Use of artificial neural networks to predict anterior communicating artery aneurysm rupture: possible methodological considerations.

Journal: European radiology
Published Date:

Abstract

Use of algorithms to generate synthetic cases might result in a misrepresentation of the entire population. Training an artificial neural network with a mix of real and synthetic data might lead to non-realistic prediction precision.

Authors

  • Guido Adriaan de Jong
    Radboud University Medical Center, Department of Neurosurgery, Radboud University Medical Center, Geert Grooteplein-Zuid 30, Internal post number 633, 6525 GA, Nijmegen, The Netherlands.
  • RenĂ© Aquarius
    Radboud University Medical Center, Department of Neurosurgery, Radboud University Medical Center, Geert Grooteplein-Zuid 30, Internal post number 633, 6525 GA, Nijmegen, The Netherlands. rene.aquarius@radboudumc.nl.