Next-generation COVID-19 detection using a metasurface biosensor with machine learning-enhanced refractive index...

Area of Science:

• Nanotechnology
• Biosensing
• Terahertz (THz) technology

Background:

• Conventional COVID-19 tests like RT-PCR and antigen tests face limitations including delays, high costs, and reduced sensitivity, especially in asymptomatic cases.
• There is a critical need for rapid, accurate, and cost-effective diagnostic tools for effective pandemic response and preparedness.

Purpose of the Study:

• To develop and characterize a high-performance graphene-silver hybrid metasurface biosensor for fast and precise COVID-19 detection.
• To leverage machine learning for enhanced predictive reliability of the biosensor across varying refractive indices.
• To demonstrate a scalable and practical fabrication strategy for the proposed biosensor.

Main Methods:

• Parametric optimization of the graphene-silver metasurface using COMSOL Multiphysics.
• Fabrication involving Chemical Vapor Deposition (CVD) graphene growth, electron beam lithography, and silver deposition.
• Implementation of a machine learning framework to improve predictive accuracy and reliability.

Main Results:

• Achieved high sensitivity (400 GHz/RIU), figure of merit (FOM) of 5.000 RIU⁻¹, and Q factor of 12.7 within a specific refractive index range.
• Machine learning model demonstrated high predictive reliability with a coefficient of determination (R²) of 0.90.
• The proposed sensor surpasses the performance of existing optical and terahertz biosensors in terms of sensitivity, FOM, and predictive accuracy.

Conclusions:

• The synergistic integration of a graphene-silver metasurface with machine learning enables rapid, label-free, and highly accurate COVID-19 detection.
• The developed biosensor offers a superior balance of performance metrics compared to conventional diagnostic methods.
• This novel, portable, and cost-effective diagnostic tool holds significant potential for next-generation pandemic preparedness.