Growth independent morphometric machine learning workflow for single-cell antimicrobial susceptibility testing of Klebsiella pneumoniae to meropenem
Frontiers in Imaging · 2024
DOI: 10.3389/fimag.2024.1418669 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Imaging, 2024. Verfasst von Kristel C Tjandra und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency Medicine, Stanford University School of Medicine, Palo Alto, CA, USA. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAID NIH HHS, National Institute of Allergy and Infectious Diseases.
Abstract (Originalsprache)
Introduction
Multidrug-resistant Enterobacteriaceae are among the most urgent global public health threats associated with various life-threatening infections. In the absence of a rapid method to identify antimicrobial susceptibility, empirical use of broad-spectrum antimicrobials such as carbapenem monotherapy has led to the spread of resistant organisms. Rapid determination of antimicrobial resistance is urgently needed to overcome this issue.
Methods
By capturing dynamic single-cell morphological features, including growth-independent, antibiotic-induced changes, of cells from 19 strains of Klebsiella pneumoniae , we evaluated data processing strategies based on time and concentration differentials to develop models for classifying its susceptibility to a commonly used carbapenem, meropenem, and predicting their minimum inhibitory concentrations (MIC). Results and discussion We report morphometric antimicrobial susceptibility testing (MorphoAST), a growth independent, computer vision-based machine learning workflow, for rapid determination of antimicrobial susceptibility by single-cell morphological analysis within sub-doubling time of K. pneumoniae . We demonstrated the technological feasibility of predicting MIC/antimicrobial susceptibility in a fraction of the bacterial doubling time (<50 min). The classifiers achieved as high as 97% accuracy in 20 min (two-fifths of the doubling time) and reached over 99% accuracy within 50 min (one doubling time) in predicting the antimicrobial response of the validation dataset. A regression model based on the concentration differential of individual cells from nineteen strains predicted the MIC with 100% categorical agreement and essential agreement for seven unseen strains, including two clinical samples from patients with urinary tract infections with different responsiveness to meropenem, within 50 min of treatment. The expansion of this innovation to other drug-bug combinations could have significant implications for the future development of rapid antimicrobial susceptibility testing.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Emergency Medicine, Stanford University School of Medicine, Palo Alto, CA, USA.
- Department of Biomedical Engineering, The Pennsylvania State University, University Park, PA, USA.
- Department of Economics, Stanford University, Palo Alto, CA, USA.
- Department of Urology, Stanford University School of Medicine, Palo Alto, CA, USA.
- Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, USA.
- Department of Mechanical Engineering and Department of Surgery, The Pennsylvania State University, University Park, PA, USA.
Förderung
- NIAID NIH HHS
- National Institute of Allergy and Infectious Diseases
Zitieren
APA
Tjandra, K. C., Ram-Mohan, N., Roshardt, M., Zudock, E., Qu, Z., Mach, K. E., Eminaga, O., Liao, J. C., Yang, S., & Wong, P. K. (2024). Growth independent morphometric machine learning workflow for single-cell antimicrobial susceptibility testing of Klebsiella pneumoniae to meropenem. Frontiers in Imaging. https://doi.org/10.3389/fimag.2024.1418669
Vancouver
Tjandra KC, Ram-Mohan N, Roshardt M, Zudock E, Qu Z, Mach KE, et al. Growth independent morphometric machine learning workflow for single-cell antimicrobial susceptibility testing of Klebsiella pneumoniae to meropenem. Frontiers in Imaging. 2024. doi:10.3389/fimag.2024.1418669
BibTeX
@article{Tjandra2024,
author = {Tjandra, Kristel C and Ram-Mohan, Nikhil and Roshardt, Manuel and Zudock, Elizabeth and Qu, Zhaonan and Mach, Kathleen E and Eminaga, Okyaz and Liao, Joseph C and Yang, Samuel and Wong, Pak Kin},
title = {Growth independent morphometric machine learning workflow for single-cell antimicrobial susceptibility testing of Klebsiella pneumoniae to meropenem},
journal = {Frontiers in Imaging},
year = {2024},
doi = {10.3389/fimag.2024.1418669}
}
EUVIMED