Will machine learning applied to neuroimaging in bipolar disorder help the clinician? A critical review and methodological suggestions.

Journal: Bipolar disorders
PMID:

Abstract

OBJECTIVES: The existence of anatomofunctional brain abnormalities in bipolar disorder (BD) is now well established by magnetic resonance imaging (MRI) studies. To create diagnostic and prognostic tools, as well as identifying biologically valid subtypes of BD, research has recently turned towards the use of machine learning (ML) techniques. We assessed both supervised ML and unsupervised ML studies in BD to evaluate their robustness, reproducibility and the potential need for improvement.

Authors

  • Laurie-Anne Claude
    APHP, Mondor University Hospitals, DMU IMPACT Psychiatry and Addictology, UPEC, Créteil, France.
  • Josselin Houenou
    APHP, Mondor University Hospitals, DMU IMPACT Psychiatry and Addictology, UPEC, Créteil, France.
  • Edouard Duchesnay
    NeuroSpin, CEA, Paris-Saclay, Gif-sur-Yvette, France.
  • Pauline Favre
    Neurospin, CEA, Université Paris-Saclay, Gif-sur-Yvette, France.