Accuracy of Computer-Aided Detection for Tuberculosis® on paediatric chest radiographs

Edem, Victory, Nkereuwem, Esin, Agbla, Schadrac, Owusu, Sheila, Sillah, Abdou, Saidy, Binta, Jallow, Musa, Forson, Audrey, Egere, Uzochukwu ORCID: https://orcid.org/0000-0002-0282-6004, Kampmann, Beate and Togun, Toyin (2024) 'Accuracy of Computer-Aided Detection for Tuberculosis® on paediatric chest radiographs'. European Respiratory Journal. (In Press)

Text Accuracy of Computer-Aided Detection of TB on Paed Chest X rays_July2024.pdf - Accepted Version Restricted to Repository staff only until 3 September 2025. Download (1MB)

Abstract

Computer-aided detection (CAD) systems hold promise for improving tuberculosis (TB) detection on digital chest x-rays (dCXR). However, data on their performance in exclusively paediatric populations are scarce. We conducted a retrospective diagnostic accuracy study evaluating the performance of CAD for TB version 7 (CAD4TBv7®) using dCXR from well-characterised cohorts of Gambian children younger than 15 years with presumed pulmonary TB. The children were consecutively recruited between 2012 and 2022. We measured CAD4TBv7 performance against a microbiological reference standard (MRS) of confirmed TB, and also performed Bayesian latent class analysis (LCA) to address the inherent limitations of MRS in children. Diagnostic performance was assessed using the area under the receiver operating characteristic curve (AUROC) and point estimates of sensitivity and specificity. A total of 724 children were included in the analysis, with confirmed TB in 58 (8%), unconfirmed TB in 145 (20%), and unlikely TB in 521 (72%). Using MRS, CAD4TBv7 showed an AUROC of 0.70 (95% CI 0.60-0.79), and demonstrated sensitivity and specificity of 19.0% (95% CI 11-31%) and 99.0% (95% CI 98.0-100.0%), respectively. Applying Bayesian LCA with assumption of conditional independence between tests, sensitivity and specificity estimates for CAD4TBv7 were 42.7% (95% CrI 29.2-57.5%) and 97.9% (95% CrI 96.6-98.8%), respectively. When allowing for conditional dependence between culture and Xpert assay, CAD4TBv7 demonstrated a sensitivity of 50.3% (95% CrI 32.9-70.0%) and specificity of 98.0% (95% CrI 96.7-98.9%). Although CAD4TBv7 demonstrated high specificity, its suboptimal sensitivity underscores the crucial need for optimisation of the CAD4TBv7 for detecting tuberculosis in children.

Item Type:	Article
Subjects:	WF Respiratory System > Tuberculosis > WF 200 Tuberculosis (General) WF Respiratory System > Tuberculosis > WF 220 Diagnosis. Prognosis WF Respiratory System > Tuberculosis > WF 225 Mass chest X-ray WF Respiratory System > Tuberculosis > WF 415 Tuberculosis in childhood
Faculty: Department:	Clinical Sciences & International Health > International Public Health Department
Digital Object Identifer (DOI):	https://doi.org/10.1183/13993003.00811-2024
Depositing User:	Rachel Dominguez
Date Deposited:	18 Sep 2024 13:45
Last Modified:	18 Sep 2024 13:45
URI:	https://archive.lstmed.ac.uk/id/eprint/25000

Statistics

View details

Actions (login required)

Edit Item