Bosch A, Miñán A, Vescina C, Degrossi J, Gatti B, Montanaro P, Messina M, Franco M, Vay C, Schmitt J, Naumann D, Yantorno O (2008): Rapid Identification of Nonfermenting Gram-Negative Bacteria Isolated from Sputum Samples of Cystic Fibrosis Patients by FT-IR Spectroscopy
J. Clin. Microbiol. 46 (8): 2535-2546. Epub Jun 11.

Accurate and rapid identification of bacteria isolated from the respiratory tract of cystic fibrosis (CF) patients is critical in epidemiological studies, intra-hospital outbreaks, patient treatment, and therapeutic options. While the most common organisms isolated from sputum samples are Pseudomonas aeruginosa, Staphylococcus aureus, and Haemophilus influenzae, in the last decades an increasing fraction of CF patients has been colonized by other non-fermenting (NF) Gram-negative rods as Burkholderia cepacia complex (BCC) bacteria, Stenotrophomonas maltophilia, Ralstonia pickettii, Acinetobacter spp., and Achromobacter spp. Here, we developed a novel strategy for rapid identification of NF rods based on Fourier transform infrared (FT-IR) spectroscopy in combination with artificial neural networks (ANN).

A total of 15 reference strains and 169 clinical isolates of NF Gram-negative bacteria recovered from sputum samples of 150 CF patients were used in this study. The clinical isolates were identified according to the guidelines for clinical microbiology practices for CF respiratory tract specimens; and particularly, BCC bacteria were further identified by recA PCR restriction fragment length polymorphisms (RFLP) using HaeIII and confirmed by recA species-specific PCR. Besides, some strains belonging to the other genera different to BCC were identified by 16S rRNA gene sequencing.

A standardized experimental protocol was established and an FT-IR spectral database containing more than 2000 IR spectra was created. The ANN identification system consisted of two hierarchical levels. The top-level network allowed the identification of P. aeruginosa, S. maltophilia, A. xylosoxidans, Acinetobacter spp, R. pickettii, and BCC bacteria with an identification success of 98.1%. The second-level network was developed to differentiate the 4 most clinically relevant species of BCC, B. cepacia, B. multivorans, B. cenocepacia and B. stabilis (genomovars I to IV), with a correct identification rate of 93.8 %.

Our results demonstrate the high reliability and strong potential of ANN-based FT-IR spectrum analysis for a rapid identification of NF rods suitable for use in routine clinical microbiology laboratories.