Page 59 - AIH-1-3

Artificial Intelligence in Health

ORIGINAL RESEARCH ARTICLE
Applying ChatGPT to writing scientific articles

on the use of telemedicine: Opportunities and
limitations

Daniil Kolesnikov * , Alexandra Kozlova 1 , Andrey Aleхandrov 1 ,
1
Nikolai Kalmykov 1 , Pavel Treshkov 1 , Tyler W. LeBaron 2,3 , and
Oleg Medvedev 4,5

1 Faculty of Biomedical Engineering, Bauman Moscow State Technical University, Moscow, Russia
2 Department of Kinesiology and Outdoor Recreation, Southern Utah University, Cedar City, Utah,
United States of America
3 Molecular Hydrogen Institute, Cedar City, Utah, United States of America
4 Department of Pharmacology, Faculty of Basic Medicine, Lomonosov Moscow State University,
Moscow, Russia
5 Laboratory of Experimental Pharmacology, National Medical Research Center of Cardiology of the
Ministry of Health of the Russian Federation, Moscow, Russia

Abstract

In the rapidly evolving world of technology, artificial intelligence (AI) has significantly
integrated into various aspects of our lives, including health-care, education, finance,
transportation, and entertainment. Notably, AI has also impacted the writing of textual
*Corresponding author: works such as scientific papers, professional opinions, and educational texts. This
Daniil Kolesnikov study investigates the application of OpenAI’s ChatGPT language model in writing
(kolesnikovda@student.bmstu.ru) scientific articles on telemedicine, specifically in the areas of cardiology, oncology,
Citation: Kolesnikov D, Kozlova A, and remote medical examination. The study uses ChatGPT versions 3.5 and 4 to create
Aleхandrov A, et al. Applying articles using three different prompts. The created articles were evaluated based on
ChatGPT to writing scientific the reliability of the cited literature references, the impact factor (IF) of the journal in
articles on the use of telemedicine:
Opportunities and limitations. Artif which the sources were published, and the relevance of the sources. The sources were
Intell Health. 2024;1(3):53-63. divided into three categories: reliable, semi-reliable, and completely fictitious. The
doi: 10.36922/aih.2592 results demonstrate that ChatGPT can produce semantically coherent and error-free
Received: December 31, 2023 texts indistinguishable from human-written texts. However, the reliability of literary
Accepted: April 22, 2024 references varies significantly. ChatGPT 4, benefitting from its larger training dataset,
generates a higher percentage of reliable sources compared to ChatGPT 3.5. The IF
Published Online: July 22, 2024 analysis indicates the prevalence of high-impact journals among reliable sources,
Copyright: © 2024 Author(s). which emphasizes the effectiveness of the model in selecting quality references. The
This is an Open-Access article study highlights the need for caution when using AI to write scientific articles due
distributed under the terms of the
Creative Commons Attribution to the potential for biased, unverified, and inaccurate information. It is important to
License, permitting distribution, critically evaluate and vet AI-generated content. In addition, the study emphasizes
and reproduction in any medium, that the correct use of AI and thoughtful drafting of prompts can improve the
provided the original work is
properly cited. efficiency and quality of scientific papers. Future advancements in AI technology are
expected to further minimize errors and biases.
Publisher’s Note: AccScience
Publishing remains neutral with
regard to jurisdictional claims in
published maps and institutional Keywords: Artificial intelligence; ChatGPT; Biotelemetry; Cardiology
affiliations.

Volume 1 Issue 3 (2024) 53 doi: 10.36922/aih.2592