Generative Artificial Intelligence, With Constrained Information, Outperforms Pre-Doctoral Student Average on Oral Pathology Differential Diagnosis Questions.

Background: Artificial intelligence (AI) technologies have seen rapid advancement and are increasingly used in healthcare fields, including clinical diagnostics and dental education. Despite their growing prominence, their effectiveness in assisting clinical decision-making in dental education remains under-explored. This study examined the performance of Generative AI in generating a clinical impression for oral pathology cases relative to dental students.

Aims: The aim of this experiment was to assess the diagnostic accuracy and potential difference of Generative AI in clinical oral pathology compared to that of Doctor of Dental Surgery (DDS) students.

Methods: A clinical oral pathology differential diagnosis exam was administered to both an AI model and DDS students. The AI model received limited information about each case, while the DDS students were provided with standard case details and a multiple-choice selection. The accuracy and statistical significance between both groups were compared and evaluated.

Results: The AI model displayed higher diagnostic accuracy compared to the students, 95.65% to 78.92%, respectively, and the difference in groups was statistically significant.

Conclusion: The findings suggest that Generative AI has the potential to be a valuable tool in clinical oral pathology, even when provided with minimal case information. Its superior diagnostic performance compared to DDS students highlights prospective benefits of incorporating AI into dental education and specifically in helping students formulate clinical impressions.