Optimal Detection of Latent Mycobacterium tuberculosis Infection by Combined Heparin-Binding Hemagglutinin (HBHA) and Early Secreted Antigenic Target 6 (ESAT-6) Whole-Blood Interferon Gamma Release Assays

Abstract

Optimal detection of latent tuberculosis (TB) infection (LTBI) remains a challenge, although it is essential to reach the goal of TB elimination. Our objective was to develop and clinically evaluate a user-friendly, 24-h, whole-blood (WB) interferon gamma (IFN-γ) release assay (IGRA) improving the detection of LTBI, compared to available tests. One milliliter of blood was divided into four aliquots and in vitro stimulated for 24 h with two different stage-specific mycobacterial antigens, i.e., heparin-binding hemagglutinin (HBHA) and early secreted antigenic target 6 (ESAT-6), a latency-associated antigen and a bacterial replication-related antigen, respectively, in addition to positive and negative controls. Clinical evaluation was performed on two independent cohorts of carefully selected subjects, i.e., a training cohort of 83 individuals and a validation cohort of 69 individuals. Both cohorts comprised LTBI subjects (asymptomatic people with a positive tuberculin skin test result and potential exposure to TB index cases), patients with active TB (aTB), and noninfected controls. The sensitivity and specificity of the WB-HBHA-IGRA to identify LTBI subjects among asymptomatic individuals were 93%. Combining the results in response to HBHA and ESAT-6 allowed us to identify LTBI subgroups. One group, with IFN-γ responses to HBHA only, was easily differentiated from patients with aTB. The other group, responding to both antigens like the aTB group, is likely at risk to reactivate the infection and should be prioritized for prophylactic anti-TB treatment. The combined WB-IGRA may be offered to clinicians for the selection of LTBI subjects to benefit from prophylactic treatment.

Keywords: early secreted antigenic target 6; heparin-binding hemagglutinin; interferon gamma release assay; latent tuberculosis infection; whole blood.

FIG 1

STARD diagram reporting the flow of asymptomatic subjects and aTB patients for evaluation of the HBHA-WB-IGRA to identify LTBI subjects. The WB-HBHA-IGRA was compared to the TST reference recommended in Belgium for LTBI detection, to the QFT, and to the PBMC-HBHA-IGRA. The four tests were performed on noninfected controls (CTRL) and LTBI subjects included in the training cohort (A) and the validation cohort (B). Controls and LTBI subjects who were positive and negative, respectively, with an PPD-IGRA were excluded from the analysis. The criteria for positive TST results were according to the CDC guidelines, and those for positive QFT results were according to the manufacturer’s instructions; for the HBHA-IGRA, positivity was considered when the IFN-γ responses were above the lower value of the gray zone for the defined cutoff value. aTB patients were included for differential diagnosis, and only those with a confirmed diagnosis were retained for the final analysis. *, TST was not done for 21 subjects; **, QFT was not done for 23 subjects; #, 1 indeterminate result.

FIG 2

Correlations between the WB-IGRA and the PBMC-IGRA performed with HBHA or ESAT-6. PBMC or 2-fold diluted WB from the subjects of the training cohort (A and C) and the validation cohort (B and D) was stimulated for 24 h with 2 μg/mL HBHA for the PBMC-IGRA or 4 μg/mL HBHA for the WB-IGRA (A and B) or with 5 μg/mL ESAT-6 (C and D) before supernatant collection and IFN-γ concentration measurements. The IFN-γ concentrations obtained for the WB-IGRA and the PBMC-IGRA are represented as gray squares for noninfected controls, white diamonds for LTBI subjects, and black triangles for aTB patients. The Spearman’s rank correlation coefficients are indicated. The gray lines represent the gray zones corresponding to 20% variability around the cutoff values.

FIG 3

WB-HBHA-IGRA and WB-ESAT-6-IGRA results according to M. tuberculosis infection status. Twofold-diluted WB from the subjects in the training cohort (A and C) and the validation cohort (B and D) was stimulated for 24 h with 4 μg/mL HBHA (A and B) or 5 μg/mL ESAT-6 (C and D) before supernatant collection and IFN-γ concentration measurements. The IFN-γ concentrations obtained for the WB-IGRA are shown for noninfected controls (CTRL), LTBI subjects (LTBI), and aTB patients (aTB). The gray lines represent the gray zones corresponding to 20% variability around the cutoff values. For each group, the horizontal line represents the median of the results. *, P < 0.05; **, P < 0.01; ***, P < 0.001; ****, P < 0.0001.

FIG 4

Correlations of the WB-HBHA-IGRA and WB-ESAT-6-IGRA results for LTBI subjects and aTB patients. Twofold-diluted WB from the subjects in the training cohort (A and C) and the validation cohort (B and D) was stimulated for 24 h with 4 μg/mL HBHA or 5 μg/mL ESAT-6 before supernatant collection and IFN-γ concentration measurements. The IFN-γ concentrations obtained with the WB-HBHA-IGRA and the WB-ESAT-6-IGRA are shown for LTBI subjects (A and B) and aTB patients (C and D). Patients with aTB had either pulmonary (black circles) or extrapulmonary (white circles) TB. The Spearman’s rank correlation coefficients are indicated. The gray lines represent the gray zones corresponding to 20% variability around the cutoff values.