Abstract: Efficient and sensitive detection technologies are crucial for the precise monitoring of food quality and safety. Nanozymes, owing to their superior catalytic activity, can significantly enhance detection signals, thereby effectively improving the sensitivity and accuracy of analytical methods. However, the complexity of food matrices and the multi-dimensional nature of spectral data may compromise the reliability of detection results. Machine learning algorithms possess robust data processing and analysis capabilities, enabling in-depth mining and interpretation of complex detection data, thus effectively improving the accuracy, sensitivity, and efficiency of analytical techniques. This article presents a comprehensive review of the applications of nanozyme-based sensing technologies integrated with machine learning in the field of food quality and safety detection. It particularly highlights the technical advantages of this integration in the detection of food hazards, quality, and authenticity. The combination of machine learning with nanozyme-based sensing technologies not only enhances the detection precision and efficiency but also provides solid technical support for advancing food safety detection toward intelligent and high-throughput systems.

Key words: machine learning; nanozyme-based sensing; food quality monitoring; food safety detection