AI-Driven Energy-Efficient mHealth Applications for Chronic Disease Management: A Review of Optimization Techniques

Abstract

Mobile health (mHealth) applications provide real-time monitoring, offering valuable support in chronic disease management; however, their operation significantly drains battery life, making long-term use challenging. AI-driven techniques present promising solutions for optimizing energy consumption while maintaining functionality. This study systematically reviews AI-powered approaches for energy-efficient mHealth applications, exploring methods that enhance energy efficiency without compromising monitoring accuracy. A systematic review of AI-driven optimization techniques in mHealth, focusing on energy-saving characteristics of adaptive sampling and task scheduling, was conducted, analyzing 30 studies from 2016 to 2024. The findings reveal that task scheduling achieved energy savings of up to 40%, extending battery life by several hours, while adaptive sampling contributed 25-30% energy savings. Federated learning minimized data transmission, achieving energy savings of up to 25%, while predictive behavior modeling further optimized energy consumption by adjusting resource use based on user interactions. The results highlight that AI-driven techniques significantly reduce energy consumption in mHealth applications, making long-term monitoring more feasible without frequent recharging. Beyond chronic disease management, these techniques hold potential applications in general health monitoring, preventive care, and wellness tracking. Future research should explore advanced machine learning models and energy-harvesting technologies to enhance sustainability in mHealth applications.