Artificial Intelligence – Enabled Integration of Physical Fitness Monitoring and Public Fitness Promotion: Mechanisms, Opportunities, and Governance Challenges

Abstract

As public health governance shifts from a disease-treatment paradigm toward health promotion and risk prevention, physical health monitoring has become a foundational component of population health management. In practice, however, monitoring systems remain constrained by a “monitoring-heavy, translation-light” dilemma, in which monitoring outputs fail to translate effectively into risk assessment and intervention, resulting in a structural break in the monitoring–assessment–intervention chain. Using a mechanisms–opportunities–governance challenges analytical framework, this paper synthesizes how artificial intelligence (AI) enables the integration of physical health monitoring with public health promotion and delineates the key conditions shaping its effectiveness. We argue that AI facilitates integration through multi-source health data integration and population profiling, population-level risk identification and prediction, and an intelligent feedback loop linking continuous monitoring, stratified intervention, outcome evaluation, and iterative adjustment. These mechanisms support a shift from periodic, static monitoring to stratified and dynamic population-level health promotion. At the same time, AI creates opportunities to enhance governance responsiveness, optimize public resource allocation, and strengthen evidence generation for policy design and evaluation, while also introducing governance challenges related to data privacy and ethics, algorithmic bias, health inequities, and accountability. We conclude that AI should be positioned as a tool and infrastructure within public health governance rather than an autonomous decision-maker, and that its real-world impact ultimately depends on institutional design, data governance, accountability, and human–AI collaboration.