Policy Optimization for Personalized Interventions in Behavioral Health

Jackie Baek (), Justin J. Boutilier (), Vivek F. Farias (), Jónas Oddur Jónasson () and Erez Yoeli ()
Additional contact information
Jackie Baek: Stern School of Business, New York University, New York, New York 10012
Justin J. Boutilier: Telfer School of Management, University of Ottawa, Ottawa, Ontario K1N 9B9, Canada
Vivek F. Farias: Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts 02142
Jónas Oddur Jónasson: Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts 02142
Erez Yoeli: Sloan School of Management, Massachusetts Institute of Technology, Cambridge, Massachusetts 02142

Manufacturing & Service Operations Management, 2025, vol. 27, issue 3, 770-788

Abstract: Problem definition : Behavioral health interventions, delivered through digital platforms, have the potential to significantly improve health outcomes through education, motivation, reminders, and outreach. We study the problem of optimizing personalized interventions for patients to maximize a long-term outcome, in which interventions are costly and capacity constrained. We assume we have access to a historical data set collected from an initial pilot study. Methodology/results : We present a new approach for this problem that we dub DecompPI , which decomposes the state space for a system of patients to the individual level and then approximates one step of policy iteration. Implementing DecompPI simply consists of a prediction task using the data set, alleviating the need for online experimentation. DecompPI is a generic, model-free algorithm that can be used irrespective of the underlying patient behavior model. We derive theoretical guarantees on a simple, special case of the model that is representative of our problem setting. When the initial policy used to collect the data is randomized, we establish an approximation guarantee for DecompPI with respect to the improvement beyond a null policy that does not allocate interventions. We show that this guarantee is robust to estimation errors. We then conduct a rigorous empirical case study using real-world data from a mobile health platform for improving treatment adherence for tuberculosis. Using a validated simulation model, we demonstrate that DecompPI can provide the same efficacy as the status quo approach with approximately half the capacity of interventions. Managerial implications : DecompPI is simple and easy to implement for an organization aiming to improve long-term behavior through targeted interventions, and this paper demonstrates its strong performance both theoretically and empirically, particularly in resource-limited settings.

Keywords: health analytics; policy optimization; reinforcement learning; global health; behavioral health; tuberculosis (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/msom.2023.0548 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormsom:v:27:y:2025:i:3:p:770-788

Access Statistics for this article

More articles in Manufacturing & Service Operations Management from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().