Diagnostic accuracy, feasibility and acceptability of stool-based testing for childhood tuberculosis

Background Childhood tuberculosis (TB) diagnosis remains challenging, partly because children cannot provide sputum. This study evaluated the diagnostic accuracy of the Simple One-Step (SOS) stool method with Xpert MTB/RIF Ultra (Xpert-Ultra) for childhood TB compared to culture and Xpert-Ultra on a respiratory sample (RS) and clinical diagnosis. It also assessed the feasibility and acceptability of stool testing according to laboratory staff, and caregivers' sample preference. Methods We enrolled children (<= 10 years) with presumptive pulmonary tuberculosis in Ethiopia. RS was tested using Xpert-Ultra and culture; stool samples were tested using the SOS stool method with XpertUltra. Laboratory staff and caregivers' opinions were assessed using standardised questionnaires. Results Of the 898 children enrolled, 792, 832 and 794 were included for assessing the diagnostic accuracy of SOS stool with Xpert-Ultra against culture, RS Xpert-Ultra and clinical diagnosis, respectively, yielding sensitivity estimates for SOS stool with Xpert-Ultra of 69.1% (95% confidence interval (CI) 56.079.7%), 76.8% (95% CI 64.2-85.9%) and 59.0% (95% CI 47.9-69.2%), respectively. The specificity was >= 98.8% for all comparisons. The rate of non-determinate test results was 2.8% after one repeat test. According to laboratory staff, stool collection was feasible and acceptable and the SOS stool method was easy to perform. Most caregivers (75%) preferred stool for TB diagnosis over RS. Conclusion This study shows that SOS stool Xpert-Ultra testing offers a good alternative to RS testing for TB in children who cannot spontaneously produce a sputum sample and would otherwise need to undergo invasive procedures to obtain RS for diagnosis.