Opportunities and challenges of artificial intelligence in public health: a systematic review on technological efficacy, ethical dilemmas, and governance pathways.

Introduction: Artificial intelligence (AI) holds profound potential to reshape public health through enhanced disease prediction, diagnosis, and health management. However, this technological advancement is accompanied by significant ethical, social, and governance challenges. This systematic review aims to comprehensively examine the opportunities and challenges of AI in public health, focusing on its applications, associated dilemmas, and governance pathways. Methods: This review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A systematic search was performed across multiple databases (e.g., PubMed, Web of Science, Scopus, IEEE Xplore, CNKI, Wanfang) from January 2019 to January 2025. The PICOS framework guided the inclusion of studies addressing AI applications in public health functions, their outcomes, and ethical or governance aspects. From an initial 901 records, 136 studies were included in the qualitative synthesis after screening and quality assessment using tools such as the Newcastle-Ottawa Scale and CASP checklist. Results: The analysis reveals a dual effect of AI in public health. It significantly enhances efficiency in epidemic surveillance, emergency response, health communication, and clinical decision-support. However, these benefits are coupled with risks including algorithmic bias, data privacy concerns, the exacerbation of health inequities, and erosion of public trust. Public acceptance is context-dependent and influenced by factors like transparency, the digital divide, and task criticality. The evidence base exhibits a geographical imbalance, with a majority of studies from high-income countries, highlighting challenges in translating findings to low- and middle-income contexts. Effective governance requires a multi-layered, adaptive ecosystem that integrates technical standards, ethical oversight, community engagement, and global collaboration. Discussion: The integration of AI into public health represents a major socio-technical transformation beyond mere technical upgrade. Navigating its dual nature requires a balanced approach that embeds ethical foresight into design, promotes equitable and participatory governance, and addresses global evidence disparities. Future efforts should prioritize explainable AI, robust data governance models, transdisciplinary research, and forward-looking policy frameworks to steer AI development towards equitable and trustworthy public health outcomes.