The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents

The popularization of large language chatbots such as ChatGPT has led to growing utility in various biomedical fields. It has been shown that chatbots can provide reasonably accurate responses to medical exam style questions. On the other hand, chatbots have known limitations which may hinder their...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaosheng Jin, Ramon Abola, Vincent Bargnes, Alexandra Tsivitis, Sadiq Rahman, Jonathon Schwartz, Sergio D. Bergese, Joy E. Schabel
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-05-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1582096/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850261621545369600
author Zhaosheng Jin
Ramon Abola
Vincent Bargnes
Alexandra Tsivitis
Sadiq Rahman
Jonathon Schwartz
Sergio D. Bergese
Joy E. Schabel
author_facet Zhaosheng Jin
Ramon Abola
Vincent Bargnes
Alexandra Tsivitis
Sadiq Rahman
Jonathon Schwartz
Sergio D. Bergese
Joy E. Schabel
author_sort Zhaosheng Jin
collection DOAJ
description The popularization of large language chatbots such as ChatGPT has led to growing utility in various biomedical fields. It has been shown that chatbots can provide reasonably accurate responses to medical exam style questions. On the other hand, chatbots have known limitations which may hinder their utility in medical education. We conducted a pragmatically designed study to evaluate the accuracy and completeness of ChatGPT generated responses to various styles of prompts, based on entry-level anesthesiology topics. Ninety-five unique prompts were constructed using topics from the Anesthesia Knowledge Test 1 (AKT-1), a standardized exam undertaken by US anesthesiology residents after 1 month of specialty training. A combination of focused and open-ended prompts was used to evaluate its ability to present and organize information. We also included prompts for journal references, lecture outlines, as well as biased (medically inaccurate) prompts. The responses were independently scored using a 3-point Likert scale, by two board-certified anesthesiologists with extensive experience in medical education. Fifty-two (55%) responses were rated as completely accurate by both evaluators. For longer responses prompts, most of the responses were also deemed complete. Notably, the chatbot frequently generated inaccurate responses when asked for specific literature references and when the input prompt contained deliberate errors (biased prompts). Another recurring observation was the conflation of adjacent concepts (e.g., a specific characteristic was attributed to the wrong drug under the same pharmacological class). Some of the inaccuracies could potentially result in significant harm if applied to clinical situations. While chatbots such as ChatGPT can generate medically accurate responses in most cases, its reliability is not yet suited for medical and clinical education. Content generated by ChatGPT and other chatbots will require validation prior to use.
format Article
id doaj-art-5f4a5ecf49dc49c5a16f65ac0b3450d0
institution OA Journals
issn 2624-8212
language English
publishDate 2025-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-5f4a5ecf49dc49c5a16f65ac0b3450d02025-08-20T01:55:21ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-05-01810.3389/frai.2025.15820961582096The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residentsZhaosheng JinRamon AbolaVincent BargnesAlexandra TsivitisSadiq RahmanJonathon SchwartzSergio D. BergeseJoy E. SchabelThe popularization of large language chatbots such as ChatGPT has led to growing utility in various biomedical fields. It has been shown that chatbots can provide reasonably accurate responses to medical exam style questions. On the other hand, chatbots have known limitations which may hinder their utility in medical education. We conducted a pragmatically designed study to evaluate the accuracy and completeness of ChatGPT generated responses to various styles of prompts, based on entry-level anesthesiology topics. Ninety-five unique prompts were constructed using topics from the Anesthesia Knowledge Test 1 (AKT-1), a standardized exam undertaken by US anesthesiology residents after 1 month of specialty training. A combination of focused and open-ended prompts was used to evaluate its ability to present and organize information. We also included prompts for journal references, lecture outlines, as well as biased (medically inaccurate) prompts. The responses were independently scored using a 3-point Likert scale, by two board-certified anesthesiologists with extensive experience in medical education. Fifty-two (55%) responses were rated as completely accurate by both evaluators. For longer responses prompts, most of the responses were also deemed complete. Notably, the chatbot frequently generated inaccurate responses when asked for specific literature references and when the input prompt contained deliberate errors (biased prompts). Another recurring observation was the conflation of adjacent concepts (e.g., a specific characteristic was attributed to the wrong drug under the same pharmacological class). Some of the inaccuracies could potentially result in significant harm if applied to clinical situations. While chatbots such as ChatGPT can generate medically accurate responses in most cases, its reliability is not yet suited for medical and clinical education. Content generated by ChatGPT and other chatbots will require validation prior to use.https://www.frontiersin.org/articles/10.3389/frai.2025.1582096/fullartificial intelligencegraduate medical educationlarge language modelanesthesiology residencygenerative AI
spellingShingle Zhaosheng Jin
Ramon Abola
Vincent Bargnes
Alexandra Tsivitis
Sadiq Rahman
Jonathon Schwartz
Sergio D. Bergese
Joy E. Schabel
The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents
Frontiers in Artificial Intelligence
artificial intelligence
graduate medical education
large language model
anesthesiology residency
generative AI
title The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents
title_full The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents
title_fullStr The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents
title_full_unstemmed The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents
title_short The utility of generative artificial intelligence Chatbot (ChatGPT) in generating teaching and learning material for anesthesiology residents
title_sort utility of generative artificial intelligence chatbot chatgpt in generating teaching and learning material for anesthesiology residents
topic artificial intelligence
graduate medical education
large language model
anesthesiology residency
generative AI
url https://www.frontiersin.org/articles/10.3389/frai.2025.1582096/full
work_keys_str_mv AT zhaoshengjin theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT ramonabola theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT vincentbargnes theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT alexandratsivitis theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT sadiqrahman theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT jonathonschwartz theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT sergiodbergese theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT joyeschabel theutilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT zhaoshengjin utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT ramonabola utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT vincentbargnes utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT alexandratsivitis utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT sadiqrahman utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT jonathonschwartz utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT sergiodbergese utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents
AT joyeschabel utilityofgenerativeartificialintelligencechatbotchatgptingeneratingteachingandlearningmaterialforanesthesiologyresidents