Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study

BackgroundThe use of ChatGPT in healthcare is still in its early stages; however, it has the potential to become a cornerstone in modern healthcare systems. This study aims to assess the accuracy of output of ChatGPT compared with those of CareNotes® in providing patient instructions for three medic...

Full description

Saved in:
Bibliographic Details
Main Authors: Norah Othman Abanmy, Nadia Al-Ghreimil, Jawza F. Alsabhan, Heyam Al-Baity, Rana Aljadeed
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1550591/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850275484351332352
author Norah Othman Abanmy
Nadia Al-Ghreimil
Jawza F. Alsabhan
Heyam Al-Baity
Rana Aljadeed
author_facet Norah Othman Abanmy
Nadia Al-Ghreimil
Jawza F. Alsabhan
Heyam Al-Baity
Rana Aljadeed
author_sort Norah Othman Abanmy
collection DOAJ
description BackgroundThe use of ChatGPT in healthcare is still in its early stages; however, it has the potential to become a cornerstone in modern healthcare systems. This study aims to assess the accuracy of output of ChatGPT compared with those of CareNotes® in providing patient instructions for three medications: tirzepatide, citalopram, and apixaban.MethodsAn exploratory case study was conducted using a published questionnaire to evaluate ChatGPT-generated reports against patient instructions from CareNotes®. The evaluation focused on the completeness and correctness of the reports, as well as their potential to cause harm or lead to poor medication adherence. The evaluation was conducted by four pharmacy experts and 33 PharmD interns.ResultsThe evaluators indicated that the ChatGPT reports of tirzepatide, citalopram, and apixaban were correct but lacked completeness. Additionally, ChatGPT reports have the potential to cause harm and may negatively affect medication adherence.ConclusionAlthough ChatGPT demonstrated promising results, particularly in terms of correctness, it cannot yet be considered a reliable standalone source of patient drug information.
format Article
id doaj-art-aee821e12503416eac83620247c754db
institution OA Journals
issn 2624-8212
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-aee821e12503416eac83620247c754db2025-08-20T01:50:42ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-04-01810.3389/frai.2025.15505911550591Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case studyNorah Othman Abanmy0Nadia Al-Ghreimil1Jawza F. Alsabhan2Heyam Al-Baity3Rana Aljadeed4Department of Clinical Pharmacy, College of Pharmacy, King Saud University, Riyadh, Saudi ArabiaInformation Technology Department, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Clinical Pharmacy, College of Pharmacy, King Saud University, Riyadh, Saudi ArabiaInformation Technology Department, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Clinical Pharmacy, College of Pharmacy, King Saud University, Riyadh, Saudi ArabiaBackgroundThe use of ChatGPT in healthcare is still in its early stages; however, it has the potential to become a cornerstone in modern healthcare systems. This study aims to assess the accuracy of output of ChatGPT compared with those of CareNotes® in providing patient instructions for three medications: tirzepatide, citalopram, and apixaban.MethodsAn exploratory case study was conducted using a published questionnaire to evaluate ChatGPT-generated reports against patient instructions from CareNotes®. The evaluation focused on the completeness and correctness of the reports, as well as their potential to cause harm or lead to poor medication adherence. The evaluation was conducted by four pharmacy experts and 33 PharmD interns.ResultsThe evaluators indicated that the ChatGPT reports of tirzepatide, citalopram, and apixaban were correct but lacked completeness. Additionally, ChatGPT reports have the potential to cause harm and may negatively affect medication adherence.ConclusionAlthough ChatGPT demonstrated promising results, particularly in terms of correctness, it cannot yet be considered a reliable standalone source of patient drug information.https://www.frontiersin.org/articles/10.3389/frai.2025.1550591/fullChatGPThealthcare technologypharmacy applicationsdrug informationartificial intelligence
spellingShingle Norah Othman Abanmy
Nadia Al-Ghreimil
Jawza F. Alsabhan
Heyam Al-Baity
Rana Aljadeed
Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study
Frontiers in Artificial Intelligence
ChatGPT
healthcare technology
pharmacy applications
drug information
artificial intelligence
title Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study
title_full Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study
title_fullStr Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study
title_full_unstemmed Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study
title_short Evaluating the accuracy of ChatGPT in delivering patient instructions for medications: an exploratory case study
title_sort evaluating the accuracy of chatgpt in delivering patient instructions for medications an exploratory case study
topic ChatGPT
healthcare technology
pharmacy applications
drug information
artificial intelligence
url https://www.frontiersin.org/articles/10.3389/frai.2025.1550591/full
work_keys_str_mv AT norahothmanabanmy evaluatingtheaccuracyofchatgptindeliveringpatientinstructionsformedicationsanexploratorycasestudy
AT nadiaalghreimil evaluatingtheaccuracyofchatgptindeliveringpatientinstructionsformedicationsanexploratorycasestudy
AT jawzafalsabhan evaluatingtheaccuracyofchatgptindeliveringpatientinstructionsformedicationsanexploratorycasestudy
AT heyamalbaity evaluatingtheaccuracyofchatgptindeliveringpatientinstructionsformedicationsanexploratorycasestudy
AT ranaaljadeed evaluatingtheaccuracyofchatgptindeliveringpatientinstructionsformedicationsanexploratorycasestudy