Rapid identification of urinary tract infection bacteria using hyperspectral whole-organism fingerprinting and artificial neural networks

• Published in: Microbiology (Society for General Microbiology) Vol. 144; no. 5; pp. 1157 - 1170
• Main Authors: Goodacre, Royston, Timmins, eadaoin M, Burton, Rebecca, Kaderbhai, Naheed, Woodward, Andrew M, Kell, Douglas B, Rooney, Paul J
• Format: Journal Article
• Language: English
• Published: Reading Soc General Microbiol 01.05.1998; Society for General Microbiology
• Subjects: Bacterial diseases; Bacterial diseases of the urinary system; Bacterial Typing Techniques; Bacteriological methods and techniques used in bacteriology; Bacteriology; Biological and medical sciences; Cluster Analysis; Enterobacteriaceae - classification; Enterobacteriaceae - isolation & purification; Enterobacteriaceae Infections - microbiology; Enterococcus - classification; Enterococcus - isolation & purification; Fundamental and applied biological sciences. Psychology; Gram-Positive Bacterial Infections - microbiology; Human bacterial diseases; Humans; Infectious diseases; Mass Spectrometry; Medical sciences; Microbiology; Neural Networks, Computer; Pseudomonas - classification; Pseudomonas - isolation & purification; Pseudomonas Infections - microbiology; Spectroscopy, Fourier Transform Infrared; Spectrum Analysis; Spectrum Analysis, Raman; Urinary Tract Infections - microbiology; Urine - microbiology; Infection; Human; Infrared spectrometry; Urinary system disease; Bacteriuria; Bacteriosis; Bacteria; Identification; Raman spectrometry; Neural network; Mass spectrometry
• ISSN: 1350-0872; 1465-2080
• DOI: 10.1099/00221287-144-5-1157

Institute of Biological Sciences, University of Wales, Aberystwyth, Ceredigion SY23 3DD, UK Bronglais General Hospital,Aberystwyth, Ceredigion SY23 lER, UK ABSTRACT Three rapid spectroscopic approaches for whole-organism fingerprinting-pyrolysis mass spectrometry (PyMS), Fourier transform infra-red spectroscopy (FT-IR) and dispersive Raman microscopy - were used to analyse a group of 59 clinical bacterial isolates associated with urinary tract infection. Direct visual analysis of these spectra was not possible, highlighting the need to use methods to reduce the dimensionality of these hyperspectral data. The unsupervised methods of discriminant function and hierarchical cluster analyses were employed to group these organisms based on their spectral fingerprints, but none produced wholly satisfactory groupings which were characteristic for each of the five bacterial types. In contrast, for PyMS and FT-IR, the artificial neural network (ANN) approaches exploiting multi-layer perceptrons or radial basis functions could be trained with representative spectra of the five bacterial groups so that isolates from clinical bacteriuria in an independent unseen test set could be correctly identified. Comparable ANNs trained with Raman spectra correctly identified some 80% of the same test set. PyMS and FT-IR have often been exploited within microbial systematics, but these are believed to be the first published data showing the ability of dispersive Raman microscopy to discriminate clinically significant intact bacterial species. These results demonstrate that modern analytical spectroscopies of high intrinsic dimensionality can provide rapid accurate microbial characterization techniques, but only when combined with appropriate chemometrics. * Author for correspondence: Royston Goodacre. Tel: + 44 1970 621947. Fax: +44 1970 622354. e-mail: rrg@aber.ac.uk Keywords: artificial neural networks, Fourier-transform infrared spectroscopy, pyrolysis mass spectrometry, Raman microscopy, urinary tract infection