Diagnostic accuracy of a three-gene Mycobacterium tuberculosis host response cartridge using fingerstick blood for childhood tuberculosis: a multicentre prospective study in low-income and middle-income countries

Abstract

Background: Childhood tuberculosis remains a major cause of morbidity and mortality in part due to missed diagnosis. Diagnostic methods with enhanced sensitivity using easy-to-obtain specimens are needed. We aimed to assess the diagnostic accuracy of the Cepheid Mycobacterium tuberculosis Host Response prototype cartridge (MTB-HR), a candidate test measuring a three-gene transcriptomic signature from fingerstick blood, in children with presumptive tuberculosis disease.

Methods: RaPaed-TB was a prospective diagnostic accuracy study conducted at four sites in African countries (Malawi, Mozambique, South Africa, and Tanzania) and one site in India. Children younger than 15 years with presumptive pulmonary or extrapulmonary tuberculosis were enrolled between Jan 21, 2019, and June 30, 2021. MTB-HR was performed at baseline and at 1 month in all children and was repeated at 3 months and 6 months in children on tuberculosis treatment. Accuracy was compared with tuberculosis status based on standardised microbiological, radiological, and clinical data.

Findings: 5313 potentially eligible children were screened, of whom 975 were eligible. 784 children had MTB-HR test results, of whom 639 had a diagnostic classification and were included in the analysis. MTB-HR differentiated children with culture-confirmed tuberculosis from those with unlikely tuberculosis with a sensitivity of 59·8% (95% CI 50·8-68·4). Using any microbiological confirmation (culture, Xpert MTB/RIF Ultra, or both), sensitivity was 41·6% (34·7-48·7), and using a composite clinical reference standard, sensitivity was 29·6% (25·4-34·2). Specificity for all three reference standards was 90·3% (95% CI 85·5-94·0). Performance was similar in different age groups and by malnutrition status. Among children living with HIV, accuracy against the strict reference standard tended to be lower (sensitivity 50·0%, 15·7-84·3) compared with those without HIV (61·0%, 51·6-69·9), although the difference did not reach statistical significance. Combining baseline MTB-HR result with one Ultra result identified 71·2% of children with microbiologically confirmed tuberculosis.

Interpretation: MTB-HR showed promising diagnostic accuracy for culture-confirmed tuberculosis in this large, geographically diverse, paediatric cohort and hard-to-diagnose subgroups.

Funding: European and Developing Countries Clinical Trials Partnership, UK Medical Research Council, Swedish International Development Cooperation Agency, Bundesministerium für Bildung und Forschung; German Center for Infection Research (DZIF).

Figure 1

Flow diagram of participants in RaPaed-TB Definitions of clinical case classification are presented in the appendix (p 3). All children with defined clinical case definition were included in the analysis. Of those excluded, most had an unclear clinical trajectory (ie, were lost to follow-up). MTB-HR=Cepheid Mycobacterium tuberculosis Host Response prototype cartridge.

Figure 2

MTB-HR TB-score distribution of participants classified as having confirmed tuberculosis or unlikely tuberculosis by SRS, MRS, or CRS (A) Raincloud plots show the distribution of the TB-score for the SRS (top panel), MRS (middle panel), and CRS (bottom panel). The bars indicate the 10–90% percentile, and the box indicates the median and IQR. The points are individual data points and show the spread. The data are displayed stratified by whether the sample was prospective or biobanked (before recentring), but the statistical test was conducted on the entire sample, comparing confirmed tuberculosis with unlikely tuberculosis. Data were analysed using Mann-Whitney U tests. (B) AUC for the MTB-HR TB-score of all participants and gene transcripts for the SRS (top panel), MRS (middle panel), and CRS (bottom panel). For the SRS, DeLong tests between TB-score and gene transcripts were: KLF2 p<0·0001, DUSP3 p=0·0018, and GBP5 p=0·53. For the MRS, DeLong tests between TB-score and gene transcripts were: KLF2 p=0·094, DUSP3 p=0·69, and GBP5 p=0·018. For the CRS, DeLong tests between TB-score and gene transcripts were: KLF2 p=0·067, DUSP3 p=0·76, and GBP5 p=0·12. AUC=area under the receiver operating characteristic curve. CRS=clinical reference standard. MRS=microbiological reference standard. MTB-HR=Cepheid Mycobacterium tuberculosis Host Response prototype cartridge. SRS=strict reference standard. TB=tuberculosis.

Figure 3

MTB-HR TB-score to estimate diagnostic accuracy of MTB-HR in subgroups of interest according to the strict reference standard (A) Diagnostic accuracy by age group (n=334). DeLong test between age <1 year and other age groups: 1–5 years p=0·60, 5–10 years p=0·68, >10 years p=0·63. (B) Diagnostic accuracy by HIV status (n=328). DeLong test between HIV negative and HIV positive: p=0·31. (C) Diagnostic accuracy by malnutrition status (n=334). DeLong test between no malnutrition and other malnutrition statuses: severe p=0·15, mild or moderate p=0·052. (D) Diagnostic accuracy by site (n=334). DeLong test between South Africa and other sites: Tanzania p=0·14, Mozambique p=0·92, Malawi p=0·047, India p=0·42. AUC=area under the receiver operating characteristic curve. MTB-HR=Cepheid Mycobacterium tuberculosis Host Response prototype cartridge.