Diagnostic test accuracy of Xpert MTB/RIF for tuberculous pericarditis: a systematic review and meta-analysis

Abstract

Introduction: Xpert MTB/RIF is a rapid diagnostic instrument for pulmonary tuberculosis (TB). However, studies reported varied accuracy of Xpert MTB/RIF in detecting Mycobacterium tuberculosis in pericardial effusion. Methods: We performed a systematic review of literature in PubMed, published up to February 1, 2020, according to PRISMA guidelines. We screened cross-sectional studies, observational cohort studies, and randomized control trials that evaluated the accuracy of Xpert MTB/RIF in diagnosing TB pericarditis. Papers with noninterpretable results of sensitivity and specificity, non-English articles, and unpublished studies were excluded. The primary outcomes were the sensitivity and specificity of Xpert MTB/RIF. We conducted a quality assessment using QUADAS-2 to evaluate the quality of the studies. A bivariate model pooled the overall sensitivity, specificity, positive likelihood ratios (PLRs), and negative likelihood ratios (NLRs) of included studies. Results: In total, 581 subjects from nine studies were analyzed in this meta-analysis. Our pooled analysis showed that the overall sensitivity, specificity, PLRs and NLRs of included studies were 0.676 (95% CI: 0.580-0.759), 0.994 (95% CI: 0.919-1.000), 110.11 (95% CI: 7.65-1584.57) and 0.326 (95% CI: 0.246-0.433), respectively. Conclusions: Xpert MTB/RIF had a robust specificity but unsatisfactory sensitivity in diagnosing TB pericarditis. These findings indicated that although positive Xpert MTB/RIF test results might be valuable in swiftly distinguishing the diagnosis of TB pericarditis, negative test results might not be able to rule out TB pericarditis. Registration: PROSPERO CRD42020167480 28/04/2020.

Keywords: Extrapulmonary TBC; PCR; Pericardial Effusion; Xpert MTB/RIF.

Figure 1.. Flow diagram of the research collection.

Figure 2.. The author's review of each domain of risk of bias and applicability concerns are presented as a percentage of all the studies included.

Figure 3.. The author's review of each domain of risk of bias and applicability concerns for each included study.

Figure 4.. The approximated sensitivity and specificity of each of the included studies are plotted in forest plots.

TP, true positive; FP, false positive; FN, false negative; TN, true negative.

Figure 5.. sROC for Xpert MTB/RIF.

The black curve describes a pattern that considers culture as the perfect reference standard. The cleared circles outlined on several coordinates represent the estimated sensitivity and specificity of each of the included studies, and the black circle is a pooled estimate of sensitivity and specificity achieved from the bivariate model. sROC, summary receiver operating characteristic; HRSOC, hierarchal summary receiver operating characteristic.