Play Crazy Game Trusted Gaming News Portal
Like every year in Peru, medical student Those who wish to obtain a medical residency must pass a series of examinations to obtain this professional degree, which, in many cases, causes some degree of difficulty.
Before receiving the degree of ResidentsDoctors must first complete a National Medical Examination (ENAM) And their qualifications make it easier for them to choose health centers for their development Rural Urban Marginal Health Services (SERM), However, not everyone is successful in achieving favorable results, so one researcher turned to the technology to get a firsthand look at how complex it is.
Thus, Javier Flores Coahuila, professor and researcher in medical education Southern Scientific University and consulted with the study’s lead author chatgpt and other artificial intelligence (AI) tools if they can take the exam, but pose as Peruvian medical students. The result will surprise you.
It should be noted that 43% of medical graduates from all Peruvian universities enrolled in serum he rejected it rewardAccording to the study that analyzed notes from 2009 to 2019.
Following Flores’ request, it was found that artificial intelligence chatgpt-4 (Most updated version) managed to pass the National Medical Examination (ENAM) with 86% accuracy in the 2022 exam.
“ChatGPT achieved a score of 17, and generally it is very strange to score more than 15 in ENAM. Additionally, if artificial intelligence was given specifications about how to approach the question, its performance increased. For example, when ChatGPT was asked to ‘pretend to be a doctor from Peru,’ ChatGPT only got 9 questions wrong,” explained Javier Flores Coahela to Andina Agency.
According to the researcher, the study was based on data ENAM 2022Which included 180 multiple choice questions. Thus, the AI results were compared to a sample of 1,025 medical students who took the same exam.
The research team analyzed various factors such as question type, specific knowledge of Peru, discrimination, difficulty and quality of the question, and topic to determine their impact on incorrect answers.
The results revealed that chatgpt Got 156 correct answers, while other similar AI applications passed with lower scores. For example, BingAI with 148; GPT-3, 120; Bard, 120; and Claude, 118.
javier flores coahila He clarified that this research does not try to compare the IQ of medical students to AI, nor does it try to demonstrate that artificial intelligence can replace a doctor; Because their work goes far beyond just answering questions.
“Becoming a doctor is more than giving something Examination Licensing Being a doctor includes our communication role with patients, collaboration with other health professionals, population health leadership, health promotion, etc.,” the researcher said.
However, he added that these results could be encouraging universities and research groups to aid medical education.
As we remember, on December 3 ENAM 2023. Since 2006, this test has been a mandatory requirement to apply to the National Medical Residency System, which is why it provides a score.
Furthermore, this grade also represents 70% of the grade that is taken into account for the distribution of places rural urban marginal health careWhich is known as serum.
