Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health

2026-04-07

AI Summary

This study addresses the challenge of sustaining personalized outreach to vulnerable populations in India’s maternal and child health programs, where scarce healthcare personnel limit effective engagement. To overcome this, the authors propose a decision-focused learning (DFL) approach grounded in the Restless Multi-Armed Bandit framework, which eschews the conventional two-stage “predict-then-optimize” paradigm by directly embedding resource allocation policies into the learning process for end-to-end optimization. Validated through a large-scale randomized controlled trial, the DFL strategy significantly improves long-term beneficiary engagement compared to standard care, reducing cumulative disengagement by 31% and effectively promoting sustained adherence to critical health behaviors, such as iron and calcium supplementation among new mothers.

Abstract

Maternal and child health is a critical concern around the world. In many global health programs disseminating preventive care and health information, limited healthcare worker resources prevent continuous, personalised engagement with vulnerable beneficiaries. In such scenarios, it becomes crucial to optimally schedule limited live-service resources to maximise long-term engagement. To address this fundamental challenge, the multi-year SAHELI project (2020-2025), in collaboration with partner NGO ARMMAN, leverages AI to allocate scarce resources in a maternal and child health program in India. The SAHELI system solves this sequential resource allocation problem using a Restless Multi-Armed Bandit (RMAB) framework. A key methodological innovation is the transition from a traditional Two-Stage "predict-then-optimize" approach to Decision-Focused Learning (DFL), which directly aligns the framework's learning method with the ultimate goal of maximizing beneficiary engagement. Empirical evaluation through large-scale randomized controlled trials demonstrates that the DFL policy reduced cumulative engagement drops by 31% relative to the current standard of care, significantly outperforming the Two-Stage model. Crucially, the studies also confirmed that this increased program engagement translates directly into statistically significant improvements in real-world health behaviors, notably the continued consumption of vital iron and calcium supplements by new mothers. Ultimately, the SAHELI project provides a scalable blueprint for applying sequential decision-making AI to optimize resource allocation in health programs.

Problem

• maternal and child health
• resource allocation
• restless multi-armed bandits
• healthcare engagement
• limited healthcare workers

Innovation

• Decision-Focused Learning
• Restless Multi-Armed Bandit
• Sequential Decision-Making
• Resource Allocation
• Maternal and Child Health