Differentiation of closely-related species within Acinetobacter baumannii-calcoaceticus complex via Raman spectroscopy: a comparative machine learning analysis

In this study, we combined surfaced-enhanced Raman spectroscopy (SERS) with a set of machine learning algorithms for identifying species within the Acb complex. According to the results, the support vector machine (SVM) model achieved the best prediction accuracy at 98.33% with a fivefold cross-validation rate of 96.73%. Taken together, this study confirms that the SERS-SVM method provides a convenient way to discriminate betweenA. baumannii,Acinetobacter pittii, andAcinetobacter nosocomialis in the Acb complex, which shows an application potential for species identification ofAcinetobacter baumannii-calcoaceticus complex in clinical settings in near future.
Source: World Journal of Microbiology and Biotechnology - Category: Microbiology Source Type: research