Approaches and processes for paediatric chest X-ray classification used in the SHINE TB treatment-shortening trial

INTRODUCTION SHINE (Shorter Treatment for Minimal Tuberculosis in Children) was the first Phase 3 paediatric TB treatment-shortening trial. Robust chest X-ray (CXR) classification methods were integral to excluding severe disease for trial eligibility and to retrospectively adjudicating TB status at baseline. We describe and critically evaluate the CXR classification approaches and processes used in the SHINE trial. METHODS Children with non-severe TB were randomised to 4- vs 6-months anti-TB treatment. Radiologically non-severe TB was defined on CXR. CXRs were systematically interpreted by on-site clinicians prospectively for eligibility determination and retrospectively by experts to inform adjudication of baseline TB status and disease severity. RESULTS A screening CXR was successfully obtained from all 1,204 enrolled children; 1,134 CXRs from children with intra-thoracic TB were reviewed by expert readers. Compared with the expert panel, enrolling clinicians classified more CXRs as abnormal and 'typical TB' and all as radiologically non-severe. The expert panel retrospectively classified 71/1,134 (6%) CXRs as severe. Of these, 4 (5.6%) had unfavourable outcomes compared with 34 (3.0%) in the trial overall. DISCUSSION Using CXRs to classify radiological disease severity and inform eligibility decisions in real-time by local enrolling clinicians was feasible and safe in this large paediatric TB trial. Retrospective central expert CXR review was successful. Refinement of the CXR methods for the classification of both disease severity and TB status could support standardised implementation in routine care and research.