Bagging and deep learning in optimal individualized treatment rules
Bagging and deep learning in optimal individualized treatment rules
复制标题
DOI：
10.1111/biom.12990
复制
发表时间：
2019-06-01
期刊：
影响因子：
1.9
通讯作者：
Zhu, Ruoqing
中科院分区：
文献类型：
--
作者：
Mi, Xinlei;Zou, Fei;Zhu, Ruoqing
针对个性化医疗问题，提出了一种集成深度学习优化治疗(EndLot)方法。该方法的统计框架基于结果加权学习(OWL)框架，将最优决策规则问题转化为加权分类问题。我们进一步使用深度神经网络(DNN)集成来学习最优决策规则。利用DNN的灵活性和Bootstrap聚集的稳定性，该方法在现有方法的基础上取得了较大的改进。开发了一个R包“ITRlearn”来实现该方法。通过对癌细胞系百科全书数据的模拟研究和实际数据分析，展示了数值性能。
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.