RESUMEN
Background: ChatGPT, launched in 2022 and updated to Generative Pre-trained Transformer 4 (GPT-4) in 2023, is a large language model trained on extensive data, including medical information. This study compares ChatGPT's performance on Plastic Surgery In-Service Examinations with medical residents nationally as well as its earlier version, ChatGPT-3.5. Methods: This study reviewed 1500 questions from the Plastic Surgery In-service Examinations from 2018 to 2023. After excluding image-based, unscored, and inconclusive questions, 1292 were analyzed. The question stem and each multiple-choice answer was inputted verbatim into ChatGPT-4. Results: ChatGPT-4 correctly answered 961 (74.4%) of the included questions. Best performance by section was in core surgical principles (79.1% correct) and lowest in craniomaxillofacial (69.1%). ChatGPT-4 ranked between the 61st and 97th percentiles compared with all residents. Comparatively, ChatGPT-4 significantly outperformed ChatGPT-3.5 in 2018-2022 examinations (P < 0.001). Although ChatGPT-3.5 averaged 55.5% correctness, ChatGPT-4 averaged 74%, a mean difference of 18.54%. In 2021, ChatGPT-3.5 ranked in the 23rd percentile of all residents, whereas ChatGPT-4 ranked in the 97th percentile. ChatGPT-4 outperformed 80.7% of residents on average and scored above the 97th percentile among first-year residents. Its performance was comparable with sixth-year integrated residents, ranking in the 55.7th percentile, on average. These results show significant improvements in ChatGPT-4's application of medical knowledge within six months of ChatGPT-3.5's release. Conclusion: This study reveals ChatGPT-4's rapid developments, advancing from a first-year medical resident's level to surpassing independent residents and matching a sixth-year resident's proficiency.
RESUMEN
OBJECTIVE: To investigate the influences of the diffusion gradient directions (angular resolution) and the strength of the diffusion gradient (b value) on diffusion tensor imaging (DTI) metrics and tractography of various connective tissues in knee joint. DESIGN: Two rat knee joints were scanned on a preclinical 9.4-T system using a 3-dimensional diffusion-weighted spin echo pulse sequence. One protocol with b value of 500, 1500, and 2500 s/mm2 were acquired separately using 43 diffusion gradient directions. The other protocol with b value of 1000 s/mm2 was performed using 147 diffusion gradient directions. The in-plane resolution was 45 µm isotropic. Fractional anisotropy (FA) and mean diffusivity (MD) were compared at different angular resolution. Tractography was quantitatively evaluated at different b values and angular resolutions in cartilage, ligament, meniscus, and growth plate. RESULTS: The ligament showed higher FA value compared with growth plate and cartilage. The FA values were largely overestimated at the angular resolution of 6. Compared with FA, MD showed less sensitivity to the angular resolution. The fiber tracking was failed at low angular resolution (6 diffusion gradient directions) or high b value (2500 s/mm2). The quantitative measurements of tract length and track volume were strongly dependent on angular resolution and b value. CONCLUSIONS: To obtain consistent DTI outputs and tractography in knee joint, the scan may require a proper b value (ranging from 500 to 1500 s/mm2) and sufficient angular resolution (>14) with signal-to-noise ratio >10.