Healthcare-associated infections (HAIs) continue to exert a heavy toll on patient outcomes and healthcare system costs worldwide. Traditional surveillance methods, relying on manual chart review and administrative data, are limited by delays, under-reporting, and inconsistencies. The advent of artificial intelligence (AI) and the digital transformation of health records have opened new frontiers for infection prevention and control (IPC), enabling real-time monitoring, risk stratification, and predictive interventions. This chapter traces the evolution of HAI surveillance from early rule-based systems to current machine learning and deep learning applications, highlighting the shift from reactive detection to proactive risk prediction. Comparative studies demonstrate that AI-driven surveillance outperforms manual methods in sensitivity, timeliness, and operational efficiency. Nonetheless, significant barriers persist, including data integration challenges, high infrastructure costs, limited AI literacy among healthcare professionals, and regulatory and ethical concerns surrounding data privacy and algorithmic bias. Despite these hurdles, economic analyses suggest that AI surveillance can offer substantial long-term savings through reduced infection rates and optimized resource allocation. Adoption patterns vary by setting, with high-income hospitals pioneering full automation while lower-resource environments explore semi-automated and open-source models. Sustainability and scalability hinge on continuous model updates, interoperability standards, cloud-based infrastructures, and international collaboration. Looking ahead, priorities include multi-center validation trials, explainable AI development, integrated antimicrobial stewardship, and comprehensive cost-effectiveness evaluations. Ultimately, AI-driven surveillance stands poised to transform IPC practice, moving from retrospective identification to proactive prevention, and offering a promising pathway to enhance patient safety and healthcare quality globally.