RESUMO
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.
RESUMO
The autoimmunity-promoting cytokine, Interleukin-15 (IL-15), is often claimed to be a key pathogenic cytokine in alopecia areata (AA). Yet, rhIL-15 promotes human hair follicle (HF) growth ex vivo. We have asked whether the expression of IL-15 and its receptor (IL-15R) isoforms is altered in human AA and how IL-15 impacts on human HF immune privilege (HF-IP) in the presence/absence of interferon-γ (IFNγ), the well-documented key AA-pathogenic cytokine, as well as on hair regrowth after experimental AA induction in vivo. Quantitative immunohistomorphometry showed the number of perifollicular IL-15+ T cells in AA skin biopsies to be significantly increased compared to healthy control skin, while IL-15, IL-15Rα, and IL-15Rγ protein expression within the hair bulb were significantly down-regulated in AA HFs. In organ-cultured human scalp HFs, rhIL-15 significantly reduced hair bulb expression of MICA, the key "danger" signal in AA pathogenesis, and increased production of the HF-IP guardian, α-MSH. Crucially, ex vivo, rhIL-15 prevented IFNγ-induced HF-IP collapse, restored a collapsed HF-IP by IL-15Rα-dependent signaling (as documented by IL-15Rα-silencing), and protected AA-preventive immunoinhibitory iNKT10 cells from IFNγ-induced apoptosis. rhIL-15 even promoted hair regrowth after experimental AA induction in human scalp skin xenotransplants on SCID/beige mice in vivo. Our data introduce IL-15 as a novel, functionally important HF-IP guardian whose signaling is constitutively defective in scalp HFs of AA patients. Our data suggest that selective stimulation of intrafollicular IL-15Rα signaling could become a novel therapeutic approach in AA management, while blocking it pharmacologically may hinder both HF-IP restoration and hair re-growth and may thus make HFs more vulnerable to AA relapse.