Dataset: A bibliometric analysis of AI-powered computer-aided detection for tuberculosis screening (2000–2024)

This dataset supports the bibliometric analysis and systematic research mapping of artificial intelligence-based computer-aided detection (TB-CAD) studies for tuberculosis screening published between January 2000 and December 2024. Records were identified from five bibliographic databases: PubMed, Scopus, Embase, Cochrane, and Web of Science, and screened according to predefined eligibility criteria. The final dataset includes 388 peer-reviewed original research articles. For each study, extracted variables include bibliographic information (title, authors, affiliations, journal, year, keywords, funding), study characteristics (setting, population, study type, CAD system or AI model evaluated), reference standards used, diagnostic outcomes reported, and dataset sources. Data were cleaned and standardized in Microsoft Excel. Missing information is coded as "NR" (not reported). This dataset was analyzed using Python (version 3.11.5) and R (version 4.3.2) for bibliometric analysis, trend analysis, and visualization.