Fast identification and susceptibility determination of E. coli isolated directly from patients' urine using infrared-spectroscopy and machine learning

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

Research output: Contribution to journalArticlepeer-review

Abstract

For effective treatment, it is crucial to identify the infecting bacterium at the species level and to determine its antimicrobial susceptibility. This is especially true now, when numerous bacteria have developed multidrug resistance to most commonly used antibiotics. Currently used methods need ∼ 48 h to identify a bacterium and determine its susceptibility to specific antibiotics. This study reports the potential of using infrared spectroscopy with machine learning algorithms to identify E. coli isolated directly from patients' urine while simultaneously determining its susceptibility to antibiotics within ∼ 40 min after receiving the patient's urine sample. For this goal, 1,765 E. coli isolates purified directly from urine samples were collected from patients with urinary tract infections (UTIs). After collection, the samples were tested by infrared microscopy and analyzed by machine learning. We achieved success rates of ∼ 96% in isolate level identification and ∼ 84% in susceptibility determination.

Original languageEnglish
Pages (from-to)121909
Number of pages1
JournalSpectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy
Volume285
DOIs
StatePublished - 15 Jan 2023

Keywords

  • Antibiotic
  • Bacteria
  • Bacterial susceptibility to antimicrobials
  • E. coli
  • Infrared spectroscopy
  • Machine learning
  • Urinary tract infections (UTIs)

ASJC Scopus subject areas

  • Analytical Chemistry
  • Atomic and Molecular Physics, and Optics
  • Instrumentation
  • Spectroscopy

Fingerprint

Dive into the research topics of 'Fast identification and susceptibility determination of E. coli isolated directly from patients' urine using infrared-spectroscopy and machine learning'. Together they form a unique fingerprint.

Cite this