Machine learning-driven fluorescent sensor array using aqueous CsPbBr₃ perovskite quantum dots for rapid detection...

Area of Science:

• Materials Science
• Biotechnology
• Analytical Chemistry

Background:

• Food safety is a growing global concern, necessitating rapid detection and disinfection of foodborne pathogens.
• Current methods for pathogen detection can be time-consuming and lack comprehensive analysis.

Purpose of the Study:

• To develop a novel machine learning-driven fluorescent sensor array for rapid identification and eradication of foodborne pathogens.
• To evaluate the sensor array's performance in terms of accuracy, detection limits, and disinfection efficiency.

Main Methods:

• Utilized aqueous CsPbBr3 perovskite quantum dots (PQDs) to create a fluorescent sensor array.
• Employed a Support Vector Machine (SVM) machine learning algorithm to analyze relative signal intensity changes (ΔRGB).
• Tested the array for pathogen identification in various concentrations and in tap water, followed by disinfection efficacy assessment.

Main Results:

• Achieved 100% accuracy in identifying five pathogens and their mixtures within a concentration range of 1.0 × 10^3 to 1.0 × 10^7 CFU/mL.
• Demonstrated low limits of detection (LOD) for the targeted pathogens.
• Showcased 100% accuracy in identifying pathogens in tap water and over 99% disinfection efficiency within 30 minutes.

Conclusions:

• The developed fluorescent sensor array offers a highly accurate and rapid solution for foodborne pathogen detection.
• The integrated disinfection capability enhances its utility as a comprehensive tool for food safety.
• This technology presents a significant advancement for public health and the food industry.