Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Presently, there is a wide variety of classification methods and deep neural network approaches in bioinformatics. Deep neural networks have proven their effectiveness for classification tasks, and have outperformed classical methods, but they suffer from a lack of interpretability. Therefore, these innovative methods are not appropriate for decision support systems in healthcare. Indeed, to allow clinicians to make informed and well thought out decisions, the algorithm should provide the main pieces of information used to compute the predicted diagnosis and/or prognosis, as well as a confidence score for this prediction.

Authors

  • David Chardin
    Transporters in imaging and Radiotherapy in Oncology (TIRO), Direction de la Recherche Fondamentale (DRF), Institute des sciences du vivant Fréderic Joliot, Commissariat à l'Energie Atomique et aux énergies alternatives (CEA), Université Côte d'Azur (UCA), Nice, France.
  • Cyprien Gille
    Laboratoire d'Informatique, Signaux et Systèmes de Sophia Antipolis (I3S), Centre de Recherche Scientifique (CNRS), Université Côte d'Azur (UCA), Sophia Antipolis, France.
  • Thierry Pourcher
  • Olivier Humbert
    Department of Nuclear Medicine, Centre Georges-François Leclerc, Dijon, France.
  • Michel Barlaud