Synthetic Data Generator for Adaptive Interventions in Global Health

TL;DR

HealthSyn is an open-source synthetic data generator designed to simulate user behavior in mobile health interventions, enabling testing and validation of reinforcement learning algorithms in realistic, customizable environments.

Contribution

The paper introduces HealthSyn, a novel synthetic data generator that models adaptive user behaviors for mobile health interventions using Markov processes and real-world data schemas.

Findings

Generated data reflects real-world user behaviors.

Supports testing of reinforcement learning algorithms.

Facilitates development of adaptive health interventions.

Abstract

Artificial Intelligence and digital health have the potential to transform global health. However, having access to representative data to test and validate algorithms in realistic production environments is essential. We introduce HealthSyn, an open-source synthetic data generator of user behavior for testing reinforcement learning algorithms in the context of mobile health interventions. The generator utilizes Markov processes to generate diverse user actions, with individual user behavioral patterns that can change in reaction to personalized interventions (i.e., reminders, recommendations, and incentives). These actions are translated into actual logs using an ML-purposed data schema specific to the mobile health application functionality included with HealthKit, and open-source SDK. The logs can be fed to pipelines to obtain user metrics. The generated data, which is based on real-world behaviors and simulation techniques, can be used to develop, test, and evaluate, both ML algorithms in research and end-to-end operational RL-based intervention delivery frameworks.