SynRL: Aligning Synthetic Clinical Trial Data with Human-preferred Clinical Endpoints Using Reinforcement Learning

TL;DR

SynRL employs reinforcement learning to generate synthetic clinical trial data that aligns with user-defined outcomes and endpoints, enhancing data quality while maintaining privacy, and offering a flexible framework adaptable to various data generators.

Contribution

This paper introduces SynRL, a novel reinforcement learning framework that customizes synthetic clinical data generation to meet specific clinical outcome requirements.

Findings

Improves quality of synthetic clinical trial data

Maintains low privacy risks

Applicable to multiple data generator types

Abstract

Each year, hundreds of clinical trials are conducted to evaluate new medical interventions, but sharing patient records from these trials with other institutions can be challenging due to privacy concerns and federal regulations. To help mitigate privacy concerns, researchers have proposed methods for generating synthetic patient data. However, existing approaches for generating synthetic clinical trial data disregard the usage requirements of these data, including maintaining specific properties of clinical outcomes, and only use post hoc assessments that are not coupled with the data generation process. In this paper, we propose SynRL which leverages reinforcement learning to improve the performance of patient data generators by customizing the generated data to meet the user-specified requirements for synthetic data outcomes and endpoints. Our method includes a data value critic function to evaluate the quality of the generated data and uses reinforcement learning to align the data generator with the users' needs based on the critic's feedback. We performed experiments on four clinical trial datasets and demonstrated the advantages of SynRL in improving the quality of the generated synthetic data while keeping the privacy risks low. We also show that SynRL can be utilized as a general framework that can customize data generation of multiple types of synthetic data generators. Our code is available at https://anonymous.4open.science/r/SynRL-DB0F/.