In the recent food safety system, the Food Supply Chain (FSC) is a significant concern linked with food safety and quality control. Fraud, contamination, inadequate quality control, and a deficiency in transparency issues are increasing as complexity in supply networks (Abass, Eruaga, Itua, & Bature, 2024). These problems not only reflect consumer health but also bolster trust in food systems. As a result, through data-driven decision-making, traceability, and monitoring, traditional models like BlockChain (BC) and AI are enhancing the food quality and safety system (Gbashi & Njobeh, 2024). The problems of food safety and quality control are addressed using a variety of models and approaches. Machine Learning (ML), Deep Learning (DL), and AI models are categories using innovative algorithms (Adamashvili, Zhizhilashvili, & Tricase, 2024). AI has done some possibilities of data analysis, quality for automated evaluations, and predictive modeling, related to existing food safety. Patterns that indicate possible contamination, spoiling, or quality abnormalities are found because of its quick and accurate analysis of enormous volumes of data. In the food system, AI is improved by BC which ensures security by using accountability and traceability illustrious by its decentralization, transparency, and immutability (Ding et al., 2023). By providing reliable records across the supply chain, this system ensures visibility, discourages tampering, and enables quick reactions in the event of product recalls. Furthermore, by applying data analytics to the information recorded on the BC, the combination of BC and AI improves decision-making processes, which in turn promotes increased food distribution efficiency and safety. (Dedeoglu, Malik, Ramachandran, Pal, & Jurdak, 2023). Fig. 1 depicts the overall concept overview of FSC.

AI works on the data up to October 2023, optimizing data storage and analysis via Blockchain. Blockchain supports food safety management improvement and ensures the integrity and traceability of information obtained, and AI algorithms detect anomalies within IoT data (Bhatia & Albarrak, 2023). When brought together, all these assists in storage and transportation, pollution-free and spoilage-free (Khan, Ezati, & Rhim, 2023). In addition, BC-based AI-assisted quality control offers a unified platform for assessing compliance with safety standards, guaranteeing that only high-quality goods reach the consumer (Ayerdurai et al., 2024). Securely on BC, the results are analyzed using AI models on sensor data (Garaus & Treiblmaier, 2021). The facility effectively provides deterrence against tampering and establishes speedy recall by letting stakeholders access credible records throughout the supply chain. The merger of BC and AI substantially improves the overall efficiency of data management and analysis, which leads to greater insight and assists in FSC assurances (Zhang et al., 2020). Fig. 2 explains the years of publication.

The present review highlights the existing technology in BC and discusses its suggestions for food safety and quality control in FSC. The bulk of already published literature has dealt with the possible benefits of BC for the food industry, particularly for its application as protection against quality and food safety. This review aims to deliver an exhaustive summary of BC's impacts on FSC.

The review proposes a hybrid framework integrating BC, AI, and IoT to address critical challenges in food safety and quality control. This framework uniquely combines advanced technologies to enable monitoring, secure data storage, and predictive analytics across the FSC, tackling issues like traceability, transparency, and data-driven decision-making.

It provides a comprehensive evaluation of significant barriers, including scalability, computational overhead, and integration complexities, offering critical insights into the limitations of current technologies and paving the way for innovative solutions.

The proposed solution employs IoT sensors for real-time data collection, BC for secure and immutable storage, and AI for anomaly detection and quality assessment, augmented by optimization algorithms to enhance FSC logistics and energy efficiency. This streamlined approach delivers a transparent, efficient, and consumer-centric food safety system, ensuring enhanced trust, compliance, and operational excellence across the FSC.

This review is organized based on these sections: introduction, survey methodology, overview of domain-specific BC-based food safety and quality control, sources of biases, future research directions, and conclusions.

Each section is carefully designed to provide a detailed exploration of its respective topic, ensuring a logical flow of information and clarity of understanding. A comprehensive outline of this structure is illustrated in Fig. 3, which visually maps the organization and key focus areas of the review for better accessibility and comprehension.