Login / Signup

Identifying Confounders Using Bayesian Networks and Estimating Treatment Effect in Prostate Cancer With Observational Data.

Melle SieswerdaShixuan XieRuby van RossumInigo BermejoGijs GeleijnseKatja K H AbenFelice N van ErningValery LemmensAndre DekkerXander Verbeek
Published in: JCO clinical cancer informatics (2023)
A blacklist in conjunction with structure learning can result in a causal BN that can be used for confounder identification. Treatment effect found here is close to the 5 percentage point found in the literature.
Keyphrases
  • prostate cancer
  • systematic review
  • radical prostatectomy
  • machine learning
  • cross sectional
  • deep learning
  • bioinformatics analysis