Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning

Raman optical spectroscopy promises label-free bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and accuracies remains challenging due to weak Raman signal from bacterial cells and numerous bacterial species and phenotypes. Here we generate an extensive dataset of bacterial Raman spectra and apply deep learning approaches to accurately identify 30 common bacterial pathogens. Even on low signal-to-noise spectra, we achieve average isolate-level accuracies exceeding 82% and antibiotic treatment identification accuracies of 97.0±0.3%. We also show that this approach distinguishes between methicillin-resistant and…

• NS
  National Science Foundation

  Awards: 1542152, award ECCS-1542152
• UD
  U.S. Department of Defense
• BA
  Bill and Melinda Gates Foundation
• AP
  Alfred P. Sloan Foundation
• SN
  Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

  Award: ECCS-1542152
• ND
  National Defense Science and Engineering Graduate
• DO
  Division of Electrical, Communications and Cyber Systems

  Awards: ECCS-1542152, 1542152