Development and Validation of a Highly Accurate Quantitative Real-Time PCR Assay for Diagnosis of Bacterial Vaginosis

Bacterial vaginosis (BV) is the most common gynecological infection in the United States. Diagnosis based on Amsel's criteria can be challenging and can be aided by laboratory-based testing. A standard method for diagnosis in research studies is enumeration of bacterial morphotypes of a Gram-stained vaginal smear (i.e., Nugent scoring). However, this technique is subjective, requires specialized training, and is not widely available. Therefore, a highly accurate molecular assay for the diagnosis of BV would be of great utility. We analyzed 385 vaginal specimens collected prospectively from subjects who were evaluated for BV by clinical signs and Nugent scoring. We analyzed quantitative real-time PCR (qPCR) assays on DNA extracted from these specimens to quantify nine organisms associated with vaginal health or disease: Gardnerella vaginalis, Atopobium vaginae, BV-associated bacteria 2 (BVAB2, an uncultured member of the order Clostridiales), Megasphaera phylotype 1 or 2, Lactobacillus iners, Lactobacillus crispatus, Lactobacillus gasseri, and Lactobacillus jensenii. We generated a logistic regression model that identified G. vaginalis, A. vaginae, and Megasphaera phylotypes 1 and 2 as the organisms for which quantification provided the most accurate diagnosis of symptomatic BV, as defined by Amsel's criteria and Nugent scoring, with 92% sensitivity, 95% specificity, 94% positive predictive value, and 94% negative predictive value. The inclusion of Lactobacillus spp. did not contribute sufficiently to the quantitative model for symptomatic BV detection. This molecular assay is a highly accurate laboratory tool to assist in the diagnosis of symptomatic BV.