Exploring machine learning strategies for predicting cardiovascular disease risk factors from multi-omic data.

Journal: BMC medical informatics and decision making
PMID: 38698395

Abstract

BACKGROUND: Machine learning (ML) classifiers are increasingly used for predicting cardiovascular disease (CVD) and related risk factors using omics data, although these outcomes often exhibit categorical nature and class imbalances. However, little is known about which ML classifier, omics data, or upstream dimension reduction strategy has the strongest influence on prediction quality in such settings. Our study aimed to illustrate and compare different machine learning strategies to predict CVD risk factors under different scenarios.

Authors

  • Gabin Drouard
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland. gabin.drouard@helsinki.fi.
  • Juha Mykkänen
    Centre for Population Health Research, University of Turku and Turku University Hospital, Turku, Finland.
  • Jarkko Heiskanen
    Centre for Population Health Research, University of Turku and Turku University Hospital, Turku, Finland.
  • Joona Pohjonen
    Research Program in Systems Oncology, University of Helsinki, Helsinki, Finland.
  • Saku Ruohonen
    Orion Corporation, Turku, Finland.
  • Katja Pahkala
    Centre for Population Health Research, University of Turku and Turku University Hospital, Turku, Finland.
  • Terho Lehtimäki
    a Faculty of Medicine and Health Technology , Tampere University , Tampere , Finland.
  • Xiaoling Wang
    Shanghai Key Lab of Trustworthy Computing, East China Normal University, Shanghai, China.
  • Miina Ollikainen
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland.
  • Samuli Ripatti
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland.
  • Matti Pirinen
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland.
  • Olli Raitakari
    Centre for Population Health Research, University of Turku and Turku University Hospital, Turku, Finland.
  • Jaakko Kaprio
    Institute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland. jaakko.kaprio@helsinki.fi.

Keywords

External Resources

Popular Topics
Recent Journals