Active case finding to detect symptomatic and subclinical pulmonary tuberculosis disease: implementation of computer-aided detection for chest radiography in Viet Nam.

Abstract

Objective: In Viet Nam, tuberculosis (TB) prevalence surveys revealed that approximately 98% of individuals with pulmonary TB have TB-presumptive abnormalities on chest radiographs, while 32% have no TB symptoms. This prompted the adoption of the "Double X" strategy, which combines chest radiographs and computer-aided detection with GeneXpert testing to screen for and diagnose TB among vulnerable populations. The aim of this study was to describe demographic, clinical and radiographic characteristics of symptomatic and asymptomatic Double X participants and to assess multilabel radiographic abnormalities on chest radiographs, interpreted by computer-aided detection software, as a possible tool for detecting TB-presumptive abnormalities, particularly for subclinical TB.

Methods: Double X participants with TB-presumptive chest radiographs and/or TB symptoms and known risks were referred for confirmatory GeneXpert testing. The demographic and clinical characteristics of all Double X participants and the subset with confirmed TB were summarized. Univariate and multivariable logistic regression modelling was used to evaluate associations between participant characteristics and subclinical TB and between computer-aided detection multilabel radiographic abnormalities and TB.

Results: From 2020 to 2022, 96 631 participants received chest radiographs, with 67 881 (70.2%) reporting no TB symptoms. Among 1144 individuals with Xpert-confirmed TB, 51.0% were subclinical. Subclinical TB prevalence was higher in older age groups, non-smokers, those previously treated for TB and the northern region. Among 11 computer-aided detection multilabel radiographic abnormalities, fibrosis was associated with higher odds of subclinical TB.

Discussion: In Viet Nam, Double X community case finding detected pulmonary TB, including subclinical TB. Computer-aided detection software may have the potential to identify subclinical TB on chest radiographs by classifying multilabel radiographic abnormalities, but further research is needed.