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 language | English |
---|---|
Pages (from-to) | 1130-1140 |
Number of pages | 11 |
Journal | Analyst |
Volume | 148 |
Issue number | 5 |
DOIs | |
State | Published - 19 Jan 2023 |
ASJC Scopus subject areas
- Analytical Chemistry
- Biochemistry
- Environmental Chemistry
- Spectroscopy
- Electrochemistry