Hostname: page-component-78c5997874-fbnjt Total loading time: 0 Render date: 2024-11-09T13:51:49.129Z Has data issue: false hasContentIssue false

Using Artificial Intelligence to Develop Educational Content for Teaching Children on Cardiopulmonary Resuscitation

Published online by Cambridge University Press:  05 September 2023

Alexei A. Birkun*
Affiliation:
Department of General Surgery, Anesthesiology, Resuscitation and Emergency Medicine, Medical Academy named after S.I. Georgievsky of V.I. Vernadsky Crimean Federal University, Simferopol, Russian Federation
*
Correspondence: Alexei A. Birkun, MD, DMedSc Lenin Blvd, 5/7, Simferopol, 295051 Russian Federation E-mail: [email protected]
Rights & Permissions [Opens in a new window]

Abstract

Type
Article Commentary
Copyright
© The Author(s), 2023. Published by Cambridge University Press on behalf of the World Association for Disaster and Emergency Medicine

Dear Editor,

Children make up around 25% of the total world population and therefore constitute a colossal (two-billion) 1 contingent of potential rescuers that could greatly enhance community response in out-of-hospital cardiac arrest (OHCA). Considering the high motivation of children to learn cardiopulmonary resuscitation (CPR) and their ability to transfer the life-saving competencies to other people, teaching all school children in resuscitation is currently strongly endorsed by international health organizations as one of the key public initiatives for improving bystander CPR rates and survival after OHCA. Reference Böttiger and Van Aken2,Reference Schroeder, Semeraro and Greif3

In 2015, it has been recommended to teach school children in resuscitation annually from the age of 12 years or less. Reference Böttiger and Van Aken2 A recent scientific statement by the International Liaison Committee on Resuscitation Reference Schroeder, Semeraro and Greif3 suggests that children should be taught basic theoretical concepts of OHCA response beginning from the preschool age (four years old and above).

Apparently, world-wide implementation of CPR education for children of various ages necessitates tremendous organizational efforts. One of the major tasks involves development of age-appropriate training curriculum and educational materials that should be adopted to cultural, social, and economic contexts of specific countries. This challenge is associated with expenditure of time and money, and therefore may constitute a barrier for wide-spread introduction of CPR education for children, especially in resource-limited settings. Reference De Buck, Laermans, Vanhove, Dockx, Vandekerckhove and Geduld4

Today, artificial intelligence (AI) chatbots powered with Generative Pre-Trained Transformer (GPT) models garner great public and researcher attention. Being trained on a large dataset of text in multiple languages, these models can produce highly sophisticated human-like responses based on a context of input text. Reference Sallam5 Free GPT chatbots, including ChatGPT (OpenAI; San Fransico, California USA) and the new Bing (Microsoft Corporation; Redmond, Washington USA), became extremely popular due to their impressive capabilities for solving a range of language-based tasks, including question answering, machine translation, and text generation. Reference Sallam5 From the resuscitation education perspective, it seems important and timely to explore the potential of using the AI-chatbots for developing educational materials on CPR.

In May 2023, the new Bing chatbot was queried: “Propose 10 types of educational materials to teach children on CPR that Bing chatbot can create.” The chatbot responded with a list of educational materials ranging from a song explaining the steps of CPR to a programming code generating random CPR scenarios and challenges to solve (Table 1). When asked to create certain materials, it showed an impressive ability to comprehend a query and generate age-appropriate textual content summarizing key points of resuscitation. This suggests rather promising opportunities to use the chatbot for composing valuable educational resources, along with anticipated time and cost savings that could expedite implementation of CPR education for children.

Table 1. Examples of Application of the Artificial Intelligence-Based Chatbot for Generating Educational Materials on CPR

Note: The new Bing chatbot generates its responses using a text-based interface and does not generate non-textual content like videos. Instead, it creates detailed text description of how to design the non-textual content (eg, video script).

Abbreviation: CPR, cardiopulmonary resuscitation.

However, it is important to bear in mind that the GPT-based chatbots are a kind of “black box technology” that can give plausible-sounding but incorrect responses. Reference Sallam5 Therefore, the AI-generated content should always be meticulously reviewed and verified by a human expert before its intended use. Further research is required to determine the best practices for using the cutting-edge GPT-powered chatbots in a safe and responsible way with the aim of promoting resuscitation education across the world.

Conflicts of interest

The author declares none.

References

Statista. Total number of people aged 0 to 14 worldwide from 1950 to 2100 (in billions). https://www.statista.com/statistics/678737/total-number-of-children-worldwide/. Accessed June 17, 2023 Google Scholar
Böttiger, BW, Van Aken, H. Kids save lives--training school children in cardiopulmonary resuscitation worldwide is now endorsed by the World Health Organization (WHO). Resuscitation. 2015;94:A5A7.CrossRefGoogle ScholarPubMed
Schroeder, DC, Semeraro, F, Greif, R, et al. KIDS SAVE LIVES: Basic Life Support education for schoolchildren: a narrative review and scientific statement from the International Liaison Committee on Resuscitation. Resuscitation. 2023;188:109772.CrossRefGoogle ScholarPubMed
De Buck, E, Laermans, J, Vanhove, AC, Dockx, K, Vandekerckhove, P, Geduld, H. An educational pathway and teaching materials for first aid training of children in sub-Saharan Africa based on the best available evidence. BMC Public Health. 2020;20:836.CrossRefGoogle ScholarPubMed
Sallam, M. ChatGPT utility in health care education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). 2023;11:887.CrossRefGoogle ScholarPubMed
Figure 0

Table 1. Examples of Application of the Artificial Intelligence-Based Chatbot for Generating Educational Materials on CPR