Global Research Trends and Insights on AI Usage in Tuberculosis: Bibliometric Analysis

Tuberculosis (TB) remains a major global health challenge despite prevention efforts. AI offers promising approaches to long-standing challenges in TB diagnosis, drug resistance detection, and case management; however, a systematic mapping of global research priorities and translational gaps in AI applications to TB is currently lacking.

This study aimed to analyze development patterns, collaboration networks, and knowledge structure of AI applications in TB management through bibliometric analysis of Web of Science publications, identifying research frontiers and translational gaps.

This study conducted a bibliometric analysis of Web of Science Core Collection publications (2000-2025; last searched April 4, 2025). Original articles and reviews containing both AI- and TB-related terms were screened by 2 independent reviewers following PRISMA 2020 principles. Coauthorship, cocitation, and keyword cooccurrence networks were constructed with VOSviewer (Nees Jan van Eck and Ludo Waltman, Leiden University), CiteSpace (Dr. Chaomei Chen, Drexel University), and Bibliometrix R package (Massimo Aria and Corrado Cuccurullo, University of Naples Federico II), and results were synthesized through descriptive statistics and scientific knowledge mapping.

Analysis of 1300 articles shows substantial growth in AI applications for TB management during 2000-2025, with post-2018 publication growth of 29.7% and citation growth of 54.2% annually. The United States dominated output (346 publications; 12,143 citations), whereas high-burden countries remained underrepresented relative to disease burden, revealing a systematic research-demand inversion. Of the 15 most cited papers, 4 (26.7%) focused on imaging analysis, 2 (13.3%) on drug resistance prediction, and 3 (20.0%) on drug discovery, together comprising 60% (9/15) of the highly cited literature; the remainder addressed foundational biology, decentralized-learning methodology, immunoinformatics, and review literature rather than a specific TB application domain. Across this literature, technical validation-stage work markedly outweighed papers reporting clinical application, underscoring a technology-over-translation imbalance; key gaps persist in cross-regional data sharing, atypical lesion recognition, and socioeconomic factor integration. These findings indicate that clinicians and program managers in high-burden settings should prioritize locally validated, implementation-ready AI tools over algorithmic refinements, and that funders should direct resources toward prospective clinical trials and equity-focused deployment frameworks.

AI-TB research has expanded rapidly, yet clinical translation remains disproportionately limited relative to algorithmic innovation. To help bridge this gap, frontline clinicians in high-burden settings could prioritize locally validated computer-aided detection (CAD) tools meeting World Health Organization (WHO)-recommended performance standards for chest-radiograph triage, and contribute real-world performance data through postdeployment surveillance channels; policymakers could support cross-national data-sharing frameworks and consider integrating validated AI tools into national TB screening programs; and funders could allocate a defined share of AI-for-TB grants to prospective clinical evaluation rather than further algorithmic refinement alone. These findings should be interpreted in light of the study's reliance on a single English-language database and the inherent limitations of bibliometric proxies, which may underrepresent research from high-burden regions and undervalue recent publications.