Cargando…

Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore

BACKGROUND: Artificial intelligence (AI) is a rapidly developing field with the potential to transform various aspects of healthcare and public health including medical training. During the ‘Hygiene and Public Health’ course for fifth-year medical students, a practical training session was conducted...

Descripción completa

Detalles Bibliográficos
Autores principales: Baglivo, F, De Angelis, L, Casigliani, V, Arzilli, G, Privitera, G P, Rizzo, C
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10595493/
http://dx.doi.org/10.1093/eurpub/ckad160.1220
_version_ 1785124880800284672
author Baglivo, F
De Angelis, L
Casigliani, V
Arzilli, G
Privitera, G P
Rizzo, C
author_facet Baglivo, F
De Angelis, L
Casigliani, V
Arzilli, G
Privitera, G P
Rizzo, C
author_sort Baglivo, F
collection PubMed
description BACKGROUND: Artificial intelligence (AI) is a rapidly developing field with the potential to transform various aspects of healthcare and public health including medical training. During the ‘Hygiene and Public Health’ course for fifth-year medical students, a practical training session was conducted on vaccination using AI as an educational supportive tool. Before receiving specific training on vaccination, the students were given an online questionnaire on vaccination. After completing the questionnaire, a correction of each question was performed using AI chatbots. OBJECTIVES: The main aim was to identify whether AI chatbots can be considered as educational support tool for training in public health. Secondary objective was to assess performance of 6 different AI chatbot models. RESULTS: The questionnaire consisted of 15 items selected from the Italian National Medical Residency Test (years 2015-2022) on the topic of vaccination. 36 medical students participated in the training, achieving a mean score of 8.22/15 on the quiz (range:3-15,median:8). 6 different AI chatbot models (3 modes of BingChat, ChatGPT, ChatSonic, and YouChat) were asked the same questions and achieved a mean score of 12.17/15 (range:10-15,median:11.5), ranking in the top 25% of medical student scores. During the class, the answers provided by the AI chatbots were evaluated with the students, paying particular attention to the completeness of the information, reliability of the sources cited, and use of technical language. CONCLUSIONS: AI chatbots have shown to be efficient tools for retrieving bibliographic references from the web and answering questions related to specific topics such as vaccination. However, it is important to note that they cannot be considered more intelligent than students, as they may not perform as well when faced with situational questions. The responsible and critical use of AI should be integrated into medical education to ensure its effective utilization. KEY MESSAGES: • AI chatbots use as support tool in public health medical training should be further investigated and endorsed. • AI chatbots could be a helpful resource for medical students in terms of researching and revising their knowledge.
format Online
Article
Text
id pubmed-10595493
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-105954932023-10-25 Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore Baglivo, F De Angelis, L Casigliani, V Arzilli, G Privitera, G P Rizzo, C Eur J Public Health Poster Displays BACKGROUND: Artificial intelligence (AI) is a rapidly developing field with the potential to transform various aspects of healthcare and public health including medical training. During the ‘Hygiene and Public Health’ course for fifth-year medical students, a practical training session was conducted on vaccination using AI as an educational supportive tool. Before receiving specific training on vaccination, the students were given an online questionnaire on vaccination. After completing the questionnaire, a correction of each question was performed using AI chatbots. OBJECTIVES: The main aim was to identify whether AI chatbots can be considered as educational support tool for training in public health. Secondary objective was to assess performance of 6 different AI chatbot models. RESULTS: The questionnaire consisted of 15 items selected from the Italian National Medical Residency Test (years 2015-2022) on the topic of vaccination. 36 medical students participated in the training, achieving a mean score of 8.22/15 on the quiz (range:3-15,median:8). 6 different AI chatbot models (3 modes of BingChat, ChatGPT, ChatSonic, and YouChat) were asked the same questions and achieved a mean score of 12.17/15 (range:10-15,median:11.5), ranking in the top 25% of medical student scores. During the class, the answers provided by the AI chatbots were evaluated with the students, paying particular attention to the completeness of the information, reliability of the sources cited, and use of technical language. CONCLUSIONS: AI chatbots have shown to be efficient tools for retrieving bibliographic references from the web and answering questions related to specific topics such as vaccination. However, it is important to note that they cannot be considered more intelligent than students, as they may not perform as well when faced with situational questions. The responsible and critical use of AI should be integrated into medical education to ensure its effective utilization. KEY MESSAGES: • AI chatbots use as support tool in public health medical training should be further investigated and endorsed. • AI chatbots could be a helpful resource for medical students in terms of researching and revising their knowledge. Oxford University Press 2023-10-24 /pmc/articles/PMC10595493/ http://dx.doi.org/10.1093/eurpub/ckad160.1220 Text en © The Author(s) 2023. Published by Oxford University Press on behalf of the European Public Health Association. https://creativecommons.org/licenses/by-nc/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com
spellingShingle Poster Displays
Baglivo, F
De Angelis, L
Casigliani, V
Arzilli, G
Privitera, G P
Rizzo, C
Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore
title Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore
title_full Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore
title_fullStr Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore
title_full_unstemmed Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore
title_short Artificial Intelligence Chatbots for medical training in Public Health: a tool to explore
title_sort artificial intelligence chatbots for medical training in public health: a tool to explore
topic Poster Displays
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10595493/
http://dx.doi.org/10.1093/eurpub/ckad160.1220
work_keys_str_mv AT baglivof artificialintelligencechatbotsformedicaltraininginpublichealthatooltoexplore
AT deangelisl artificialintelligencechatbotsformedicaltraininginpublichealthatooltoexplore
AT casiglianiv artificialintelligencechatbotsformedicaltraininginpublichealthatooltoexplore
AT arzillig artificialintelligencechatbotsformedicaltraininginpublichealthatooltoexplore
AT priviteragp artificialintelligencechatbotsformedicaltraininginpublichealthatooltoexplore
AT rizzoc artificialintelligencechatbotsformedicaltraininginpublichealthatooltoexplore