Nationwide longitudinal evaluation of a machine learning approach for enhanced interpretation of Xpert MTB/RIF ultra rifampicin-resistance results in low bacterial load tuberculosis specimens
By leveraging the LGBM model, AI-CDSS effectively distinguished true RIF resistance from false-positive Xpert Ultra results, particularly among patients with low MTB bacterial loads. This approach enhances clinical decision making, optimizes treatment initiation, and conserves vital multidrug-resistant TB resources.
Authors
- Hung‐Sheng Shang (ORCID: https://orcid.org/0000-0002-4831-1866)
- Cherng‐Lih Perng (ORCID: https://orcid.org/0000-0001-7182-1031)
- Ming‐Jr Jian (ORCID: https://orcid.org/0000-0002-4902-4447)
- Hsing‐Yi Chung (ORCID: https://orcid.org/0000-0002-7870-8354)
- Yuan-Hao Chen (ORCID: https://orcid.org/0000-0002-0570-4328)
- Chih-Kai Chang
- Tai-Han Lin
- Feng‐Yee Chang
- Yun-Wen Lai
Institutions
- National Defense Medical Center (TW)
Publication Details
- Journal
- Journal of Infection and Public Health
- Published
- 2025-11-22
- DOI
- https://doi.org/10.1016/j.jiph.2025.103064
- Primary Topic
- Tuberculosis Research and Epidemiology
- Type
- article
- Field-Weighted Citation Impact
- 0.00