Diagnostic accuracy of AI-assisted chest radiographs in tuberculosis screening: A Ghanaian clinical study
The AI system outperformed the radiologist in TB screening, demonstrating higher diagnostic accuracy and agreement with GeneXpert MTB/RIF result. These findings support the integration of AI into TB screening workflows, particularly in settings with limited access to expert radiological interpretation.
Authors
- Derick Seyram Sule (ORCID: https://orcid.org/0000-0002-9520-289X)
- Andrew Yaw Nyantakyi (ORCID: https://orcid.org/0000-0003-0742-6007)
- William K. Antwi (ORCID: https://orcid.org/0000-0002-6726-2342)
- Godwill Acquah (ORCID: https://orcid.org/0000-0003-3248-4313)
- K. Dzefi-Tettey
- Joseph Daniels
- Kofi Adesi Kyei
Institutions
- University of Cape Coast (GH)
- University of Health and Allied Sciences (GH)
- Korle Bu Teaching Hospital (GH)
Publication Details
- Journal
- PLoS ONE
- Published
- 2026-03-27
- DOI
- https://doi.org/10.1371/journal.pone.0342988
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00