Artificial intelligence (AI) has been increasingly applied to address challenges in food packaging, including food waste, sustainability, and real-time quality assurance. However, existing studies are often confined to specific applications, with limited integration across different stages of the packaging life cycle and insufficient linkage between material performance, functionality, and system-level outcomes. This review systematically analyzes peer-reviewed studies retrieved from the Web of Science Core Collection (2021-2025), selected based on their relevance to AI applications in food packaging, including material performance, safety, and life cycle management. A life cycle-oriented framework is proposed, linking major AI paradigms (supervised, unsupervised, reinforcement, deep learning, and hybrid models) to six key domains: material design, production optimization, food quality prediction, safety assurance, smart labeling and traceability, and recycling. Within this framework, AI supports data-driven prediction, monitoring, and decision-making, whereas hybrid models improve robustness in complex, multifactor systems. Despite challenges related to data quality, model generalization, and regulatory acceptance, AI-driven packaging systems may support a transition from passive containment toward more adaptive and data-informed solutions that improve efficiency, sustainability, and consumer trust.
Huang et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: