Diagnostic Accuracy of Chest X-ray Computer-Aided Detection Software for Detection of Prevalent and Incident Tuberculosis in Household Contacts
Clinical Infectious Diseases · 2025
DOI: 10.1093/cid/ciae528 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Infectious Diseases, 2025. Verfasst von Liana Macpherson und 24 weiteren Autor:innen. Beteiligte Einrichtung: MRC Clinical Trials Unit, University College London, London, United Kingdom. Hauptthemen laut MEDLINE: Software, Radiography, Thoracic, Diagnosis, Computer-Assisted, Tuberculosis, Pulmonary. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cancer Research UK, Wellcome Trust, German Ministry for Education and Research through KfW Development Bank.
Abstract (Originalsprache)
Background
World Health Organization (WHO) tuberculosis (TB) screening guidelines recommend computer-aided detection (CAD) software for chest radiograph (CXR) interpretation. However, studies evaluating their diagnostic and prognostic accuracy are limited.
Methods
We conducted a prospective cohort study of household contacts of rifampicin-resistant TB in South Africa. Participants underwent baseline CXR and sputum investigation (routine [single spontaneous] and enhanced [additionally 2–3 induced]) for prevalent TB and follow-up for incident TB. Three CXR-CAD software products (CAD4TBv7.0, qXRv3.0.0, and Lunit INSIGHT v3.1.4.111) were compared. We evaluated their performance to detect routine and enhanced prevalent and incident TB, comparing performance with blood tests (Xpert MTB host-response, erythrocyte sedimentation rate, C-reactive protein, QuantiFERON) in a subgroup.
Results
483 participants were followed up for 4.6 years (median). There were 23 prevalent (7 routinely diagnosed) and 38 incident TB cases. The AUC ROCs (95% CIs) to identify prevalent TB for CAD4TBv7.0, qXRv3.0.0, and Lunit INSIGHT v3.1.4.111 were .87 (.77–.96), .88 (.79–.97), and .91 (.83–.99), respectively. More than 30% with scores above recommended CAD thresholds who were bacteriologically negative on routine baseline sputum were subsequently diagnosed by enhanced sputum investigation or during follow-up. The AUC performance of baseline CAD to identify incident cases ranged between .60 and .65. Diagnostic performance of CAD for prevalent TB was superior to blood testing.
Conclusions
Our findings suggest that the potential of CAD-CXR screening for TB is not maximized as a high proportion of those above current thresholds, but with a negative routine confirmatory sputum, have true TB disease that may benefit intervention.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- MRC Clinical Trials Unit, University College London, London, United Kingdom.
- FIND, Geneva, Switzerland.
- Centre for Infectious Diseases Research in Africa, Institute of Infectious Disease and Molecular Medicine and Department of Medicine, University of Cape Town, Cape Town, South Africa.
- Institute of Infectious Disease and Molecular Medicine and Department of Pathology, University of Cape Town, Cape Town, South Africa.
- Rutgers-New Jersey Medical School, Center for Emerging Pathogens, Newark, New Jersey, USA.
- Department of Internal Medicine, University Hospital of Zurich, University of Zurich, Zurich, Switzerland.
ORCID-Profile: Sandra V Kik, Matteo Quartagno, Richard Court, Arshad Taliep, Bianca Sossen, Friedrich Thienemann, Robert J Wilkinson, Anna K Coussens, Hanif Esmail
Förderung
- Cancer Research UK
- Wellcome Trust
- German Ministry for Education and Research through KfW Development Bank
- Medical Research Council
- NIAID NIH HHS
- Francis Crick Institute
- South African Medical Research Council
- Bill and Melinda Gates Foundation
Zitieren
APA
Macpherson, L., Kik, S. V., Quartagno, M., Lakay, F., Jaftha, M., Yende, N., Galant, S., Aziz, S., Daroowala, R., Court, R., Taliep, A., Serole, K., Goliath, R. T., Davies, N. O., Jackson, A., Douglass, E., Sossen, B., Mukasa, S., Thienemann, F., …, & Imaging of TB Household Contacts Group (2025). Diagnostic Accuracy of Chest X-ray Computer-Aided Detection Software for Detection of Prevalent and Incident Tuberculosis in Household Contacts. Clinical Infectious Diseases. https://doi.org/10.1093/cid/ciae528
Vancouver
Macpherson L, Kik SV, Quartagno M, Lakay F, Jaftha M, Yende N, et al. Diagnostic Accuracy of Chest X-ray Computer-Aided Detection Software for Detection of Prevalent and Incident Tuberculosis in Household Contacts. Clinical Infectious Diseases. 2025. doi:10.1093/cid/ciae528
BibTeX
@article{Macpherson2025,
author = {Macpherson, Liana and Kik, Sandra V and Quartagno, Matteo and Lakay, Francisco and Jaftha, Marche and Yende, Nombuso and Galant, Shireen and Aziz, Saalikha and Daroowala, Remy and Court, Richard and Taliep, Arshad and Serole, Keboile and Goliath, Rene T and Davies, Nashreen Omar and Jackson, Amanda and Douglass, Emily and Sossen, Bianca and Mukasa, Sandra and Thienemann, Friedrich and Song, Taeksun and Ruhwald, Morten and Wilkinson, Robert J and Coussens, Anna K and Esmail, Hanif and Imaging of TB Household Contacts Group, Imaging of TB Household Contacts Group},
title = {Diagnostic Accuracy of Chest X-ray Computer-Aided Detection Software for Detection of Prevalent and Incident Tuberculosis in Household Contacts},
journal = {Clinical Infectious Diseases},
year = {2025},
doi = {10.1093/cid/ciae528}
}
EUVIMED