Deep doubly robust outcome weighted learning

被引:0
|
作者
Xiaotong Jiang
Xin Zhou
Michael R. Kosorok
机构
[1] University of North Carolina at Chapel Hill,Department of Biostatistics
[2] Yale University,Department of Biostatistics
来源
Machine Learning | 2024年 / 113卷
关键词
Precision medicine; Individualized treatment rule; Deep learning; Double robustness;
D O I
暂无
中图分类号
学科分类号
摘要
Precision medicine is a framework that adapts treatment strategies to a patient’s individual characteristics and provides helpful clinical decision support. Existing research has been extended to various situations but high-dimensional data have not yet been fully incorporated into the paradigm. We propose a new precision medicine approach called deep doubly robust outcome weighted learning (DDROWL) that can handle big and complex data. This is a machine learning tool that directly estimates the optimal decision rule and achieves the best of three worlds: deep learning, double robustness, and residual weighted learning. Two architectures have been implemented in the proposed method, a fully-connected feedforward neural network and the Deep Kernel Learning model, a Gaussian process with deep learning-filtered inputs. We compare and discuss the performance and limitation of different methods through a range of simulations. Using longitudinal and brain imaging data from patients with Alzheimer’s disease, we demonstrate the application of the proposed method in real-world clinical practice. With the implementation of deep learning, the proposed method can expand the influence of precision medicine to high-dimensional abundant data with greater flexibility and computational power.
引用
收藏
页码:815 / 842
页数:27
相关论文
共 50 条
  • [21] Robust Tracking with Weighted Online Structured Learning
    Yao, Rui
    Shi, Qinfeng
    Shen, Chunhua
    Zhang, Yanning
    van den Hengel, Anton
    COMPUTER VISION - ECCV 2012, PT III, 2012, 7574 : 158 - 172
  • [22] Weighted and robust incremental method for subspace learning
    Skocaj, D
    Leonardis, A
    NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, 2003, : 1494 - 1501
  • [23] Learning to Reweight Examples for Robust Deep Learning
    Ren, Mengye
    Zeng, Wenyuan
    Yang, Bin
    Urtasun, Raquel
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [24] Doubly robust estimation of multivariate fractional outcome means with multivalued treatments
    Negi, Akanksha
    Jeffrey, Wooldridge M.
    ECONOMETRIC REVIEWS, 2024, 43 (2-4) : 175 - 196
  • [25] Doubly Robust Augmented Transfer for Meta-Reinforcement Learning
    Jiang, Yuankun
    Kan, Nuowen
    Li, Chenglin
    Dai, Wenrui
    Zou, Junni
    Xiong, Hongkai
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [26] Doubly robust learning for estimating individualized treatment with censored data
    Zhao, Y. Q.
    Zeng, D.
    Laber, E. B.
    Song, R.
    Yuan, M.
    Kosorok, M. R.
    BIOMETRIKA, 2015, 102 (01) : 151 - 168
  • [27] On Doubly Robust Inference for Double Machine Learning in Semiparametric Regression
    Dukes, Oliver
    Vansteelandt, Stijn
    Whitney, David
    JOURNAL OF MACHINE LEARNING RESEARCH, 2024, 25 : 1 - 46
  • [28] Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random
    Wang, Xiaojie
    Zhang, Rui
    Sun, Yu
    Qi, Jianzhong
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [29] Outcome weighted ψ-learning for individualized treatment rules
    Liu, Mingyang
    Shen, Xiaotong
    Pan, Wei
    STAT, 2021, 10 (01):
  • [30] A Doubly Weighted Approach for Appearance-Based Subspace Learning Methods
    Lu, Jiwen
    Tan, Yap-Peng
    IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, 2010, 5 (01) : 71 - 81