RAPID IDENTIFICATION OF URINARY-TRACT INFECTION BACTERIA USING HYPERSPECTRAL WHOLE-ORGANISM FINGERPRINTING AND ARTIFICIAL NEURAL NETWORKS

Three rapid spectroscopic approaches for whole-organism fingerprinting pyrolysis mass spectrometry (PyMS), Fourier transform infra-red spect roscopy (FT-IR) and dispersive Raman microscopy - were used to analyse a group of 59 clinical bacterial isolates associated with urinary tra ct 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 fu nction and hierarchical cluster analyses were employed to group these organisms based on their spectral fingerprints, but none produced whol ly satisfactory groupings which were characteristic for each of the fi ve bacterial types. In contrast, for PyMS and FT-IR, the artificial ne ural network (ANN) approaches exploiting multi-layer perceptrons or ra dial basis functions could be trained with representative spectra of t he five bacterial groups so that isolates from clinical bacteriuria in an independent unseen test set could be correctly identified. Compara ble ANNs trained with Raman spectra correctly identified some 80% of t he same test set. PyMS and FT-IR have often been exploited within micr obial systematics, but these are believed to be the first published da ta showing the ability of dispersive Raman microscopy to discriminate clinically significant intact bacterial species. These results demonst rate that modern analytical spectroscopies of high intrinsic dimension ality can provide rapid accurate microbial characterization techniques , but only when combined with appropriate chemometrics.