Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation

07/04/2018
by   Lu Wang, et al.
2

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 the 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/19/2022

Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes

Despite intense efforts in basic and clinical research, an individualize...
research
10/08/2018

Actor-Critic Deep Reinforcement Learning for Dynamic Multichannel Access

We consider the dynamic multichannel access problem, which can be formul...
research
09/23/2018

A Learning Framework for High Precision Industrial Assembly

Automatic assembly has broad applications in industries. Traditional ass...
research
05/23/2019

Exploiting Cognitive Structure for Adaptive Learning

Adaptive learning, also known as adaptive teaching, relies on learning p...
research
11/05/2021

Supervised Advantage Actor-Critic for Recommender Systems

Casting session-based or sequential recommendation as reinforcement lear...
research
02/03/2023

Two-Stage Constrained Actor-Critic for Short Video Recommendation

The wide popularity of short videos on social media poses new opportunit...
research
07/01/2020

A Novel RL-assisted Deep Learning Framework for Task-informative Signals Selection and Classification for Spontaneous BCIs

In this work, we formulate the problem of estimating and selecting task-...

Please sign up or login with your details

Forgot password? Click here to reset