EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra

Hoai-An Nguyen iD, Anton Y Peleg iD, Jiangning Song iD, Bhavna Antony iD, Geoffrey I Webb iD, Jessica A Wisniewski, Luke V Blakeway, Gnei Z Badoordeen, Ravali Theegala, Helen Zisis, David L Dowe iD, Nenad Macesic iD

mSystems · 17.09.2024 · 9 (9)

DOI: 10.1128/msystems.00789-24 ↗

Kurz gefasst

Fachartikel in der Zeitschrift mSystems, erschienen am 17.09.2024. Verfasst von Hoai-An Nguyen und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Infectious Diseases, The Alfred Hospital and School of Translational Medicine, Monash University, Melbourne, Australia. Hauptthemen laut MEDLINE: Pseudomonas aeruginosa, Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization, Artificial Intelligence, Anti-Bacterial Agents. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DHAC | National Health and Medical Research Council (NHMRC), Australian Medical Research Future Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Matrix-assisted laser desorption/ionization–time of flight mass spectrometry (MALDI-TOF MS) is widely used in clinical microbiology laboratories for bacterial identification but its use for detection of antimicrobial resistance (AMR) remains limited. Here, we used MALDI-TOF MS with artificial intelligence (AI) approaches to successfully predict AMR in Pseudomonas aeruginosa , a priority pathogen with complex AMR mechanisms. The highest performance was achieved for modern β-lactam/β-lactamase inhibitor drugs, namely, ceftazidime/avibactam and ceftolozane/tazobactam. For these drugs, the model demonstrated area under the receiver operating characteristic curve (AUROC) of 0.869 and 0.856, specificity of 0.925 and 0.897, and sensitivity of 0.731 and 0.714, respectively. As part of this work, we developed dynamic binning, a feature engineering technique that effectively reduces the high-dimensional feature set and has wide-ranging applicability to MALDI-TOF MS data. Compared to conventional feature engineering approaches, the dynamic binning method yielded highest performance in 7 of 10 antimicrobials. Moreover, we showcased the efficacy of transfer learning in enhancing the AUROC performance for 8 of 11 antimicrobials. By assessing the contribution of features to the model's prediction, we identified proteins that may contribute to AMR mechanisms. Our findings demonstrate the potential of combining AI with MALDI-TOF MS as a rapid AMR diagnostic tool for Pseudomonas aeruginosa . IMPORTANCE Pseudomonas aeruginosa is a key bacterial pathogen that causes significant global morbidity and mortality. Antimicrobial resistance (AMR) emerges rapidly in P. aeruginosa and is driven by complex mechanisms. Drug-resistant P. aeruginosa is a major challenge in clinical settings due to limited treatment options. Early detection of AMR can guide antibiotic choices, improve patient outcomes, and avoid unnecessary antibiotic use. Matrix-assisted laser desorption/ionization–time of flight mass spectrometry (MALDI-TOF MS) is widely used for rapid species identification in clinical microbiology. In this study, we repurposed mass spectra generated by MALDI-TOF and used them as inputs for artificial intelligence approaches to successfully predict AMR in P. aeruginosa for multiple key antibiotic classes. This work represents an important advance toward using MALDI-TOF as a rapid AMR diagnostic for P. aeruginosa in clinical settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pseudomonas aeruginosaSpectrometry, Mass, Matrix-Assisted Laser Desorption-IonizationArtificial IntelligenceAnti-Bacterial AgentsTazobactamHumansPseudomonas InfectionsMicrobial Sensitivity TestsDrug Resistance, BacterialDrug CombinationsCeftazidimeAzabicyclo CompoundsCephalosporins

Stichwörter der Autor:innen

MALDI-TOF MSPseudomonas aeruginosaantimicrobial resistancemachine learning

Substanzen

Anti-Bacterial AgentsTazobactamceftolozane, tazobactam drug combinationDrug CombinationsCeftazidimeavibactam, ceftazidime drug combinationAzabicyclo CompoundsCephalosporins

Autor:innen und Institutionen

  • Department of Infectious Diseases, The Alfred Hospital and School of Translational Medicine, Monash University, Melbourne, Australia.
  • Department of Microbiology, Monash Biomedicine Discovery Institute, Monash University, Melbourne, Australia.
  • Centre to Impact AMR, Monash University, Melbourne, Australia.
  • Department of Biochemistry & Molecular Biology, Monash Biomedicine Discovery Institute, Monash University, Melbourne, Australia.
  • Department of Data Science & AI, Monash University, Melbourne, Australia.

ORCID-Profile: Hoai-An Nguyen, Anton Y Peleg, Jiangning Song, Bhavna Antony, Geoffrey I Webb, David L Dowe, Nenad Macesic

Förderung

  • DHAC | National Health and Medical Research Council (NHMRC)
  • Australian Medical Research Future Fund

Zitieren

APA

Nguyen, H. A., Peleg, A. Y., Song, J., Antony, B., Webb, G. I., Wisniewski, J. A., Blakeway, L. V., Badoordeen, G. Z., Theegala, R., Zisis, H., Dowe, D. L., & Macesic, N. (2024). Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra. mSystems, 9(9). https://doi.org/10.1128/msystems.00789-24

Vancouver

Nguyen HA, Peleg AY, Song J, Antony B, Webb GI, Wisniewski JA, et al. Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra. mSystems. 2024;9(9). doi:10.1128/msystems.00789-24

BibTeX
@article{Nguyen2024,
  author = {Nguyen, Hoai-An and Peleg, Anton Y and Song, Jiangning and Antony, Bhavna and Webb, Geoffrey I and Wisniewski, Jessica A and Blakeway, Luke V and Badoordeen, Gnei Z and Theegala, Ravali and Zisis, Helen and Dowe, David L and Macesic, Nenad},
  title = {Predicting Pseudomonas aeruginosa drug resistance using artificial intelligence and clinical MALDI-TOF mass spectra},
  journal = {mSystems},
  year = {2024},
  volume = {9},
  number = {9},
  doi = {10.1128/msystems.00789-24}
}
Kostenlos starten →