Artificial Intelligence In Oral Disease Diagnosis: Mapping Trends

Abstract

This study aims to systematically map the research landscape and emerging trends in artificial intelligence (AI)-assisted oral disease diagnosis, identifying key contributors, intellectual structures, and interdisciplinary intersections within this field. A bibliometric analysis was conducted using 1,816 articles retrieved from the Web of Science Core Collection (SCI-Expanded, 2005–2025). CiteSpace software was employed to visualize collaboration networks, keyword clusters, citation bursts, and timeline evolution. Data included annual publication trends, leading countries/institutions, high-impact journals, and co-citation patterns. Annual publications exhibited exponential growth, peaking at 519 in 2024. China, the United States, and India were the most productive countries, while institutions like Humboldt University of Berlin and Sichuan University showed significant contributions. Keyword clustering revealed core research themes: “deep learning,” “oral cancer,” “periodontitis,” and “transfer learning.” Burst detection identified emerging trends such as “systematic review,” “explainable AI,” and “multimodal imaging.” Interdisciplinary integration spanned dentistry, biomedical engineering, and computer science, with timeline analysis highlighting shifts toward clinical translation. This study provides a comprehensive knowledge graph of AI-driven oral disease diagnosis research, delineating its evolution, collaborative networks, and frontier directions. Findings offer strategic insights for advancing clinical applications, fostering cross-disciplinary innovation, and addressing current limitations in AI implementation for oral healthcare.

Ähnliche Arbeiten