Asset Details
Do you wish to reserve the book?
3555 Neurology resident and fellow teaching cases can be delivered in an interactive format with artificial intelligence
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
3555 Neurology resident and fellow teaching cases can be delivered in an interactive format with artificial intelligence
Do you wish to request the book?
3555 Neurology resident and fellow teaching cases can be delivered in an interactive format with artificial intelligence
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
3555 Neurology resident and fellow teaching cases can be delivered in an interactive format with artificial intelligence
2025
Overview
Background/ObjectivesEducational cases and case reports may be published in a variety of formats. These lexical differences could influence the effectiveness of large language models (LLMs) in the conversion of such cases into an interactive format. This research aimed to assess whether LLMs, a type of artificial intelligence (AI), could effectively transform existing Neurology Resident & Fellow Section Case-based Articles (RFS-CBA) into interactive digital content.MethodsUsing an LLM, researchers converted three RFS-CBA articles into narrative ‘screenplays’ using Anthropic’s Claude 3.5 Sonnet. These screenplays were then implemented on an online platform powered by GPT-4 to create interactive experiences. Two neurology fellows tested the system by engaging with the cases through questions and answers, gathering patient histories, physical examination data, and test results to develop diagnoses and treatment strategies. A neurologist subsequently reviewed all question-answer exchanges.ResultsThe system provided appropriate responses in 206 out of 210 instances (98.1%). In 26 of 210 responses, the LLM generated additional information beyond the original content, all of which was considered medically sound and contextually appropriate. The four observed errors consisted of missing investigation results during the ‘screenplay’ creation phase, a type of mistake that can be easily fixed through manual review.ConclusionConverting RFS-CBA into an interactive question-and-answer format using LLMs is viable. Additional research is needed to evaluate the educational impact of this teaching approach.
Publisher
BMJ Publishing Group LTD
Subject
