{"title":"Using ChatGPT and Google Bard to improve the readability of written patient information: a proof of concept.","authors":"Philip Moons, Liesbet Van Bulck","doi":"10.1093/eurjcn/zvad087","DOIUrl":null,"url":null,"abstract":"<p><p>Patient information materials often tend to be written at a reading level that is too advanced for patients. In this proof-of-concept study, we used ChatGPT and Google Bard to reduce the reading level of three selected patient information sections from scientific journals. ChatGPT successfully improved readability. However, it could not achieve the recommended 6th-grade reading level. Bard reached the reading level of 6th graders but oversimplified the texts by omitting up to 83% of the content. Despite the present limitations, developers of patient information are encouraged to employ large language models, preferably ChatGPT, to optimize their materials.</p>","PeriodicalId":50493,"journal":{"name":"European Journal of Cardiovascular Nursing","volume":null,"pages":null},"PeriodicalIF":2.9000,"publicationDate":"2024-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European Journal of Cardiovascular Nursing","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/eurjcn/zvad087","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Patient information materials often tend to be written at a reading level that is too advanced for patients. In this proof-of-concept study, we used ChatGPT and Google Bard to reduce the reading level of three selected patient information sections from scientific journals. ChatGPT successfully improved readability. However, it could not achieve the recommended 6th-grade reading level. Bard reached the reading level of 6th graders but oversimplified the texts by omitting up to 83% of the content. Despite the present limitations, developers of patient information are encouraged to employ large language models, preferably ChatGPT, to optimize their materials.
期刊介绍:
The peer-reviewed journal of the European Society of Cardiology’s Council on Cardiovascular Nursing and Allied Professions (CCNAP) covering the broad field of cardiovascular nursing including chronic and acute care, cardiac rehabilitation, primary and secondary prevention, heart failure, acute coronary syndromes, interventional cardiology, cardiac care, and vascular nursing.