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.].

Combining avidin with CD63 improves basophil activation test accuracy in classifying peanut allergy.

BACKGROUND: Conventional basophil activation tests (BATs) measure basophil activation by the increased expression of CD63. Previously, fluorophore-labeled avidin, a positively-charged molecule, was found to bind to activated basophils, which tend to expose negatively charged granule constituents during degranulation. This study further compares avidin versus CD63 as basophil activation biomarkers in classifying peanut allergy. METHODS: Seventy subjects with either a peanut allergy (N = 47), a food allergy other than peanut (N = 6), or no food allergy (N = 17) were evaluated. We conducted BATs in response to seven peanut extract (PE) concentrations (0.01-10,000 ng/mL) and four control conditions (no stimulant, anti-IgE, fMLP (N-formylmethionine-leucyl-phenylalanine), and anti-FcεRI). We measured avidin binding and CD63 expression on basophils with flow cytometry. We evaluated logistic regression and XGBoost models for peanut allergy classification and feature identification. RESULTS: Avidin binding was correlated with CD63 expression. Both markers discriminated between subjects with and without a peanut allergy. Although small by percentage, an avidin+ /CD63- cell subset was found in all allergic subjects tested, indicating that the combination of avidin and CD63 could allow a more comprehensive identification of activated basophils. Indeed, we obtained the best classification accuracy (97.8% sensitivity, 96.7% specificity) by combining avidin and CD63 across seven PE doses. Similar accuracy was obtained by combining PE dose of 10,000 ng/mL for avidin and PE doses of 10 and 100 ng/mL for CD63. CONCLUSIONS: Avidin and CD63 are reliable BAT activation markers associated with degranulation. Their combination enhances the identification of activated basophils and improves the classification accuracy of peanut allergy.

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.