Artificial Intelligence Tools for Diagnosing the Relationship Between the Inferior Alveolar Nerve and the Third Molar: A Systematic Review

Objective To evaluate the diagnostic capability of artificial intelligence (AI) compared to human radiographic interpretation in assessing the relationship between the inferior alveolar nerve (IAN) and the third molar. Methods The search was conducted in nine electronic databases (PubMed/MEDLINE, EMBASE, LILACS, Web of Science, Scopus, LIVIVO, Computers & Applied Sciences, ACM Digital Library, and Compendex) and gray literature (Google Scholar and ProQuest) for studies published up to December 2024. Results Fifteen diagnostic studies were included, encompassing approximately 19,049 third molars and 14,455 imaging exams. Nine studies used 2D images (panoramic radiographs) to assess the IAN-third molar relationship, two used CBCT, and four used both panoramic radiographs and CBCT. Significant heterogeneity was observed across studies regarding AI models, imaging techniques, and classification methods, along with inconsistencies in the presentation of diagnostic metrics. Conclusions AI tools have demonstrated high accuracy in diagnosing the relationship between the IAN and third molars, offering time savings and reliable diagnostic support for radiologists, oral and maxillofacial surgeons, and general practitioners. While CBCT-based AI models showed promising diagnostic accuracy, the available data were limited, and the certainty of evidence was low.