SP 2.2.4 - Machine Learning and Gas Sensors for Antimicrobial Reisistence Identification

Event

EUROSENSORS 2026
2026-09-06 - 2026-09-09
Zurich

Band

Lectures

Chapter

Antimicrobial Resistance Diagnostics

Author(s)

A. Belenguer-Llorens, E. Slack, A. T. Güntner, C. R. Jutzeler - ETH Zurich,Zurich (Switzerland), A. Egli - University of Zurich,Zurich (Switzerland), T. M. Kessler - Balgrist University Hospital,Zurich (Switzerland)

Pages

307 - 308

DOI

10.5162/eurosensors2026/SP2.2.4

ISBN

978-3-910600-12-6

Price

free

Abstract

The global rise of antimicrobial resistance (AMR) requires a paradigm shift away from slow, culturebased diagnostics toward more rapid, data-driven approaches. We propose a novel pipeline that integrates high-resolution volatilomics extracted from gas sensors with machine learning (ML) techniques to bypass traditional time-consuming workflows, enabling rapid identification of resistance profiles directly from microbial emissions. This approach aims to provide a scalable foundation for point-of-care diagnostics, with the potential to reduce antibiotic overuse and support timely, precision-guided therapy.