PCR in diagnosis of invasive aspergillosis: a meta-analysis of diagnostic performance

Abstract

Invasive aspergillosis is a difficult-to-diagnose infection with a high mortality rate that affects high-risk groups such as patients with neutropenia and hematologic malignancies. We performed a bivariate meta-analysis of diagnostic data for an Aspergillus sp. PCR assay with blood specimens from high-risk hematology patients. We included all studies involving human subjects that assessed the performance of any PCR assay for invasive aspergillosis in whole blood or serum and that used the European Organization for the treatment of Cancer/Mycoses Study Group criteria as a reference standard. Three investigators independently searched the literature for eligible studies and extracted the data. Out of a total of 37 studies, 25 met strict quality criteria and were included in our evidence synthesis. Twenty-five studies with 2,595 patients were analyzed. The pooled diagnostic performance of whole-blood and serum PCR assays was moderate, with a sensitivity and specificity of 84% (95% confidence interval [CI], 75 to 91%) and 76% (95% CI, 65 to 84%), respectively, suggesting that a positive or negative result is unable, on its own, to confirm or exclude a suspected infection. The performance of a PCR assay of serum was not significantly different from that of whole blood. Notably, at least two positive PCR test results were found to have a specificity of 95% and a sensitivity of 64% for invasive infection, achieving a high positive likelihood ratio of 12.8. Importantly, the European Aspergillus PCR Initiative (EAPCRI) recommendations improved the performance of the PCR even further when at least two positive specimens were used to define PCR positivity. In conclusion, two positive PCR results should be considered highly indicative of an active Aspergillus sp. infection. Use of the EAPCRI recommendations by clinical laboratories can further enhance PCR performance.

FIG 1

Flow diagram of the inclusion criteria used in this study.

FIG 2

Forest plot of independent sensitivity and specificity estimates. The studies cited correspond to references , , to , to , , to , and to .

FIG 3

SROC curve of PCR performance.