• Recurrent global health emergencies have intensified interest in the use of AI and ML across the vaccine life cycle. • AI and ML applications are already reshaping vaccinology. • Progress is limited by variable data quality, restricted external validation, and equity gaps. Recurrent global health emergencies have intensified interest in the application of artificial intelligence (AI) and machine learning (ML) to all stages of the vaccine life cycle. This systematic review synthesizes the available evidence and maps the current breakthroughs, persistent gaps, and future opportunities for AI- and ML-enabled vaccinology. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 guidelines, we searched PubMed, Scopus, Embase, ScienceDirect, Cochrane Library, and Google Scholar for peer-reviewed articles published from January 2010 to April 2025. Eligible studies reported any AI/ML application in vaccine discovery, development, manufacturing, supply chain management, or equitable deployment. Two reviewers independently screened the titles, abstracts, and full texts, extracted the data, and assessed the risk of bias using Joanna Briggs Institute tools. The findings were collated using qualitative synthesis. A total of 119 studies examined AI/ML applications across the vaccine lifecycle, including innovation and discovery, development, supply chain optimization, and equitable deployment. AI/ML approaches have improved epitope mapping, candidate screening, safety prediction, demand forecasting, and delivery efficiency, demonstrating their potential to accelerate vaccine development and enhance equitable access. AI/ML tools are transforming the vaccine lifecycle by accelerating epitope prediction, candidate screening, demand forecasting, and equitable allocation; however, their full potential is limited by data silos, algorithmic bias, and uneven validation across populations and settings. Recognizing their impact requires equity-focused strategies, cross-disciplinary collaboration, ethical governance, open data standards, and research on implementation, cost-effectiveness, and explainable AI to ensure equitable and trustworthy vaccine systems.
Okesanya et al. (Thu,) studied this question.