Harnessing machine learning to predict antibiotic susceptibility in Pseudomonas aeruginosa biofilms

Antibiotic susceptibility tests (ASTs) often fail to predict treatment outcomes because they do not account for biofilm-specific tolerance mechanisms. In the present study, we explored alternative approaches to predict tobramycin susceptibility of Pseudomonas aeruginosa biofilms that were experimentally evolved in physiologically relevant conditions. To this end, we used four analytical methods - whole-genome sequencing (WGS), matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS), isothermal microcalorimetry (IMC) and multi-excitation Raman spectroscopy (MX-Raman). Machine learning models were trained on data outputs from these methods to predict tobramycin susceptibility of our evolved strains and validated with a collection of clinical isolates. For minimal inhibitory concentration (MIC) predictions of the evolved strains, the highest accuracy was achieved with MALDI-TOF MS (97.83%), while for biofilm prevention concentration (BPC) predictions, Raman spectroscopy performed best with an accuracy of 80.43%. Overall, all analytical methods demonstrated comparable predictive performance, showing their potential for improving biofilm AST.

Authors

Institutions

Publication Details

Journal
npj Biofilms and Microbiomes
Published
2025-11-10
DOI
https://doi.org/10.1038/s41522-025-00833-4
Citations
1
Primary Topic
Bacterial Identification and Susceptibility Testing
Type
article
Field-Weighted Citation Impact
1.32

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Harnessing machine learning to predict antibiotic susceptibility in Pseudomonas aeruginosa biofilms

Margo Cnockaert, Thomas Bjarnsholt, Peter Vandamme, Mads Lichtenberg et al.
1 citations
npj Biofilms and Microbiomes
Bacterial Identification and Susceptibility Testing
1.32
article

Harnessing machine learning to predict antibiotic susceptibility in Pseudomonas aeruginosa biofilms

Margo Cnockaert, Thomas Bjarnsholt, Peter Vandamme, Mads Lichtenberg, Willem Waegeman, Sumeet Mahajan, Niall Hanrahan, Jeremy S. Webb, Callum Highmore, Y. Cook, Gaetan De Waele, Andrea Saß, Filip Van Nieuwerburgh, Tom Coenye, Fauve Vergauwe
article en
1 citations

Abstract

Antibiotic susceptibility tests (ASTs) often fail to predict treatment outcomes because they do not account for biofilm-specific tolerance mechanisms. In the present study, we explored alternative approaches to predict tobramycin susceptibility of Pseudomonas aeruginosa biofilms that were experimentally evolved in physiologically relevant conditions. To this end, we used four analytical methods - whole-genome sequencing (WGS), matrix-assisted laser desorption/ionization-time of flight mass spectrometry (MALDI-TOF MS), isothermal microcalorimetry (IMC) and multi-excitation Raman spectroscopy (MX-Raman). Machine learning models were trained on data outputs from these methods to predict tobramycin susceptibility of our evolved strains and validated with a collection of clinical isolates. For minimal inhibitory concentration (MIC) predictions of the evolved strains, the highest accuracy was achieved with MALDI-TOF MS (97.83%), while for biofilm prevention concentration (BPC) predictions, Raman spectroscopy performed best with an accuracy of 80.43%. Overall, all analytical methods demonstrated comparable predictive performance, showing their potential for improving biofilm AST.

npj Biofilms and MicrobiomesVol. 11(1)
University of Copenhagen (DK), Ghent University Hospital (BE), Copenhagen University Hospital (DK), Rigshospitalet (DK), University Hospital Southampton NHS Foundation Trust (GB), Ghent University (BE), NIHR Southampton Biomedical Research Centre (GB), University of Southampton (GB)
University of Otago, Universiteit Gent, Vlaamse regering, Bijzonder Onderzoeksfonds UGent
Openalex Percentile: Top 14%
Bacterial Identification and Susceptibility Testing
1.32
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.