Portable devices and machine learning-assisted lateral flow assay for food safety analysis: Developments and perspectives

Background

The ingestion of food contaminated with biological hazards like bacteria, chemical hazards and environmental pollutants can cause major public health issues. The lateral flow assay (LFA) technology facilitates the visual acquisition of qualitative results and has been extensively utilized, especially in resource-constrained settings. It is imperative to accurately quantify analyte concentrations and ensure the reliability of test results for point-of-care testing (POCT) applications. Therefore, there is a pressing requirement for suitable diagnostic platform that can quantitatively evaluate LFA outcomes.

Scope and approach

This review provides a comprehensive analysis of measurement principles and development trends of common signals in LFA. It offers an in-depth discussion on the adaptability and advantages of LFA to various portable, rapid, miniaturized, and smartphone-integrated devices. Furthermore, the integration of machine learning with intelligent LFA platform devices has been specifically explored to enhance intelligence and efficiency of the theoretical framework for food safety management. In addition to emphasizing the benefits of intelligent platform-assisted LFA in food safety monitoring, we also provide a critical analysis of the current challenges and future directions in this field.

Key findings and conclusions

The intelligent platform, integrated with machine learning-assisted LFA, can effectively enhance the detection sensitivity and stability of LFA, enabling rapid, quantitative and sensitive detection of foodborne hazards, addressing significant challenges in rapid food safety monitoring and its practical applications. It is expected that this technology will continue to evolve and become an essential instrument in the global initiative to combat food safety concerns.