Determining the threshold levels of food allergens that trigger reactions is an ongoing challenge for the food industry. While conventional allergen detection methods such as enzyme-linked immunosorbent assays (ELISA), DNA-PCR, and others are capable of detecting and quantifying the main allergens, new technologies are offering potential for non-destructive methods with improved turn-around times and reliability.
Emerging methodologies that marry sensor technologies with machine learning algorithms offer promising avenues for enhanced detection and quantification capabilities. These innovative approaches could revolutionise allergen management in food processing and manufacturing.
A recently published review on the magnitude and impact of food allergens considers the importance of allergen detection and quantification and introduces the promise of emerging non-destructive methods leveraging sensors and machine learning in comparison with conventional approaches.
Focussing on Fourier Transform Infrared (FTIR) spectroscopy, Hyperspectral Imaging (HSI) and Computer Vision (CV), the review authors propose that while each method carries advantages and limitations, the integration of artificial intelligence emerges as a particularly compelling opportunity for improved accuracy and efficiency in allergen management protocols.
For example, AI-enabled sensors and imaging technologies that offer non-destructive methods for allergen detection allow for real-time monitoring without altering the integrity of food products. This capability could be particularly useful in quality control during production and packaging stages.
As the field continues to evolve, technology advancements will increase the accessibility of testing tools for customers and stakeholders across the food supply chain, driving greater assurance and safety for allergic consumers.
Reference: Adedeji, et al. 2024. The Magnitude and Impact of Food Allergens and the Potential of AI-Based Non-Destructive Testing Methods in Their Detection and Quantification. Foods. 13 (7) pp. 994. DOI: 10.3390/foods13070994. Available with Open Access.
