Universal Newborn Screening for Congenital Cytomegalovirus Infection - From Infant to Maternal Infection: A Prospective Multicenter Study

Abstract

Introduction: Most infants at risk for cytomegalovirus (CMV)-associated sensorineural hearing loss (SNHL) are unrecognized because of the absence of a universal neonatal CMV screening. The search of CMV-DNA by molecular methods in salivary swabs was demonstrated to be a reliable approach. This study describes the results obtained by carrying out a universal screening for congenital CMV (cCMV) infection including all live-born newborns in three Italian sites, as well as the therapeutic interventions and clinical outcome of the CMV-infected neonates. Moreover, CMV maternal infection's characteristics were evaluated.

Methods: To confirm or exclude cCMV infection, a CMV-DNA-positive result on a first salivary swab was followed by repeated saliva and urine samples collected within 21 days of age. Breast milk samples were also collected. The search of CMV-DNA was performed with a single automated quantitative commercial real-time PCR assay, regardless of the type of samples used.

Results: A total of 3,151 newborns were enrolled; 21 (0.66%) of them were congenitally infected (median saliva viral load at screening, 6.65 [range, 5.03-7.17] log₁₀ IU/ml). Very low/low viral load in screening saliva samples (median value, 1.87 [range, 1.14-2.59] log₁₀ IU/ml) was associated with false-positive results (n = 54; 1.7%). CMV-DNA was detected in almost half of the breast milk samples of mother-infant pairs with a false-positive result, suggesting that contamination from breast milk may not be the only explanation in the study population. cCMV infection confirmation with the search of CMV-DNA in a urine sample proved to be the gold standard strategy, since false-positive results were observed in 4/54 (7.5%) of the repeated saliva samples. Symptomatic cCMV infection was observed in 3/21 (14.3%) infants; notably, one (4.7%) developed moderate unilateral SNHL at 5 months after birth. Finally, two symptomatic cCMV infections were associated with primary maternal infection acquired in the first trimester of gestation; one newborn with severe cCMV symptoms was born to a mother with no CMV checkups in pregnancy.

Conclusion: Without universal neonatal CMV screening, some infected infants who develop late neurological sequelae may not be recognized and, consequently, they are not able to benefit early from instrumental and therapeutic interventions to limit and/or treat CMV disease.

Keywords: CMV maternal infection; congenital CMV infection; false positive results; levels of CMV-DNA; salivary swabs; universal newborn screening.

Figure 1

Flowchart of the neonatal congenital CMV (cCMV) screening and the algorithm used for the diagnosis of infection.

Figure 2

Distribution plot of CMV-DNA load in the 75 (2.3%) positive saliva screening samples. The remaining 3,076 (97.6%) samples were found to be CMV-DNA negative at screening.

Figure 3

Graphical representation of the results obtained by confirmatory testing. CMV-DNA loads were expressed as log₁₀ IU/ml (median value, [range]).

Figure 4

Viral loads detected in screening saliva samples from infants with and without cCMV infection.