Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes

In this paper, we propose a privacy-preserving reinforcement learning framework for a patient-centric dynamic treatment regime, which we refer to as Preyer. Using Preyer, a patient-centric treatment strategy can be made spontaneously while preserving the privacy of the patient's current health...

Full description

Saved in:

Bibliographic Details
Main Authors:	LIU, Ximeng, DENG, Robert H., CHOO, Kim-Kwang Raymond, YANG, Yang
Format:	text
Language:	English
Published:	Institutional Knowledge at Singapore Management University 2019
Subjects:	Cryptography Diseases Dynamic Treatment Regime Experience Replay Patient-Centric Privacy Privacy-Preserving Protocols Q-learning Reinforcement learning Reinforcement Learning Cloud computing Computational modeling Health Information Technology Information Security
Online Access:	https://ink.library.smu.edu.sg/sis_research/5073
Tags:	Add Tag No Tags, Be the first to tag this record!
Institution:	Singapore Management University
Language:	English

id	sg-smu-ink.sis_research-6076
record_format	dspace
spelling	sg-smu-ink.sis_research-60762020-03-12T06:54:03Z Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes LIU, Ximeng DENG, Robert H. CHOO, Kim-Kwang Raymond YANG, Yang In this paper, we propose a privacy-preserving reinforcement learning framework for a patient-centric dynamic treatment regime, which we refer to as Preyer. Using Preyer, a patient-centric treatment strategy can be made spontaneously while preserving the privacy of the patient's current health state and the treatment decision. Specifically, we first design a new storage and computation method to support noninteger processing for multiple encrypted domains. A new secure plaintext length control protocol is also proposed to avoid plaintext overflow after executing secure computation repeatedly. Moreover, we design a new privacy-preserving reinforcement learning framework with experience replay to build the model for secure dynamic treatment policymaking. Furthermore, we prove that Preyer facilitates patient dynamic treatment policymaking without leaking sensitive information to unauthorized parties. We also demonstrate the utility and efficiency of Preyer using simulations and analysis. 2019-01-01T08:00:00Z text https://ink.library.smu.edu.sg/sis_research/5073 info:doi/10.1109/TETC.2019.2896325 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Cryptography Diseases Dynamic Treatment Regime Experience Replay Patient-Centric Privacy Privacy-Preserving Protocols Q-learning Reinforcement learning Reinforcement Learning Cloud computing Computational modeling Health Information Technology Information Security
institution	Singapore Management University
building	SMU Libraries
continent	Asia
country	Singapore Singapore
content_provider	SMU Libraries
collection	InK@SMU
language	English
topic	Cryptography Diseases Dynamic Treatment Regime Experience Replay Patient-Centric Privacy Privacy-Preserving Protocols Q-learning Reinforcement learning Reinforcement Learning Cloud computing Computational modeling Health Information Technology Information Security
spellingShingle	Cryptography Diseases Dynamic Treatment Regime Experience Replay Patient-Centric Privacy Privacy-Preserving Protocols Q-learning Reinforcement learning Reinforcement Learning Cloud computing Computational modeling Health Information Technology Information Security LIU, Ximeng DENG, Robert H. CHOO, Kim-Kwang Raymond YANG, Yang Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
description	In this paper, we propose a privacy-preserving reinforcement learning framework for a patient-centric dynamic treatment regime, which we refer to as Preyer. Using Preyer, a patient-centric treatment strategy can be made spontaneously while preserving the privacy of the patient's current health state and the treatment decision. Specifically, we first design a new storage and computation method to support noninteger processing for multiple encrypted domains. A new secure plaintext length control protocol is also proposed to avoid plaintext overflow after executing secure computation repeatedly. Moreover, we design a new privacy-preserving reinforcement learning framework with experience replay to build the model for secure dynamic treatment policymaking. Furthermore, we prove that Preyer facilitates patient dynamic treatment policymaking without leaking sensitive information to unauthorized parties. We also demonstrate the utility and efficiency of Preyer using simulations and analysis.
format	text
author	LIU, Ximeng DENG, Robert H. CHOO, Kim-Kwang Raymond YANG, Yang
author_facet	LIU, Ximeng DENG, Robert H. CHOO, Kim-Kwang Raymond YANG, Yang
author_sort	LIU, Ximeng
title	Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
title_short	Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
title_full	Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
title_fullStr	Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
title_full_unstemmed	Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
title_sort	privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes
publisher	Institutional Knowledge at Singapore Management University
publishDate	2019
url	https://ink.library.smu.edu.sg/sis_research/5073
_version_	1770575206482444288

Privacy-preserving reinforcement learning design for patient-centric dynamic treatment regimes

Similar Items