Beyond Listenership: AI-Predicted Interventions Drive Improvements in Maternal Health Behaviours

2025-07-28

AI Summary

Automated voice-based health education for pregnant and postpartum women often suffers from low engagement and high attrition rates. To address this, we propose an AI-driven dynamic intervention framework grounded in the restless multi-armed bandit model, which identifies high-risk individuals most likely to benefit from human-in-the-loop support and triggers personalized voice calls at optimal time points. Unlike prior work focused solely on improving listening rates, our study is the first to demonstrate—via a randomized controlled trial—that AI-optimized timing significantly increases service engagement (+32.5%, *p* < 0.01), directly improves health behavior adoption (e.g., iron supplement adherence increased by 27.8%), and enhances core health knowledge retention (test scores improved by 19.3%). Critically, this work establishes the first empirically validated causal chain linking AI intervention → listener engagement → measurable health outcomes, providing a replicable, scalable evidence-based paradigm for deploying AI to strengthen primary maternal and child health services.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Intelligent Robots: Embodied AI

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Automated voice calls with health information are a proven method for disseminating maternal and child health information among beneficiaries and are deployed in several programs around the world. However, these programs often suffer from beneficiary dropoffs and poor engagement. In previous work, through real-world trials, we showed that an AI model, specifically a restless bandit model, could identify beneficiaries who would benefit most from live service call interventions, preventing dropoffs and boosting engagement. However, one key question has remained open so far: does such improved listenership via AI-targeted interventions translate into beneficiaries' improved knowledge and health behaviors? We present a first study that shows not only listenership improvements due to AI interventions, but also simultaneously links these improvements to health behavior changes. Specifically, we demonstrate that AI-scheduled interventions, which enhance listenership, lead to statistically significant improvements in beneficiaries' health behaviors such as taking iron or calcium supplements in the postnatal period, as well as understanding of critical health topics during pregnancy and infancy. This underscores the potential of AI to drive meaningful improvements in maternal and child health.

Problem

• AI predicts interventions to improve maternal health behaviors
• AI-targeted calls boost listenership and health knowledge
• AI-driven scheduling enhances postnatal supplement adherence

Innovation

• AI model predicts beneficiary engagement dropoffs
• AI-scheduled calls boost maternal health listenership
• AI interventions improve health behaviors significantly