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

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

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

Afiliação

Mishra V; Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC, United States.
Sarraju A; Department of Cardiovascular Medicine, Cleveland Clinic, Cleveland, OH, United States.
Kalwani NM; Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, United States.
Dexter JP; Division of Cardiovascular Medicine and the Cardiovascular Institute, Department of Medicine, Stanford University School of Medicine, Stanford, CA, United States.

J Med Internet Res ; 26: e55388, 2024 Apr 22.

Article em En | MEDLINE | ID: mdl-38648104

ABSTRACT

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.

Assuntos

Doenças Cardiovasculares; Estudos Transversais; Humanos; Idioma

Palavras-chave

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

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google

Texto completo: 1 Coleções: 01-internacional Contexto em Saúde: 2_ODS3 Base de dados: MEDLINE Assunto principal: Doenças Cardiovasculares Limite: Humans Idioma: En Revista: J Med Internet Res Ano de publicação: 2024 Tipo de documento: Article

Texto completo

Imprimir

XML

PubMed Links

Buscar no Google