# Evaluation of rapid detection methods for H5N1 virus using biosensors: An AI-based study

## TL;DR

This study uses AI simulations to evaluate biosensors for rapid detection of H5N1 virus in saliva, aiming to improve quick diagnosis during potential outbreaks.

## Contribution

The novel contribution is the AI-based simulation and evaluation of three biosensor types for rapid H5N1 detection.

## Key findings

- LFT, FET, and QCM biosensors showed potential for rapid H5N1 detection in saliva samples.
- AI simulations highlighted the sensitivity and specificity of each biosensor type.
- The study proposes a framework for rapid deployment of these biosensors during outbreaks.

## Abstract

High mortality and zoonotic potential predispose the H5N1 avian influenza virus as a critical threat. knowing that an epidemic could
be occurring, quick and precise diagnostic techniques are essential for managing and containing possible epidemics. To detect H5N1 in
saliva samples, this study investigates the theoretical design, simulation and evaluation of three kind of biosensors based on different
technologies with potential as rapid identifications tools to diagnose quickly H5N1: Lateral Flow Tests (LFT), Field Effect transistors
(FET) based electrochemical sensors and Quartz Crystal Microbalance (QCM) sensors. Through detailed AI-based simulations, we show the
capabilities, sensitivities and specificities of these biosensors, highlighting their potential for applications in general biology as
well as their suitability both for routine home practice and for applications by control entities in public settings. We therefore wish
to pave the way to a framework for the quick creation of detection tools that can be swiftly implemented for rapid deployment in case of
an outbreak of disease.