Instant detection of extended-spectrum β-lactamase-producing bacteria from the urine of patients using infrared spectroscopy combined with machine learning

George Abu-Aqil, Manal Suleiman, Uraib Sharaha, Itshak Lapidot, Mahmoud Huleihel, Ahmad Salman

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Antibiotics are considered the most effective treatment against bacterial infections. However, most bacteria have already developed resistance to a broad spectrum of commonly used antibiotics, mainly due to their uncontrolled use. Extended-spectrum beta-lactamase (ESBL)-producing bacteria are an essential class of multidrug-resistant (MDR) bacteria. It is of extreme urgency to develop a method that can detect ESBL-producing bacteria rapidly for the effective treatment of patients with bacterial infectious diseases. Fourier transform infrared (FTIR) microscopy is a sensitive method that can rapidly detect cellular molecular changes. In this study, we examined the potential of FTIR spectroscopy-based machine learning algorithms for the rapid detection of ESBL-producing bacteria obtained directly from a patient's urine. Using 591 ESBL-producing and 1658 non-ESBL-producing samples of Escherichia coli (E. coli) and Klebsiella pneumoniae, our results show that the FTIR spectroscopy-based machine learning approach can identify ESBL-producing bacteria within 40 minutes from receiving a patient's urine sample, with a success rate of 80%.

Original languageEnglish
Pages (from-to)1130-1140
Number of pages11
JournalAnalyst
Volume148
Issue number5
DOIs
StatePublished - 19 Jan 2023

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry
  • Environmental Chemistry
  • Spectroscopy
  • Electrochemistry

Fingerprint

Dive into the research topics of 'Instant detection of extended-spectrum β-lactamase-producing bacteria from the urine of patients using infrared spectroscopy combined with machine learning'. Together they form a unique fingerprint.

Cite this