Explainability and uncertainty: Two sides of the same coin for enhancing the interpretability of deep learning models in healthcare.

Journal: International journal of medical informatics
PMID: 39993336

Abstract

BACKGROUND: The increasing use of Deep Learning (DL) in healthcare has highlighted the critical need for improved transparency and interpretability. While Explainable Artificial Intelligence (XAI) methods provide insights into model predictions, reliability cannot be guaranteed by simply relying on explanations.

Authors

  • Massimo Salvi
  • Silvia Seoni
    Department of Electronics and Telecommunications, Biolab, Politecnico di Torino, Torino 10129, Italy.
  • Andrea Campagner
    IRCCS Istituto Ortopedico Galeazzi, Via Riccardo Galeazzi, 4, 20161, Milano, Italy. Electronic address: a.campagner@campus.unimib.it.
  • Arkadiusz Gertych
  • U Rajendra Acharya
    School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Darling Heights, Australia.
  • Filippo Molinari
    Department of Electronics and Telecommunications, Politecnico di Torino, Italy.
  • Federico Cabitza
    Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milano, Italy.

Keywords

External Resources

Popular Topics
Recent Journals