■这项研究的目的是评估生成预训练变压器-4(GPT-4)生成的放电指令在预设阅读水平下的完整性和可读性,以用于常见的儿科急诊室投诉。
■按阅读水平(五年级或八年级)和语言(英语,西班牙语)使用GPT-4产生五倍。具体来说,制作并分析了120份出院说明(6种情况:60份英文,西班牙语60;五年级阅读水平60,八年级阅读水平为60),并比较了完整性和可读性(在语言之间,在阅读水平之间,并按小组和阅读水平分层)。完整性定义为出院说明中包含的文献衍生关键点的比例。可读性使用Flesch-Kincaid(英语)和Fernandez-Huerta(西班牙语)可读性评分进行量化。
■英语GPT生成的放电指令包含的必须包括放电指令的比例明显高于西班牙语(英语:平均值(平均值的标准误差)=62%(3%),西班牙语:53%(3%),P=.02)。在五年级和八年级的条件下,英语和西班牙语输出的完整性没有显着差异。不同语言的可读性没有差异。
■GPT-4在调节文档阅读水平的同时,用英语和西班牙语制作了可读的放电说明。英语的放电指令往往比西班牙语的指令具有更高的完整性。
■在快速工程和GPT-4性能方面的未来研究,一般和多种语言,需要通过语言和阅读水平来减少健康差异的可能性。
UNASSIGNED: The aim of this study was to assess the completeness and readability of generative pre-trained transformer-4 (GPT-4)-generated discharge instructions at prespecified reading levels for common pediatric emergency room complaints.
UNASSIGNED: The outputs for 6 discharge scenarios stratified by reading level (fifth or eighth grade) and language (English, Spanish) were generated fivefold using GPT-4. Specifically, 120 discharge instructions were produced and analyzed (6 scenarios: 60 in English, 60 in Spanish; 60 at a fifth-grade reading level, 60 at an eighth-grade reading level) and compared for completeness and readability (between language, between reading level, and stratified by group and reading level). Completeness was defined as the proportion of literature-derived key points included in discharge instructions. Readability was quantified using Flesch-Kincaid (English) and Fernandez-Huerta (Spanish) readability scores.
UNASSIGNED: English-language GPT-generated discharge instructions contained a significantly higher proportion of must-include discharge instructions than those in Spanish (English: mean (standard error of the mean) = 62% (3%), Spanish: 53% (3%), P = .02). In the fifth-grade and eighth-grade level conditions, there was no significant difference between English and Spanish outputs in completeness. Readability did not differ across languages.
UNASSIGNED: GPT-4 produced readable discharge instructions in English and Spanish while modulating document reading level. Discharge instructions in English tended to have higher completeness than those in Spanish.
UNASSIGNED: Future research in prompt engineering and GPT-4 performance, both generally and in multiple languages, is needed to reduce potential for health disparities by language and reading level.