» Articles » PMID: 38313589

Validation of ChatGPT 3.5 As a Tool to Optimize Readability of Patient-facing Craniofacial Education Materials

Overview
Specialty General Surgery
Date 2024 Feb 5
PMID 38313589
Authors
Affiliations
Soon will be listed here.
Abstract

Background: To address patient health literacy, the American Medical Association recommends that readability of patient education materials should not exceed a sixth grade reading level; the National Institutes of Health recommend no greater than an eigth-grade reading level. However, patient-facing materials in plastic surgery often remain at an above-recommended average reading level. The purpose of this study was to evaluate ChatGPT 3.5 as a tool for optimizing patient-facing craniofacial education materials.

Methods: Eighteen patient-facing craniofacial education materials were evaluated for readability by a traditional calculator and ChatGPT 3.5. The resulting scores were compared. The original excerpts were then inputted to ChatGPT 3.5 and simplified by the artificial intelligence tool. The simplified excerpts were scored by the calculators.

Results: The difference in scores for the original excerpts between the online calculator and ChatGPT 3.5 were not significant ( = 0.441). Additionally, the simplified excerpts' scores were significantly lower than the originals ( < 0.001), and the mean of the simplified excerpts was 7.78, less than the maximum recommended 8.

Conclusions: The use of ChatGPT 3.5 for simplification and readability analysis of patient-facing craniofacial materials is efficient and may help facilitate the conveyance of important health information. ChatGPT 3.5 rendered readability scores comparable to traditional readability calculators, in addition to excerpt-specific feedback. It was also able to simplify materials to the recommended grade levels. With human oversight, we validate this tool for readability analysis and simplification.

Citing Articles

Large language models in patient education: a scoping review of applications in medicine.

Aydin S, Karabacak M, Vlachos V, Margetis K Front Med (Lausanne). 2024; 11:1477898.

PMID: 39534227 PMC: 11554522. DOI: 10.3389/fmed.2024.1477898.


Large Language Models for Intraoperative Decision Support in Plastic Surgery: A Comparison between ChatGPT-4 and Gemini.

Gomez-Cabello C, Borna S, Pressman S, Haider S, Forte A Medicina (Kaunas). 2024; 60(6).

PMID: 38929573 PMC: 11205293. DOI: 10.3390/medicina60060957.


Artificial Intelligence in Postoperative Care: Assessing Large Language Models for Patient Recommendations in Plastic Surgery.

Gomez-Cabello C, Borna S, Pressman S, Haider S, Sehgal A, Leibovich B Healthcare (Basel). 2024; 12(11).

PMID: 38891158 PMC: 11171524. DOI: 10.3390/healthcare12111083.


Analysis of the Most Popular Online Ankle Fracture-Related Patient Education Materials.

Arif H, LeBrun G, Moore S, Friscia D Foot Ankle Orthop. 2024; 9(2):24730114241241310.

PMID: 38577700 PMC: 10989055. DOI: 10.1177/24730114241241310.

References
1.
Seth A, Vargas C, Chuang D, Lee B . Readability Assessment of Patient Information about Lymphedema and Its Treatment. Plast Reconstr Surg. 2016; 137(2):287e-295e. DOI: 10.1097/01.prs.0000475747.95096.ab. View

2.
Para A, Thelmo F, Rynecki N, Zelman B, Gupta R, Coban D . Evaluating the Readability of Online Patient Education Materials Related to Orthopedic Oncology. Orthopedics. 2020; 44(1):38-42. DOI: 10.3928/01477447-20201012-04. View

3.
Vargas C, Ricci J, Lee M, Tobias A, Medalie D, Lee B . The accessibility, readability, and quality of online resources for gender affirming surgery. J Surg Res. 2017; 217:198-206. DOI: 10.1016/j.jss.2017.05.026. View

4.
Patel A, Joshi C, Varghese J, Hassan A, Janis J, Galiano R . Do Websites Serve Our Patients Well? A Comparative Analysis of Online Information on Cosmetic Injectables. Plast Reconstr Surg. 2022; 149(4):655e-668e. DOI: 10.1097/PRS.0000000000008921. View

5.
Greene S, Tuzzio L, Cherkin D . A framework for making patient-centered care front and center. Perm J. 2012; 16(3):49-53. PMC: 3442762. DOI: 10.7812/TPP/12-025. View