%0 Journal Article
%@ 1438-8871
%I JMIR Publications
%V 26
%N 
%P e55388
%T Evaluation of Prompts to Simplify Cardiovascular Disease Information Generated Using a Large Language Model: Cross-Sectional Study
%A Mishra,Vishala
%A Sarraju,Ashish
%A Kalwani,Neil M
%A Dexter,Joseph P
%+ Data Science Initiative, Harvard University, Science and Engineering Complex 1.312-10, 150 Western Avenue, Allston, MA, 02134, United States, 1 8023381330, jdexter@fas.harvard.edu
%K artificial intelligence
%K ChatGPT
%K GPT
%K digital health
%K large language model
%K NLP
%K language model
%K language models
%K prompt engineering
%K health communication
%K generative
%K health literacy
%K natural language processing
%K patient-physician communication
%K health communication
%K prevention
%K cardiology
%K cardiovascular
%K heart
%K education
%K educational
%K human-in-the-loop
%K machine learning
%D 2024
%7 22.4.2024
%9 Research Letter
%J J Med Internet Res
%G English
%X 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.
%M 38648104
%R 10.2196/55388
%U https://www.jmir.org/2024/1/e55388
%U https://doi.org/10.2196/55388
%U http://www.ncbi.nlm.nih.gov/pubmed/38648104