Machine learning-assisted nitrite detection on smartphone-integrated μPAD using lychee-like perovskite nanocomposites

Area of Science:

• Materials Science
• Nanotechnology
• Analytical Chemistry

Background:

• Reliable nitrite detection is essential for environmental monitoring and food safety.
• Existing methods often lack convenience, portability, or sensitivity.
• Development of novel detection platforms is crucial for addressing these limitations.

Purpose of the Study:

• To develop a novel dual-response nitrite detection platform using CsPbCl3: Mn2+@MSN@MnO2 (ClMnM@MnO2) nanocomposites.
• To create a portable system for quantitative nitrite detection and antioxidant discrimination.
• To expand the application of perovskites in biosensing for complex matrices.

Main Methods:

• Synthesis of monodisperse, water-stable ClMnM@MnO2 nanocomposites with in-situ grown perovskite nanocrystals in mesoporous silica.
• MnO2 shell formation via NaClO-mediated oxidation for enhanced oxidase-like activity.
• Integration of nanocomposites with a microfluidic paper-based device (μPAD) for smartphone-based image analysis and machine learning (ANN algorithm) for data processing.

Main Results:

• The ClMnM@MnO2 nanocomposites demonstrated enhanced dispersion and stability in water.
• The developed μPAD system enabled quantitative nitrite detection and antioxidant additive discrimination using smartphone imaging.
• The platform achieved high sensitivity and accuracy in nitrite concentration prediction through machine learning analysis.

Conclusions:

• The novel ClMnM@MnO2 nanocomposites offer a robust platform for dual-response nitrite detection.
• The integrated μPAD and machine learning system provides a portable, convenient, and accurate solution for real-world nitrite monitoring.
• This work highlights the potential of perovskite-based nanomaterials in advanced biosensing applications for environmental and food safety.