The Rapid Development of Artificial Intelligence: GPT-4's Performance on Orthopedic Surgery Board Questions.

Advances in artificial intelligence and machine learning models, like Chat Generative Pre-trained Transformer (ChatGPT), have occurred at a remarkably fast rate. OpenAI released its newest model of ChatGPT, GPT-4, in March 2023. It offers a wide range of medical applications. The model has demonstrated notable proficiency on many medical board examinations. This study sought to assess GPT-4's performance on the Orthopaedic In-Training Examination (OITE) used to prepare residents for the American Board of Orthopaedic Surgery (ABOS) Part I Examination. The data gathered from GPT-4's performance were additionally compared with the data of the previous iteration of ChatGPT, GPT-3.5, which was released 4 months before GPT-4. GPT-4 correctly answered 251 of the 396 attempted questions (63.4%), whereas GPT-3.5 correctly answered 46.3% of 410 attempted questions. GPT-4 was significantly more accurate than GPT-3.5 on orthopedic board-style questions (P<.00001). GPT-4's performance is most comparable to that of an average third-year orthopedic surgery resident, while GPT-3.5 performed below an average orthopedic intern. GPT-4's overall accuracy was just below the approximate threshold that indicates a likely pass on the ABOS Part I Examination. Our results demonstrate significant improvements in OpenAI's newest model, GPT-4. Future studies should assess potential clinical applications as AI models continue to be trained on larger data sets and offer more capabilities. [Orthopedics. 2024;47(2):e85-e89.].

GPT-4 Artificial Intelligence Model Outperforms ChatGPT, Medical Students, and Neurosurgery Residents on Neurosurgery Written Board-Like Questions.

BACKGROUND: Artificial intelligence (AI) and machine learning have transformed health care with applications in various specialized fields. Neurosurgery can benefit from artificial intelligence in surgical planning, predicting patient outcomes, and analyzing neuroimaging data. GPT-4, an updated language model with additional training parameters, has exhibited exceptional performance on standardized exams. This study examines GPT-4's competence on neurosurgical board-style questions, comparing its performance with medical students and residents, to explore its potential in medical education and clinical decision-making. METHODS: GPT-4's performance was examined on 643 Congress of Neurological Surgeons Self-Assessment Neurosurgery Exam (SANS) board-style questions from various neurosurgery subspecialties. Of these, 477 were text-based and 166 contained images. GPT-4 refused to answer 52 questions that contained no text. The remaining 591 questions were inputted into GPT-4, and its performance was evaluated based on first-time responses. Raw scores were analyzed across subspecialties and question types, and then compared to previous findings on Chat Generative pre-trained transformer performance against SANS users, medical students, and neurosurgery residents. RESULTS: GPT-4 attempted 91.9% of Congress of Neurological Surgeons SANS questions and achieved 76.6% accuracy. The model's accuracy increased to 79.0% for text-only questions. GPT-4 outperformed Chat Generative pre-trained transformer (P < 0.001) and scored highest in pain/peripheral nerve (84%) and lowest in spine (73%) categories. It exceeded the performance of medical students (26.3%), neurosurgery residents (61.5%), and the national average of SANS users (69.3%) across all categories. CONCLUSIONS: GPT-4 significantly outperformed medical students, neurosurgery residents, and the national average of SANS users. The mode's accuracy suggests potential applications in educational settings and clinical decision-making, enhancing provider efficiency, and improving patient care.