Bagging and deep learning in optimal individualized treatment rules

Biometrics. 2019 Jun;75(2):674-684. doi: 10.1111/biom.12990. Epub 2019 Mar 29.

Abstract

An ENsemble Deep Learning Optimal Treatment (EndLot) approach is proposed for personalized medicine problems. The statistical framework of the proposed method is based on the outcome weighted learning (OWL) framework which transforms the optimal decision rule problem into a weighted classification problem. We further employ an ensemble of deep neural networks (DNNs) to learn the optimal decision rule. Utilizing the flexibility of DNNs and the stability of bootstrap aggregation, the proposed method achieves a considerable improvement over existing methods. An R package "ITRlearn" is developed to implement the proposed method. Numerical performance is demonstrated via simulation studies and a real data analysis of the Cancer Cell Line Encyclopedia data.

Keywords: Bootstrap aggregating; deep neural network; high-dimensional data; outcome weighted learning; personalized medicine.

MeSH terms

  • Cell Line, Tumor
  • Computer Simulation
  • Databases as Topic
  • Decision Support Systems, Clinical / statistics & numerical data*
  • Deep Learning / statistics & numerical data*
  • Humans
  • Neural Networks, Computer
  • Precision Medicine / statistics & numerical data*