ABSTRACT
Background: The deployment of OpenAI's ChatGPT-3.5 and its subsequent versions, ChatGPT-4 and ChatGPT-4 With Vision (4V; also known as "GPT-4 Turbo With Vision"), has notably influenced the medical field. Having demonstrated remarkable performance in medical examinations globally, these models show potential for educational applications. However, their effectiveness in non-English contexts, particularly in Chile's medical licensing examinations-a critical step for medical practitioners in Chile-is less explored. This gap highlights the need to evaluate ChatGPT's adaptability to diverse linguistic and cultural contexts. Objective: This study aims to evaluate the performance of ChatGPT versions 3.5, 4, and 4V in the EUNACOM (Examen Único Nacional de Conocimientos de Medicina), a major medical examination in Chile. Methods: Three official practice drills (540 questions) from the University of Chile, mirroring the EUNACOM's structure and difficulty, were used to test ChatGPT versions 3.5, 4, and 4V. The 3 ChatGPT versions were provided 3 attempts for each drill. Responses to questions during each attempt were systematically categorized and analyzed to assess their accuracy rate. Results: All versions of ChatGPT passed the EUNACOM drills. Specifically, versions 4 and 4V outperformed version 3.5, achieving average accuracy rates of 79.32% and 78.83%, respectively, compared to 57.53% for version 3.5 (P<.001). Version 4V, however, did not outperform version 4 (P=.73), despite the additional visual capabilities. We also evaluated ChatGPT's performance in different medical areas of the EUNACOM and found that versions 4 and 4V consistently outperformed version 3.5. Across the different medical areas, version 3.5 displayed the highest accuracy in psychiatry (69.84%), while versions 4 and 4V achieved the highest accuracy in surgery (90.00% and 86.11%, respectively). Versions 3.5 and 4 had the lowest performance in internal medicine (52.74% and 75.62%, respectively), while version 4V had the lowest performance in public health (74.07%). Conclusions: This study reveals ChatGPT's ability to pass the EUNACOM, with distinct proficiencies across versions 3.5, 4, and 4V. Notably, advancements in artificial intelligence (AI) have not significantly led to enhancements in performance on image-based questions. The variations in proficiency across medical fields suggest the need for more nuanced AI training. Additionally, the study underscores the importance of exploring innovative approaches to using AI to augment human cognition and enhance the learning process. Such advancements have the potential to significantly influence medical education, fostering not only knowledge acquisition but also the development of critical thinking and problem-solving skills among health care professionals.
Subject(s)
Educational Measurement , Licensure, Medical , Female , Humans , Male , Chile , Clinical Competence/standards , Educational Measurement/methods , Educational Measurement/standardsABSTRACT
Resumen Las infecciones, incluyendo las zoonosis, constituyen una amenaza a la salud humana debido a la diseminación de patógenos resistentes. Estas enfermedades generan una respuesta inflamatoria controlada por un mecanismo de resolución, en el que participan moléculas especializadas derivadas de lípidos de membrana llamadas lipoxinas, resolvinas, maresinasios o que puede prevenir la derivación hacia cursos crónicos, dañinos para el hospedero. En esta revisión se presenta una puesta al día sobre el uso de estatinas o aspirina para el manejo experimental de infecciones parasitarias, como enfermedad de Chagas, leishmaniasis, toxo-plasmosis y malaria. Se hizo una revisión narrativa, buscando artículos originales de los últimos siete anos, se encontraron 38 que cumplieron con los criterios de inclusión. De acuerdo con las publicaciones consultadas, la resolución de la inflamación modulada mediante estatinas podría ser un adyuvante en la terapia de enfermedades parasitarias. Por otro lado, no se observó una evidencia experimental fuerte con respecto al uso de aspirina, por lo que se recomiendan más estudios para evaluar su rol en el proceso de resolución de la inflamación en enfermedades infecciosas.
ABSTRACT
Infections, including zoonoses, constitute a threat to human health due to the spread of resistant pathogens. These diseases generate an inflammatory response controlled by a resolving mechanism involving specialized membrane lipid-derived molecules called lipoxins, resolvins, maresins, and protectins. The production of some of these molecules can be triggered by aspirin or statins. Thus, it is proposed that modulation of the host response could be a useful therapeutic strategy, contributing to the management of resistance to antiparasitic agents or preventing drift to chronic, host-damaging courses. Therefore, the present work presents the state of the art on the use of statins or aspirin for the experimental management of parasitic infections such as Chagas disease, leishmaniasis, toxoplasmosis or malaria. The methodology used was a narrative review covering original articles from the last seven years, 38 of which met the inclusion criteria. Based on the publications consulted, modulation of the resolution of inflammation using statins may be feasible as an adjuvant in the therapy of parasitic diseases. However, there was no strong experimental evidence on the use of aspirin; therefore, further studies are needed to evaluate its role inflammation resolution process in infectious diseases.
