Culture-independent susceptibility determination of E. coli isolated directly from patients’ urine using FTIR and machine-learning

Abstract

One of the most common human bacterial infections is the urinary tract infection (UTI).

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

“…These encouraging results are in agreement with our previous studies that proved the potential of this approach to determine the susceptibility of bacteria obtained directly from a patient's urine to various antibiotics. 56,57…”

“…These encouraging results are in agreement with our previous studies that proved the potential of this approach to determine the susceptibility of bacteria obtained directly from a patient's urine to various antibiotics. 56,57 It is worth noting that a major part of the spectral differences observed in Fig. 5 and 8 are mainly taxonomic (different strains) and not due to resistivity.…”

“…Thus, to differentiate between these classes, advanced machine learning techniques were applied. Based on our previous studies, 40,43,54,56,57 the second derivative spectra (Fig. 5) were used as feature vectors for all subsequent classification experiments.…”

Significant reduction of the culturing time required for bacterial identification and antibiotic susceptibility determination by infrared spectroscopy

“…[16][17][18][19] Notably, it has been utilized for identifying different clinical and environmental microorganisms, such as fungi and bacteria at the strain level. [20][21][22][23][24][25] Our previous studies have effectively assessed the capability of infrared microscopy, coupled with machine learning, to identify bacterial susceptibility to antibiotics within approximately 20 minutes aer the rst culture. Consequently, the testing duration was notably shortened from a minimum of 48 hours to approximately 24 hours.…”

“…Consequently, the testing duration was notably shortened from a minimum of 48 hours to approximately 24 hours. 26,27 Additionally, our research group 25,28 has attained remarkable accuracy in identifying bacterial susceptibility in urinary tract infection (UTI) patients directly from their urine samples within 40 minutes postsample receipt.…”