The aim of this study was to assess the reliability of the artificial intelligence (AI) automatic evaluation of panoramic radiographs (PRs). Thirty PRs, covering at least six teeth with the possibility of assessing the marginal and apical periodontium, were uploaded to the Diagnocat (LLC Diagnocat, Moscow, Russia) account, and the radiologic report of each was generated as the basis of automatic evaluation. The same PRs were manually evaluated by three independent evaluators with 12, 15, and 28 years of experience in dentistry, respectively. The data were collected in such a way as to allow statistical analysis with SPSS Statistics software (IBM, Armonk, NY, USA). A total of 90 reports were created for 30 PRs. The AI protocol showed very high specificity (above 0.9) in all assessments compared to ground truth except from periodontal bone loss. Statistical analysis showed a high interclass correlation coefficient (ICC > 0.75) for all interevaluator assessments, proving the good credibility of the ground truth and the reproducibility of the reports. Unacceptable reliability was obtained for caries assessment (ICC = 0.681) and periapical lesions assessment (ICC = 0.619). The tested AI system can be helpful as an initial evaluation of screening PRs, giving appropriate credibility reports and suggesting additional diagnostic methods for more accurate evaluation if needed.
Keywords: AI; dentistry; diagnosis; panoramic radiograph; screening.