Field-Deployable Risk Stratification of Pathogens via an AI-Integrated Nanozyme Sensor.

Area of Science:

• Nanotechnology
• Environmental Science
• Analytical Chemistry

Background:

• Pathogen surveillance in complex environments demands sensitive, robust, and field-deployable analytical methods.
• Existing methods often lack the sensitivity or practicality for real-time environmental monitoring.

Purpose of the Study:

• To develop a geometry-engineered trimetallic nanozyme-enabled multimodal lateral flow immunoassay (LFIA) for enhanced pathogen detection.
• To create a self-contained, intelligent, and field-deployable system for pathogen analysis and risk stratification.

Main Methods:

• Fabrication of spiky porous trimetallic PdPtRu nanozymes for improved photothermal and catalytic properties.
• Integration of nanozymes into LFIAs for pathogen detection, validated with *Salmonella typhimurium*.
• Development of a smartphone application with a convolutional neural network and a portable 3D-printed module for signal acquisition and analysis.

Main Results:

• The nanozyme exhibited enhanced photothermal conversion and catalytic activity due to its unique architecture and multimetallic synergy.
• LFIA sensitivity for *Salmonella typhimurium* was increased 200-fold compared to conventional colloidal gold assays.
• The integrated system achieved high predictive performance for risk-level stratification (R² = 0.98, AUC = 0.99).

Conclusions:

• The developed nanozyme-LFIA platform provides a sensitive, robust, and field-deployable solution for pathogen surveillance.
• The intelligent detection system facilitates rapid risk assessment and timely public health interventions.
• This work lays the foundation for scalable, modular early-warning systems for environmental pathogen monitoring.