Rapidly Personalizing Mobile Health Treatment Policies with Limited Data

by   Sabina Tomkins, et al.

In mobile health (mHealth), reinforcement learning algorithms that adapt to one's context without learning personalized policies might fail to distinguish between the needs of individuals. Yet the high amount of noise due to the in situ delivery of mHealth interventions can cripple the ability of an algorithm to learn when given access to only a single user's data, making personalization challenging. We present IntelligentPooling, which learns personalized policies via an adaptive, principled use of other users' data. We show that IntelligentPooling achieves an average of 26 state-of-the-art across all generative models. Additionally, we inspect the behavior of this approach in a live clinical trial, demonstrating its ability to learn from even a small group of users.


page 1

page 2

page 3

page 4


IntelligentPooling: Practical Thompson Sampling for mHealth

In mobile health (mHealth) smart devices deliver behavioral treatments r...

Personalization of Health Interventions using Cluster-Based Reinforcement Learning

Research has shown that personalization of health interventions can cont...

Personalized Policy Learning using Longitudinal Mobile Health Data

We address the personalized policy learning problem using longitudinal m...

Personalizing Intervention Probabilities By Pooling

In many mobile health interventions, treatments should only be delivered...

Design and Evaluation of Personalized Free Trials

Free trial promotions, where users are given a limited time to try the p...

On Using Chatbots to Promote Smoking Cessation Among Adolescents of Low Socioeconomic Status

Reducing youth tobacco use is critical for improving child health since ...

Streamlined Empirical Bayes Fitting of Linear Mixed Models in Mobile Health

To effect behavior change a successful algorithm must make high-quality ...