Phoenix 100 versus Vitek 2 in the identification of gram-positive and gram-negative bacteria: a comprehensive meta-analysis

Abstract

Phoenix 100 and Vitek 2 (operating with the current colorimetric cards) are commonly used in hospital laboratories for rapid identification of microorganisms. The present meta-analysis aims to evaluate and compare their performance on Gram-positive and Gram-negative bacteria. The MEDLINE database was searched up to October 2010 for the retrieval of relevant articles. Pooled correct identification rates were derived from random-effects models, using the arcsine transformation. Separate analyses were conducted at the genus and species levels; subanalyses and meta-regression were undertaken to reveal meaningful system- and study-related modifiers. A total of 29 (6,635 isolates) and 19 (4,363 isolates) articles were eligible for Phoenix and colorimetric Vitek 2, respectively. No significant differences were observed between Phoenix and Vitek 2 either at the genus (97.70% versus 97.59%, P = 0.919) or the species (92.51% versus 88.77%, P = 0.149) level. Studies conducted with conventional comparator methods tended to report significantly better results compared to those using molecular reference techniques. Speciation of Staphylococcus aureus was significantly more accurate in comparison to coagulase-negative staphylococci by both Phoenix (99.78% versus 88.42%, P < 0.00001) and Vitek 2 (98.22% versus 91.89%, P = 0.043). Vitek 2 also reached higher correct identification rates for Gram-negative fermenters versus nonfermenters at the genus (99.60% versus 95.90%, P = 0.004) and the species (97.42% versus 84.85%, P = 0.003) level. In conclusion, the accuracy of both systems seems modified by underlying sample- and comparator method-related parameters. Future simultaneous assessment of the instruments against molecular comparator procedures may facilitate interpretation of the current observations.

Fig. 1.

Results of the meta-analysis for Phoenix and Vitek 2 at the genus (a and c, respectively) and species (b and d, respectively) levels. Each study is shown by a point estimate of the effect size (correct identification rate) and its 95% confidence intervals derived from the arcsine (Freeman-Tukey) transformation algorithm. The diamond represents the summary random-effects estimate from the meta-analysis.