图 书 馆
基于递归神经网络的监督强化学习在动态治疗推荐中的应用Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation |
|
| 课程网址: | http://http://videolectures.net/kdd2018_wang_dynamic_treatment_re... |
| 主讲教师: | Lu Wang |
| 开课单位: | 华东师范大学 |
| 开课时间: | 2018-11-23 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Dynamic treatment recommendation systems based on large-scale electronic health records (EHRs) become a key to successfully improve practical clinical outcomes. Prior relevant studies recommend treatments either use supervised learning (e.g. matching the indicator signal which denotes doctor prescriptions), or reinforcement learning (e.g. maximizing evaluation signal which indicates cumulative reward from survival rates). However, none of these studies have considered to combine the benefits of supervised learning and reinforcement learning. In this paper, we propose Supervised Reinforcement Learning with Recurrent Neural Network (SRL-RNN), which fuses them into a synergistic learning framework. Specifically, SRL-RNN applies an off-policy actor-critic framework to handle complex relations among multiple medications, diseases and individual characteristics. The “actor’’ in the framework is adjusted by both the indicator signal and evaluation signal to ensure effective prescription and low mortality. RNN is further utilized to solve the Partially-Observed Markov Decision Process (POMDP) problem due to lack of fully observed states in real world applications. Experiments on the publicly real-world dataset, i.e., MIMIC-3, illustrate that our model can reduce the estimated mortality, while providing promising accuracy in matching doctors’ prescriptions. |
| 关 键 词: | 基于递归神经网络; 大规模电子健康记录; 监督强化学习; 在动态治疗推荐中的应用; SRL-RNN应用非政策行动 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2023-03-27：cyh |
| 最后编审: | 2023-03-27：cyh |
| 阅读次数: | 22 |