Background: This research aimed to investigate the concordance between clinical impressions and histopathologic diagnoses made by clinicians and artificial intelligence tools for odontogenic keratocyst (OKC) and Odontogenic tumours (OT) in a New Zealand population from 2008-2023.
Methods: Histopathological records from the Oral Pathology Centre, University of Otago (2008-2023) were examined to identify OKCs and OT. Specimen referral details, histopathologic reports, and clinician differential diagnoses, as well as those provided by ORAD and Chat PT-4, were documented. Data were analyzed using SPSS, and concordance between provisional and histopathologic diagnoses was ascertained.
Results: Of the 34,225 biopsies, 302 and 321 samples were identified as OTs and OKCs. Concordance rates were 43.2% for clinicians, 45.6% for ORAD, and 41.4% for CHAT-GPT4. Surgeons achieved higher concordance rate (47.7%) compared to non-surgeons (29.82%). Odds ratio of having concordant diagnosis using CHAT-GPT and ORAD were between 1.4-2.8 (p<0.05). In differentiation between Ameloblastoma and OKC, CHAT-GPT4 had highest sensitivity at 75.9% and accuracy of 82.5%. For clinicians and ORAD the corresponding values were 66.7%/86.8% and 66.7%/84.9%, respectively.
Conclusion: Clinicians with surgical training achieved higher concordance rate when it comes to OT and OKC. CHAT-GPT4 and Bayesian approach (ORAD) have shown potential in enhancing diagnostic capabilities.