Diagnostic Accuracy of Artificial Intelligence- Enabled Screening for Oral Cancer: A Systematic Review and Meta-analysis

Background Oral cancer is a global health challenge, with delayed detection leading to poor survival. Artificial intelligence (AI)-based tools show promise for early detection, but evidence remains fragmented and heterogeneous. This systematic review and meta-analysis evaluated the diagnostic performance and clinical utility of AI-enabled approaches for oral cancer screening. Methods PubMed, Scopus, Web of Science, Cochrane Library, and Google Scholar were searched through August 2024. Study quality was assessed using the QUADAS-2 tool. Results Twenty-seven studies were included in the review, with nine contributing to the meta-analysis. The pooled sensitivity for the reviewed AI-enabled screening systems was 0.91 (95% CI: 0.81–0.91), the pooled specificity was 0.91 (95% CI: 0.86–0.94), and the area under the summary receiver operating characteristic curve was 0.938, indicating excellent diagnostic accuracy. Conclusion The findings of this study demonstrate the high diagnostic accuracy of AI-based technologies for oral cancer screening and underscore their potential for integration into clinical practice to enhance early detection and improve patient outcomes.