Diagnostic Accuracy Study of a Novel Blood-Based Assay for Identification of Tuberculosis in People Living with HIV

A nonsputum triage test to rule out tuberculosis (TB) disease is a WHO high-priority diagnostic, and a combinatory score based on a 3-gene host signature has shown promise in discriminating TB from other illnesses. We evaluated the accuracy of an early-prototype cartridge assay ("Xpert MTB Host Response" or Xpert-MTB-HR-Prototype) of this 3-gene signature on biobanked blood samples from people living with HIV (PLHIV) against a comprehensive microbiological reference standard (CMRS) and against Xpert MTB/RIF on the first sputum sample alone. We depict results based on performance targets set by the WHO in comparison with a laboratory-based C-reactive protein (CRP) assay. Of 201 patients included, 67 were culture positive for Mycobacterium tuberculosis. The areas under the concentration-time curve (AUCs) for Xpert-MTB-HR-Prototype were 0.89 (confidence interval [CI], 0.83 to 0.94) against the CMRS and 0.94 (CI, 0.89 to 0.98) against Xpert MTB/RIF. Considering Xpert-MTB-HR-Prototype as a triage test (at the nearest upper value of sensitivity to 90%), specificities were 55.8% (CI, 47.2 to 64.1%) compared to the CMRS and 85.9% (CI, 79.3 to 90.7%) compared to Xpert MTB/RIF as confirmatory tests. Considering Xpert-MTB-HR-Prototype as a stand-alone diagnostic test, at a specificity near 95%, the test achieved a sensitivity of 65.7% (CI, 53.7 to 75.9%), while the CRP assay achieved a sensitivity of only 13.6% (CI, 7.3 to 23.4%). In this first accuracy study of a prototype blood-based host marker assay, we show the possible value of the assay for triage and diagnosis in PLHIV.