How AI-Supported Intelligent Systems Support Infection Prevention and Control Training in Healthcare: A Systematic Review of Educational Functions and Outcomes

Abstract Background: Artificial intelligence (AI) has increasingly been incorporated into infection prevention and control (IPC) education, primarily to support monitoring and feedback of observable behaviors. However, existing evidence has focused largely on short-term compliance outcomes, with limited synthesis of AI’s educational role in supporting sustained IPC competence. Objective: This systematic review examined how AI-supported intelligent systems have been designed and utilized to support IPC education and training, focusing on system characteristics, educational functions, and reported outcomes. Methods: A systematic literature search was conducted across PubMed/MEDLINE, Embase, Cochrane and CINAHL. Eighteen studies met the inclusion criteria. Findings were synthesized qualitatively according to AI system design, educational functions, and outcome domains. Methodological quality was appraised using the Mixed Methods Appraisal Tool (MMAT). Results: Most AI-supported IPC education focused on hand hygiene and relied on fully automated monitoring systems to capture behaviors and deliver performance feedback. Educational functions were predominantly limited to assessment, automated feedback, and reminders. Outcomes were mainly measured using compliance or performance metrics, while sustained behavior change and decision quality were rarely assessed. Conclusion: AI-supported IPC education has been effective in reinforcing short-term compliance, but current applications remain limited in supporting sustained competence over time. The findings of this review suggest that AI-supported intelligent systems may function as maintenance-oriented educational supports, extending learning beyond initial instruction through repeated practice and feedback. Future research should prioritize outcome measures that capture the durability of performance and decision-making processes to better align AI-assisted IPC education with the educational demands of clinical practice.