Improvement of Mycobacterium tuberculosis detection by Xpert MTB/RIF Ultra: A head-to-head comparison on Xpert-negative samples

Background The new Xpert MTB/RIF Ultra assay (Ultra, Cepheid, Sunnyvale, USA) is a cartridge-based automated diagnostic test that can simultaneously identify Mycobacterium tuberculosis complex (MTB) and resistance to Rifampicin (RIF). With respect to the previous version Xpert MTB/RIF assay (Xpert), IS6110/1S1081 repetitive elements probes have been added allowing the detection of lower MTB load, defined by the new semi-quantitative category "trace" with indeterminate RIF resistance. The aim of this study was to evaluate performance of the new version Ultra on Xpert-negative, but TB culture-positive clinical samples. Methods The de-identified frozen samples (-20 degrees C) collected over a 4-year period (February 2014-October 2017), which had previously resulted smear-negative, Xpert-negative but MTB culture-positive, were analyzed with Ultra. The de-frosted samples were loaded into the cartridge using the same process as the previous version, according to manufacturer's instruction. Results During the study period 382 MTB culture-positive samples were archived: 314 resulted Xpert-positive and 68 Xpert-negative. Thirty-one of the 68 Xpert-negative samples resulted positive with Ultra, with an overall improvement in MTB detection of 45.6%. Out of 36 Xpert-negative respiratory samples, 18 resulted Ultra-positive with the following semi-quantitative loads: "low"(n = 1), "very low"(n = 11), "trace"(n = 6), with an improvement in MTB detection of 50%. The best performance was achieved on bronchoalveolar lavage specimens (53.8%). Out of 32 Xpert-negative non-respiratory samples, 13 resulted Ultra-positive with the following semi-quantitative loads: "very low"(n = 7), "trace"(n = 6), with an improvement in MTB detection of 40.6%. The best performance was achieved on biopsies (55.6%) and lymph nodes (50%). The new category "trace" detected 12 out of the 31 Ultra-positive MTB samples; in the remaining 19 samples RIF susceptibility was determined with 100% concordance with the phenotypic susceptibility test. The mean time to positivity of samples found negative by Ultra was significantly longer in comparison to positive samples in liquid culture. Conclusions Our results are consistent with the few studies published so far and confirm the better performance of Ultra compared to the previous version in both respiratory and non-respiratory smear-negative samples, with an overall improvement of 45.6%.