Related Experiment Video
Updated: Jun 26, 2026
09:04
Foodborne Pathogen Screening Using Magneto-fluorescent Nanosensor: Rapid Detection of E. Coli O157:H7
Published on: September 17, 2017
Deep learning integrated plasmonic electrochemical sensing for fast and accurate pathogen detection.
Sahar Mansour1, Noha Negm2, Asma A Alhashmi3
1Department of Radiological Sciences, College of Health and Rehabilitation Sciences, Princess Nourahbint Abdulrahman University, P.O. Box 84428, 11671, Riyadh, Saudi Arabia.
Scientific Reports
|June 24, 2026
Summary
This study introduces a novel plasmonic biosensor combined with deep learning for rapid pathogen detection. The AI-powered system achieves high accuracy in identifying bacteria like E. coli, Salmonella, and Staphylococcus aureus in under 10 minutes.
Area of Science:
- Nanotechnology and biosensing
- Artificial intelligence in diagnostics
- Electrochemical biosensor development
Background:
- Pathogen diagnostics require rapid, field-deployable solutions.
- Current methods often lack sensitivity or speed for early detection.
- Integrating advanced AI with nanostructured biosensors offers a promising approach.
Purpose of the Study:
- To develop a plasmonic electrochemical biosensor integrated with a deep learning model for sensitive and rapid detection of key bacterial pathogens.
- To enhance biosensor performance using gold-nanoparticle graphene oxide nanocomposites and localized surface plasmon resonance (LSPR).
- To evaluate the diagnostic capabilities of a MobileNet-Transformer and Gated Recurrent Unit (GRU) deep neural network for pathogen identification.
Main Methods:
- Fabrication of a nanostructured plasmonic biosensor using gold-nanoparticle graphene oxide hybrid nanocomposites.
- Utilizing localized surface plasmon resonance (LSPR) to enhance electrochemical responses.
- Implementing a deep learning pipeline combining MobileNet-Transformer for feature extraction and GRU for signal processing of voltammetric data.
- Testing the biosensor's performance against Escherichia coli, Salmonella typhimurium, and Staphylococcus aureus.
Main Results:
- Achieved ultra-low limits of detection for E. coli (0.12 pg/mL), Salmonella (0.17 pg/mL), and S. aureus (0.21 pg/mL).
- Demonstrated rapid assay time of less than 10 minutes with a small sample volume (5 μL).
- The AI model achieved high classification accuracy (95.6%) and AUC (0.986), outperforming baseline models.
- The system showed comparable performance to laboratory benchtop systems in a portable format.
Conclusions:
- The integrated plasmonic biosensor and deep learning system enables real-time, on-device pathogen diagnostics.
- This AI-assisted electrochemical biosensing platform is suitable for applications in food safety, environmental monitoring, and point-of-care diagnostics.
- The study presents a scalable and cost-effective approach for portable diagnostic hardware compatible with advanced AI.
