DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network.

Journal: BMC medical research methodology
Published Date:

Abstract

BACKGROUND: Medical practitioners use survival models to explore and understand the relationships between patients' covariates (e.g. clinical and genetic features) and the effectiveness of various treatment options. Standard survival models like the linear Cox proportional hazards model require extensive feature engineering or prior medical knowledge to model treatment interaction at an individual level. While nonlinear survival methods, such as neural networks and survival forests, can inherently model these high-level interaction terms, they have yet to be shown as effective treatment recommender systems.

Authors

  • Jared L Katzman
    Department of Computer Science, Yale University, 51 Prospect Street, New Haven, 06511, CT, USA.
  • Uri Shaham
    Department of Statistics, Yale University, New Haven, CT 06511, USA.
  • Alexander Cloninger
    Applied Mathematics Program, Yale University, 51 Prospect Street, New Haven, 06511, CT, USA.
  • Jonathan Bates
    Yale School of Medicine, New Haven, CT VA Connecticut Healthcare System, West Haven, CT jonathan.bates@yale.edu.
  • Tingting Jiang
    Interdepartmental Program in Computational Biology and Bioinformatics, Yale University, New Haven, 06511, CT, USA.
  • Yuval Kluger
    Department of Pathology, Yale School of Medicine, New Haven, CT 06510, USA.