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

Vishala Mishra; Ashish Sarraju; Neil M Kalwani; Joseph P Dexter

doi:10.2196/55388

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

J Med Internet Res. 2024 Apr 22:26:e55388. doi: 10.2196/55388.

Authors

Vishala Mishra^#¹, Ashish Sarraju², Neil M Kalwani^{3

4}, Joseph P Dexter^#^{5

6

7}

Affiliations

¹ Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, United States.
² Department of Cardiovascular Medicine, Cleveland Clinic, Cleveland, OH, United States.
³ Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, United States.
⁴ Division of Cardiovascular Medicine and the Cardiovascular Institute, Department of Medicine, Stanford University School of Medicine, Stanford, CA, United States.
⁵ Data Science Initiative, Harvard University, Allston, MA, United States.
⁶ Department of Human Evolutionary Biology, Harvard University, Cambridge, MA, United States.
⁷ Institute of Collaborative Innovation, University of Macau, Taipa, Macao.

^# Contributed equally.

PMID: 38648104
PMCID: PMC11074888
DOI: 10.2196/55388

Abstract

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.

Keywords: ChatGPT; GPT; NLP; artificial intelligence; cardiology; cardiovascular; digital health; education; educational; generative; health communication; health literacy; heart; human-in-the-loop; language model; language models; large language model; machine learning; natural language processing; patient-physician communication; prevention; prompt engineering.

©Vishala Mishra, Ashish Sarraju, Neil M Kalwani, Joseph P Dexter. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 22.04.2024.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Cardiovascular Diseases*
Cross-Sectional Studies
Humans
Language