Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey

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

doi:10.1371/journal.pgph.0001272

Accuracy of computer-aided chest X-ray in community-based tuberculosis screening: Lessons from the 2016 Kenya National Tuberculosis Prevalence Survey

PLOS Glob Public Health. 2022 Nov 23;2(11):e0001272. doi: 10.1371/journal.pgph.0001272. eCollection 2022.

Authors

Brenda Mungai^{1

2

3}, Jane Ong'angò⁴, Chu Chang Ku⁵, Marc Y R Henrion^{1

6}, Ben Morton^{1

7}, Elizabeth Joekes^{1

8}, Elizabeth Onyango⁹, Richard Kiplimo⁹, Dickson Kirathe⁹, Enos Masini^{10

11}, Joseph Sitienei⁹, Veronica Manduku⁴, Beatrice Mugi¹², Stephen Bertel Squire^{1

13}, Peter MacPherson^{1

6

14}; IMPALA Consortium

Affiliations

¹ Department of Clinical Sciences, Liverpool School of Tropical Medicine, Liverpool, United Kingdom.
² African Institute for Development Policy, Nairobi, Kenya.
³ Centre for Health Solutions, Nairobi, Kenya.
⁴ Kenya Medical Research Institute (KEMRI), Nairobi, Kenya.
⁵ Department of Infectious Disease Epidemiology, Imperial College London, London, United Kingdom.
⁶ Malawi-Liverpool-Wellcome Trust Clinical Research Programme, Blantyre, Malawi.
⁷ Critical Care Department, Liverpool University Hospitals NHS Foundation Trust, Liverpool, United Kingdom.
⁸ Worldwide Radiology, Liverpool, United Kingdom.
⁹ Division of National Tuberculosis, Leprosy and Lung Disease Program, Nairobi, Kenya.
¹⁰ The Global Fund to Fight AIDS, Tuberculosis and Malaria, Geneva, Switzerland.
¹¹ Stop TB Partnership, Le Grand-Saconnex, Switzerland.
¹² Kenyatta National Hospital, Nairobi, Kenya.
¹³ Tropical & Infectious Diseases Unit, Liverpool University Hospitals NHS Foundation Trust, Liverpool, United Kingdom.
¹⁴ Clinical Research Department, London School of Hygiene and Tropical Medicine, Liverpool, United Kingdom.

Abstract

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.

Copyright: © 2022 Mungai et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Grants and funding

This research was funded by the National Institute for Health Research (NIHR) (IMPALA, grant reference 16/136/35) using UK aid from the UK Government to support global health research to SBS. SBS was Director of the IMPALA Global Health Research Unit at the time of this work and BNM was a PhD candidate funded through IMPALA. PM was funded by Wellcome (200901/Z/16/Z). MYRH was in part supported by a strategic award from Wellcome to Malawi-Liverpool-Wellcome Trust Clinical Research programme (206545/Z/17/Z). The views expressed in this publication are those of the author(s) and not necessarily those of the National Institute for Health Research or the UK Department of Health and Social Care. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.