AI-powered programmable wetting-delamination μPAD for point-of-care food safety detection

Area of Science:

• Analytical Chemistry
• Biotechnology
• Materials Science

Background:

• Pesticide and genetically modified (GM) crop use impacts food security but poses health/ecosystem risks.
• Conventional detection methods are often complex, costly, and unsuitable for rapid, on-site analysis.
• There is a need for accessible, affordable diagnostics for food contaminants.

Purpose of the Study:

• To develop a low-cost, point-of-care microfluidic paper-based analytical device (μPAD) for rapid visual detection of food contaminants.
• To integrate a programmable wetting-delamination timer (PWDT) for controlled fluidic delays and enhanced detection.
• To enable simultaneous detection of pesticide residues and transgenic proteins for comprehensive food safety assessment.

Main Methods:

• Fabrication of μPADs with a novel PWDT using a precutting-assisted dip-dyeing strategy for improved stability and control.
• Development of a dual-mode color attenuation/enhancement (CA/CE) system using MnO2 nanozymes for sensitive phoxim pesticide detection.
• Implementation of a PWDT-assisted lateral flow assay (LFA) with signal amplification for detecting Cry1Ab/Ac transgenic protein, coupled with deep learning for automated analysis.

Main Results:

• The PWDT achieved programmable fluid delays with over 50% increased stability.
• The phoxim detection system demonstrated 100% sensitivity, 95% specificity, and 97.5% accuracy.
• The Cry1Ab/Ac detection system showed a 5.56-fold improvement in detection limit, with 100% sensitivity and 98.6% accuracy via deep learning analysis.

Conclusions:

• The PWDT-μPAD platform offers a versatile, scalable, and cost-effective solution for food safety diagnostics.
• This technology facilitates rapid, visual detection of both pesticide residues and transgenic proteins.
• The developed device is suitable for user-friendly food safety applications in low-resource and at-home settings.