Search

Background: The introduction of ChatGPT by OpenAI has garnered significant attention. Among its capabilities, paraphrasing stands out., Objective: This study aims to investigate the satisfactory levels of plagiarism in the paraphrased text produced by this chatbot., Methods: Three texts of varying lengths were presented to ChatGPT. ChatGPT was then instructed to paraphrase the provided texts using five different prompts. In the subsequent stage of the study, the texts were divided into separate paragraphs, and ChatGPT was requested to paraphrase each paragraph individually. Lastly, in the third stage, ChatGPT was asked to paraphrase the texts it had previously generated., Results: The average plagiarism rate in the texts generated by ChatGPT was 45% (SD 10%). ChatGPT exhibited a substantial reduction in plagiarism for the provided texts (mean difference -0.51, 95% CI -0.54 to -0.48; P<.001). Furthermore, when comparing the second attempt with the initial attempt, a significant decrease in the plagiarism rate was observed (mean difference -0.06, 95% CI -0.08 to -0.03; P<.001). The number of paragraphs in the texts demonstrated a noteworthy association with the percentage of plagiarism, with texts consisting of a single paragraph exhibiting the lowest plagiarism rate (P<.001)., Conclusions: Although ChatGPT demonstrates a notable reduction of plagiarism within texts, the existing levels of plagiarism remain relatively high. This underscores a crucial caution for researchers when incorporating this chatbot into their work., (© Soheil Hassanipour, Sandeep Nayak, Ali Bozorgi, Mohammad-Hossein Keivanlou, Tirth Dave, Abdulhadi Alotaibi, Farahnaz Joukar, Parinaz Mellatdoust, Arash Bakhshi, Dona kuriyakose, Lakshmi Polisetty, Mallika Chimpiri, Ehsan Amini-Salehi. Originally published in JMIR Medical Education (https://mededu.jmir.org).)

Background: Measles, a highly contagious and vaccine-preventable disease, continues to present global public health challenges. This retrospective study focused on measles outbreaks in Hormozgan province, southern Iran, spanning from 2014 to 2019., Methods: Between 2014 and 2019, patients suspected of having measles, as reported by medical centers in Hormozgan, were subject to a comprehensive evaluation. The diagnosis of measles was conclusively established through the use of real-time polymerase chain reaction (RT-PCR) testing. A detailed collection of pertinent data was undertaken. SPSS software, version 21, was employed for statistical analysis., Results: In the current study, out of 1291 clinically suspected measles cases, 151 were PCR-confirmed, with an average age of 16.77 years (±10.46), comprising 50.9% males and 49.1% females. The annual distribution showed varied incidence: 8.4% in 2014, peaking at 18.8% in 2015, then fluctuating to 11.4% in 2016, 0.8% in 2017, and 17.9% in 2018, with no cases in 2019. Among confirmed cases, 16.5% were vaccinated, while 68.2% were not, and 15.23% had unknown vaccination status., Conclusion: This retrospective study highlights the ongoing challenge of measles in Hormozgan province, Iran, from 2014 to 2019. Despite measles being preventable by vaccination, a significant number of cases were confirmed among both vaccinated and unvaccinated individuals, indicating gaps in immunization coverage and effectiveness. The fluctuating annual incidence, with a peak in 2015 and no cases in 2019, suggests variable success in disease control efforts. This underscores the need for enhanced surveillance, improved vaccination strategies, and public health interventions to effectively combat measles outbreaks in this region., Competing Interests: The authors have no conflict of interest to declare.Sponsorships or competing interests that may be relevant to content are disclosed at the end of this article., (Copyright © 2024 The Author(s). Published by Wolters Kluwer Health, Inc.)