Full text

Turn on search term navigation

© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

Background: This study evaluates the potential of ChatGPT and Google Bard as educational tools for patients in orthopedics, focusing on sports medicine and pediatric orthopedics. The aim is to compare the quality of responses provided by these natural language processing (NLP) models, addressing concerns about the potential dissemination of incorrect medical information. Methods: Ten ACL- and flat foot-related questions from a Google search were presented to ChatGPT-3.5 and Google Bard. Expert orthopedic surgeons rated the responses using the Global Quality Score (GQS). The study minimized bias by clearing chat history before each question, maintaining respondent anonymity and employing statistical analysis to compare response quality. Results: ChatGPT-3.5 and Google Bard yielded good-quality responses, with average scores of 4.1 ± 0.7 and 4 ± 0.78, respectively, for sports medicine. For pediatric orthopedics, Google Bard scored 3.5 ± 1, while the average score for responses generated by ChatGPT was 3.8 ± 0.83. In both cases, no statistically significant difference was found between the platforms (p = 0.6787, p = 0.3092). Despite ChatGPT’s responses being considered more readable, both platforms showed promise for AI-driven patient education, with no reported misinformation. Conclusions: ChatGPT and Google Bard demonstrate significant potential as supplementary patient education resources in orthopedics. However, improvements are needed for increased reliability. The study underscores the evolving role of AI in orthopedics and calls for continued research to ensure a conscientious integration of AI in healthcare education.

Details

Title
Google Bard and ChatGPT in Orthopedics: Which Is the Better Doctor in Sports Medicine and Pediatric Orthopedics? The Role of AI in Patient Education
Author
Giorgino, Riccardo 1   VIAFID ORCID Logo  ; Alessandri-Bonetti, Mario 2   VIAFID ORCID Logo  ; Matteo Del Re 3 ; Verdoni, Fabio 3 ; Peretti, Giuseppe M 4   VIAFID ORCID Logo  ; Mangiavini, Laura 4 

 Residency Program in Orthopaedics and Traumatology, University of Milan, 20122 Milan, Italy; IRCCS Ospedale Galeazzi Sant’ambrogio, 20157 Milan, Italy; [email protected] (M.D.R.); [email protected] (F.V.); [email protected] (G.M.P.); [email protected] (L.M.) 
 Department of Plastic Surgery, University of Pittsburgh Medical Center, 1350 Locust Street, Pittsburgh, PA 15213, USA; [email protected] 
 IRCCS Ospedale Galeazzi Sant’ambrogio, 20157 Milan, Italy; [email protected] (M.D.R.); [email protected] (F.V.); [email protected] (G.M.P.); [email protected] (L.M.) 
 IRCCS Ospedale Galeazzi Sant’ambrogio, 20157 Milan, Italy; [email protected] (M.D.R.); [email protected] (F.V.); [email protected] (G.M.P.); [email protected] (L.M.); Department of Biomedical Sciences for Health, University of Milan, 20122 Milan, Italy 
First page
1253
Publication year
2024
Publication date
2024
Publisher
MDPI AG
e-ISSN
20754418
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3072305375
Copyright
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.