswald, Greifswald, Germany.
  • Lars Kaderali
  • Neetika Nath

Keywords

External Resources

Popular Topics
Recent Journals