Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey.
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 ima...
Main Authors: | , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2022-01-01
|
Series: | PLOS Global Public Health |
Online Access: | https://doi.org/10.1371/journal.pgph.0001272 |
_version_ | 1797696213088206848 |
---|---|
author | Brenda Mungai Jane Ong'angò Chu Chang Ku Marc Y R Henrion Ben Morton Elizabeth Joekes Elizabeth Onyango Richard Kiplimo Dickson Kirathe Enos Masini Joseph Sitienei Veronica Manduku Beatrice Mugi Stephen Bertel Squire Peter MacPherson IMPALA Consortium |
author_facet | Brenda Mungai Jane Ong'angò Chu Chang Ku Marc Y R Henrion Ben Morton Elizabeth Joekes Elizabeth Onyango Richard Kiplimo Dickson Kirathe Enos Masini Joseph Sitienei Veronica Manduku Beatrice Mugi Stephen Bertel Squire Peter MacPherson IMPALA Consortium |
author_sort | Brenda Mungai |
collection | DOAJ |
description | 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<0.0001). CAD4TBv6 met the optimum TPP; with the threshold set to achieve a mean sensitivity of 95% (optimum TPP), specificity was 83.3%, (95% credible interval [CrI]: 83.0%-83.7%, CAD4TBv6 threshold: 55). There was considerable variation in accuracy by participant characteristics, with older individuals and those with previous TB having lowest specificity. CAD4TBv6 met the optimal TPP for TB community screening. To optimise screening accuracy and efficiency of confirmatory sputum testing, we recommend that an adaptive approach to threshold setting is adopted based on participant characteristics. |
first_indexed | 2024-03-12T03:23:15Z |
format | Article |
id | doaj.art-99e9752e8c614435bacb5e54f90ee0cb |
institution | Directory Open Access Journal |
issn | 2767-3375 |
language | English |
last_indexed | 2024-03-12T03:23:15Z |
publishDate | 2022-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLOS Global Public Health |
spelling | doaj.art-99e9752e8c614435bacb5e54f90ee0cb2023-09-03T13:45:09ZengPublic Library of Science (PLoS)PLOS Global Public Health2767-33752022-01-01211e000127210.1371/journal.pgph.0001272Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey.Brenda MungaiJane Ong'angòChu Chang KuMarc Y R HenrionBen MortonElizabeth JoekesElizabeth OnyangoRichard KiplimoDickson KiratheEnos MasiniJoseph SitieneiVeronica MandukuBeatrice MugiStephen Bertel SquirePeter MacPhersonIMPALA ConsortiumCommunity-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<0.0001). CAD4TBv6 met the optimum TPP; with the threshold set to achieve a mean sensitivity of 95% (optimum TPP), specificity was 83.3%, (95% credible interval [CrI]: 83.0%-83.7%, CAD4TBv6 threshold: 55). There was considerable variation in accuracy by participant characteristics, with older individuals and those with previous TB having lowest specificity. CAD4TBv6 met the optimal TPP for TB community screening. To optimise screening accuracy and efficiency of confirmatory sputum testing, we recommend that an adaptive approach to threshold setting is adopted based on participant characteristics.https://doi.org/10.1371/journal.pgph.0001272 |
spellingShingle | Brenda Mungai Jane Ong'angò Chu Chang Ku Marc Y R Henrion Ben Morton Elizabeth Joekes Elizabeth Onyango Richard Kiplimo Dickson Kirathe Enos Masini Joseph Sitienei Veronica Manduku Beatrice Mugi Stephen Bertel Squire Peter MacPherson IMPALA Consortium Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. PLOS Global Public Health |
title | Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. |
title_full | Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. |
title_fullStr | Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. |
title_full_unstemmed | Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. |
title_short | Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey. |
title_sort | accuracy of computer aided chest x ray in community based tuberculosis screening lessons from the 2016 kenya national tuberculosis prevalence survey |
url | https://doi.org/10.1371/journal.pgph.0001272 |
work_keys_str_mv | AT brendamungai accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT janeongango accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT chuchangku accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT marcyrhenrion accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT benmorton accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT elizabethjoekes accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT elizabethonyango accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT richardkiplimo accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT dicksonkirathe accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT enosmasini accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT josephsitienei accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT veronicamanduku accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT beatricemugi accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT stephenbertelsquire accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT petermacpherson accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey AT impalaconsortium accuracyofcomputeraidedchestxrayincommunitybasedtuberculosisscreeninglessonsfromthe2016kenyanationaltuberculosisprevalencesurvey |