BACKGROUND
With the rapid advancement of artificial intelligence (AI) in various fields, evaluating its application in specialized medical contexts becomes crucial. ChatGPT, a large language model developed by OpenAI, has shown potential in diverse applications, including medicine.
OBJECTIVE
This study aims to compare the performance of ChatGPT with that of attending neurologists in a real neurology specialist examination conducted in the Valencian Community, Spain, to assess the AI's capabilities and limitations in medical knowledge.
METHODS
We conducted a comparative analysis using the 2022 neurology specialist exam results from 120 neurologists and responses generated by ChatGPT versions 3.5 and 4. The exam consisted of 80 multiple-choice questions, with a focus on clinical neurology and health legislation. Questions were classified according to Bloom's Taxonomy. Statistical analysis of performance, including Kappa coefficient for response consistency, was performed.
RESULTS
Human participants exhibited a median score of 5.91, with 32 neurologists failing to pass. ChatGPT-3.5 ranked 116th out of 122, answering 54.5% of questions correctly (score 3.94). ChatGPT-4 showed marked improvement, ranking 17th with 81.8% of correct answers (score 7.57), surpassing several human specialists. No significant variations were observed in the performance on lower-order versus higher-order questions. Additionally, ChatGPT-4 demonstrated increased inter-rater reliability, as reflected by a higher Kappa coefficient of 0.73, compared to ChatGPT-3.5's coefficient of 0.69.
CONCLUSIONS
This study underscores the evolving capabilities of AI in medical knowledge assessment, particularly in specialized fields. ChatGPT4's performance, surpassing the median human score in a rigorous neurology exam, marks a notable advancement, suggesting its potential as an effective tool in specialized medical education and assessment.