Objectives: Artificial intelligence (AI) is considered a promising tool for enhancing diagnostic accuracy in medicine. Periodontal disease, a highly prevalent oral condition, necessitates early detection to enable timely intervention and prevent progression. This study was designed to assess the effectiveness of AI in identifying periodontal bone loss (PBL) on panoramic radiographs.

Materials and Methods: A systematic literature search was performed following the PRISMA framework. The search strategy, implemented in PubMed, Scopus and Web of Science, combined keywords related to AI, panoramic radiography, and periodontal disease. Study selection proceeded through standardized screening of titles, abstracts, and full texts. The methodological quality of the final included studies was appraised using the Critical Appraisal Skills Programme (CASP) checklists.

Results: The systematic review yielded sixteen studies meeting the inclusion criteria. Based on CASP appraisal, six studies were judged to be of high quality, seven of moderate quality, and three of low quality. Regarding diagnostic performance, the reviewed AI models achieved maximum metrics as follows: accuracy up to 99%, sensitivity up to 100%, and specificity up to 99%. The highest reported area under the curve (AUC) was 95%, while precision and F1-scores both reached peaks of 99%.

Conclusions: AI has demonstrated strong potential in detecting PBL from panoramic radiographs, providing an efficient method for evaluating dental health. Additional clinical studies are necessary to confirm the reliability, consistency, and practical applicability of AI in real-world dental settings.