Clinical Decision-Making in Implant Planning: A Comparison Between Human and Artificial Intelligence

Artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT, has attracted attention for its potential to enhance diagnostic decision-making. This study aims to compare the decision-making tendencies of clinicians from different disciplines regarding implant planning with the approach of ChatGPT and to evaluate the potential integration of AI into clinical decision-making. This cross-sectional, survey-based study compared the implant planning decisions of prosthodontic and surgical residents with those of ChatGPT 4.0 and each other. Fourteen cases were presented to 20 prosthodontics, 20 oral and maxillofacial surgery residents, and ChatGPT. Participants selected the option they found most appropriate; responses were compared case by case using chi-square tests with p < 0.05. The responses of residents showed no statistically significant differences. However, comparisons between the AI and clinicians revealed significant differences in 11 of the scenarios. In clinical scenarios where no differences were found, both human and artificial intelligence tended to make the same choices on less complicated cases. While AI is increasingly advancing in clinical decision-making, its responses to clinical scenarios may show some inconsistencies. AI demonstrated similarity in simple cases but diverged in complex ones. While promising as a support, broader studies with diverse scenarios are necessary to enhance the integration potential of AI in clinical decision-making.