Infrared Spectroscopy Combined with AI Automates Detection of Staphylococcus aureus

An instrument employing this technique shines a beam containing many frequencies of light at once, and measures how much of that beam is absorbed by the sample. Next, the beam is modified to contain a different combination of frequencies, giving a second data point. This process is repeated many times. Afterwards, a computer takes all these data and works backwards to infer what the absorption was at each wavelength.

Investigators at the University of Veterinary Medicine (Vienna, Austria) combined FTIR spectroscopy with a computerized self-learning system known as an artificial neuronal network (ANN). A comprehensive set of clinical isolates derived from different origins and control strains, representative for each serotype was used to "teach" the system to recognize the spectra emitted by the capsular polysaccharides (CP) present on the surface of the clinically relevant strains of S. aureus.

Studies carried out with the high-throughput ANN-assisted FTIR spectroscopy CP typing system yielded overall accuracy of 96.7% for internal validation and 98.2% for external validation. These results support the use of this system for diagnostic as well as large-scale epidemiologic surveillance of S. aureus capsule expression,

Senior author Dr. Monika Ehling-Schulz, professor of functional microbiology at the University of Veterinary Medicine, said, "In principle, germs have two choices when they infect a host: attack or hide—in technical terms virulence or persistence. If they attack, they risk destroying the host and consequently themselves, whereas if they hide, they may be outcompeted by others. A detailed knowledge of the mechanisms of virulence and persistence and the way bacteria switch between them will help us to develop novel and more effective therapies."

A full description of the ANN-assisted FTIR spectroscopy CP typing system was published in the July 2013 issue of the Journal of Clinical Microbiology.

Related Links:
University of Veterinary Medicine