Accuracy of computer-aided chest X-ray in community-based tuberculosis screening

Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey

Dados Bibliográficos

ID19593657
AutoresBrenda Mungai (0000-0001-7337-3607, Liverpool School of Tropical Medicine, autor correspondente), Jane Rahedi Ong’ang’o (0000-0001-5481-8447, Kenya Medical Research Institute), Jane Ong‘angò, Chu Chang Ku (0000-0002-4719-117X, Imperial College London), Marc Y R Henrion (0000-0003-1242-839X, University of Liverpool), Ben Morton (0000-0002-6164-2854, University of Liverpool), Elizabeth Joekes (Liverpool School of Tropical Medicine), Elizabeth Onyango (0000-0003-1322-6554), Richard Kiplimo (0000-0002-7319-0410), Dickson Kirathe (0000-0003-4417-5278), Enos Masini (0000-0001-7522-5528, Global Fund to Fight AIDS, Tuberculosis and Malaria), Joseph Sitienei (0000-0001-9140-4630), Veronica Manduku (0000-0003-2488-9900, Kenya Medical Research Institute), Beatrice Mugi (0000-0002-9165-5904, Kenyatta National Hospital), Bertel Squire (0000-0001-7173-9038), Stephen Bertel Squire (University of Liverpool), Peter MacPherson (0000-0002-0329-9613, University of Liverpool)
EditoresMajumdar (0000-0002-9656-557X), Suman Majumdar (0000-0001-5948-6920)
Ano2022
Volume2
Fascículo11
Páginase0001272
Data de publicação2022-11-23
Peer ReviewedSim
Open AccessSim
TipoARTICLE
PeriódicoPLOS Global Public Health (JOURNAL)
Identificadores do periódicoISSN: 2767-3375 • E-ISSN: 2767-3375
EditoraPublic Library of Science (PLoS) (PUBLISHER)
DOI10.1371/journal.pgph.0001272
PMID36962655
OpenAlexW4309796546
IdiomaEN
Citações recebidas6
Referências citadas15

Community-based screening for tuberculosis (TB) could improve detection but is resource intensive. We set out to evaluate the accuracy of computer-aided TB screening using digital chest X-ray (CXR) to determine if this approach met target product profiles (TPP) for community-based screening. CXR images from participants in the 2016 Kenya National TB Prevalence Survey were evaluated using CAD4TBv6 (Delft Imaging), giving a probabilistic score for pulmonary TB ranging from 0 (low probability) to 99 (high probability). We constructed a Bayesian latent class model to estimate the accuracy of CAD4TBv6 screening compared to bacteriologically-confirmed TB across CAD4TBv6 threshold cut-offs, incorporating data on Clinical Officer CXR interpretation, participant demographics (age, sex, TB symptoms, previous TB history), and sputum results. We compared model-estimated sensitivity and specificity of CAD4TBv6 to optimum and minimum TPPs. Of 63,050 prevalence survey participants, 61,848 (98%) had analysable CXR images, and 8,966 (14.5%) underwent sputum bacteriological testing; 298 had bacteriologically-confirmed pulmonary TB. Median CAD4TBv6 scores for participants with bacteriologically-confirmed TB were significantly higher (72, IQR: 58–82.75) compared to participants with bacteriologically-negative sputum results (49, IQR: 44–57, p

Confidence interval · Credible interval · Demographics · Pathology · Pulmonary tuberculosis · Sputum · Tuberculosis · COVID-19 diagnosis using AI · Demography · Medicine · Mycobacterium research and diagnosis · Tuberculosis Research and Epidemiology · Internal Medicine