Evaluation of Prompts to Simplify Cardiovascular Disease Information Generated Using a Large Language Model: Cross-Sectional Study

In this cross-sectional study, we evaluated the completeness, readability, and syntactic complexity of cardiovascular disease prevention information produced by GPT-4 in response to 4 kinds of prompts.

Saved in:
Bibliographic Details
Published inJournal of medical Internet research Vol. 26; no. 1; p. e55388
Main Authors Mishra, Vishala, Sarraju, Ashish, Kalwani, Neil M, Dexter, Joseph P
Format Journal Article
LanguageEnglish
Published Canada Journal of Medical Internet Research 22.04.2024
JMIR Publications
Subjects
Analysis
Cardiovascular Diseases
Cross-Sectional Studies
Diagnosis
Humans
Language
Literacy
Medical advice systems
Patient education
Research Letter
prompt engineering
education
educational
natural language processing
GPT
language model
human-in-the-loop
cardiovascular
large language model
machine learning
artificial intelligence
cardiology
heart
generative
patient-physician communication
NLP
digital health
health literacy
ChatGPT
health communication
language models
prevention
Online AccessGet full text

Cover

More Information
Summary:In this cross-sectional study, we evaluated the completeness, readability, and syntactic complexity of cardiovascular disease prevention information produced by GPT-4 in response to 4 kinds of prompts.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1438-8871
1439-4456
1438-8871
DOI:10.2196/55388