Abstract:

As accelerating global aging and the burden of chronic diseases, the transition from traditional "passive medicine" to "active prevention", termed proactive health management, has emerged as a pivotal strategy for improving population health. In recent years, artificial intelligence (AI) has undergone rapid advancement in the medical field, offering critical technical support for early disease risk prediction, personalized assessment, and intervention. Despite existing evidence, the current progress and limitations of AI applications in proactive health service management in China remain unclear. Thus, this review systematically summarized evidence from the past decade across databases including PubMed, Web of Science, and the China National Knowledge Infrastructure (CNKI) on the practical implementation of AI in proactive health management. The findings indicate that AI technologies, including machine learning, deep learning, and large language models, have formed a relatively mature application framework for key domains such as health monitoring, risk assessment, personalized intervention, and integrated health management platform development. Nevertheless, challenges including data bias, privacy and security concerns, and a lack of algorithm validation continue to impede large-scale clinical translation and implementation. This review provides a crucial theoretical foundation for optimizing human–AI collaborative models and guiding the formulation of ethical and policy frameworks for the future of proactive health management in China.