Assessment of recent HIV-1 infection by a line immunoassay for HIV-1/2 confirmation

Abstract

Background: Knowledge of the number of recent HIV infections is important for epidemiologic surveillance. Over the past decade approaches have been developed to estimate this number by testing HIV-seropositive specimens with assays that discriminate the lower concentration and avidity of HIV antibodies in early infection. We have investigated whether this "recency" information can also be gained from an HIV confirmatory assay.

Methods and findings: The ability of a line immunoassay (INNO-LIA HIV I/II Score, Innogenetics) to distinguish recent from older HIV-1 infection was evaluated in comparison with the Calypte HIV-1 BED Incidence enzyme immunoassay (BED-EIA). Both tests were conducted prospectively in all HIV infections newly diagnosed in Switzerland from July 2005 to June 2006. Clinical and laboratory information indicative of recent or older infection was obtained from physicians at the time of HIV diagnosis and used as the reference standard. BED-EIA and various recency algorithms utilizing the antibody reaction to INNO-LIA's five HIV-1 antigen bands were evaluated by logistic regression analysis. A total of 765 HIV-1 infections, 748 (97.8%) with complete test results, were newly diagnosed during the study. A negative or indeterminate HIV antibody assay at diagnosis, symptoms of primary HIV infection, or a negative HIV test during the past 12 mo classified 195 infections (26.1%) as recent (< or = 12 mo). Symptoms of CDC stages B or C classified 161 infections as older (21.5%), and 392 patients with no symptoms remained unclassified. BED-EIA ruled 65% of the 195 recent infections as recent and 80% of the 161 older infections as older. Two INNO-LIA algorithms showed 50% and 40% sensitivity combined with 95% and 99% specificity, respectively. Estimation of recent infection in the entire study population, based on actual results of the three tests and adjusted for a test's sensitivity and specificity, yielded 37% for BED-EIA compared to 35% and 33% for the two INNO-LIA algorithms. Window-based estimation with BED-EIA yielded 41% (95% confidence interval 36%-46%).

Conclusions: Recency information can be extracted from INNO-LIA-based confirmatory testing at no additional costs. This method should improve epidemiologic surveillance in countries that routinely use INNO-LIA for HIV confirmation.

Figure 1. Antibody Reaction as Assessed by the INNO-LIA in Different Groups of Newly Diagnosed HIV-1 Patients

(A) Sum of antibody scores to env antigens sgp120 and gp41 (top graph), gag antigens p24 and p17 (middle graph) and pol antigen p31 (bottom graph); bars represent means and error bars their 95% confidence intervals. Reaction is stratified according to recency definitions 1, 2, or 3 and other reported staging information (see Methods). (B) Correct order of recency definitions based on increasing antibody development. Box plots show sum of antibody scores to all five HIV-1 antigen bands. Boxes indicate the median and the 25th and 75th percentile. Horizontal lines located outside of, but closest to the boxes represent the 10th and 90th percentile, respectively. Outliers are plotted individually. The medians of the groups consisting of infections not classified coincide with the 75th percentile (upper limit of box). p-Values on top denote differences between subgroups of recent infections.