Suppr超能文献

Google 翻译在急诊科医嘱中的实用性评估。

A Pragmatic Assessment of Google Translate for Emergency Department Instructions.

机构信息

Olive View-UCLA Medical Center, Sylmar, CA, USA.

Memorial Sloan Kettering Cancer Center, New York, NY, USA.

出版信息

J Gen Intern Med. 2021 Nov;36(11):3361-3365. doi: 10.1007/s11606-021-06666-z. Epub 2021 Mar 5.

Abstract

BACKGROUND

Because many hospitals have no mechanism for written translation, ED providers resort to the use of automated translation software, such as Google Translate (GT) for patient instructions. A recent study of discharge instructions in Spanish and Chinese suggested that accuracy rates of Google Translate (GT) were high.

STUDY OBJECTIVE

To perform a pragmatic assessment of GT for the written translation of commonly used ED discharge instructions in seven commonly spoken languages.

METHODS

A prospective assessment of the accuracy of GT for 20 commonly used ED discharge instruction phrases, as evaluated by a convenience sample of native speakers of seven commonly spoken languages (Spanish, Chinese, Vietnamese, Tagalog, Korean, Armenian, and Farsi). Translations were evaluated using a previously validated matrix for scoring machine translation, containing 5-point Likert scales for fluency, adequacy, meaning, and severity, in addition to a dichotomous assessment of retention of the overall meaning.

RESULTS

Twenty volunteers evaluated 400 google translated discharge statements. Volunteers were 50% female and spoke Spanish (5), Armenian (2), Chinese (3), Tagalog (4), Korean (2), and Farsi (2). The overall meaning was retained for 82.5% (330/400) of the translations. Spanish had the highest accuracy rate (94%), followed by Tagalog (90%), Korean (82.5%), Chinese (81.7%), Farsi (67.5%), and Armenian (55%). Mean Likert scores (on a 5-point scale) were high for fluency (4.2), adequacy (4.4), meaning (4.3), and severity (4.3) but also varied.

CONCLUSION

GT for discharge instructions in the ED is inconsistent between languages and should not be relied on for patient instructions.

摘要

背景

由于许多医院没有书面翻译机制,急诊医生只能使用自动化翻译软件,例如 Google 翻译(GT)来为患者提供医嘱。最近一项关于西班牙语和中文出院医嘱的研究表明,GT 的准确率很高。

研究目的

对 GT 在七种常用语言中翻译常用急诊出院医嘱的能力进行实用性评估。

方法

采用便利抽样法,选取七种常用语言(西班牙语、中文、越南语、塔加洛语、韩语、亚美尼亚语和波斯语)的母语者,对 GT 翻译的 20 个常用 ED 出院医嘱的准确性进行前瞻性评估。使用先前验证过的机器翻译评分矩阵来评估翻译,该矩阵包含 5 分制的流利度、充分性、含义和严重程度评分,以及对整体含义保留的二分评估。

结果

20 名志愿者评估了 400 个谷歌翻译的出院陈述。志愿者中 50%为女性,分别来自西班牙语(5 人)、亚美尼亚语(2 人)、中文(3 人)、塔加洛语(4 人)、韩语(2 人)和波斯语(2 人)。82.5%(330/400)的翻译保留了整体含义。西班牙语的准确率最高(94%),其次是塔加洛语(90%)、韩语(82.5%)、中文(81.7%)、波斯语(67.5%)和亚美尼亚语(55%)。流利度(4.2)、充分性(4.4)、含义(4.3)和严重程度(4.3)的平均 Likert 评分都很高,但也存在差异。

结论

GT 翻译 ED 出院医嘱的能力在不同语言之间不一致,不能依赖 GT 为患者提供医嘱。

相似文献

1
A Pragmatic Assessment of Google Translate for Emergency Department Instructions.
J Gen Intern Med. 2021 Nov;36(11):3361-3365. doi: 10.1007/s11606-021-06666-z. Epub 2021 Mar 5.
2
3
5
Evaluating the Accuracy of Google Translate for Diabetes Education Material.
JMIR Diabetes. 2016 Jun 28;1(1):e3. doi: 10.2196/diabetes.5848.
6
Translating Discharge Instructions for Limited English-Proficient Families: Strategies and Barriers.
Hosp Pediatr. 2019 Oct;9(10):779-787. doi: 10.1542/hpeds.2019-0055.
7
Evaluating the impact of translated written discharge instructions for patients with limited English language proficiency.
Int J Pediatr Otorhinolaryngol. 2018 Aug;111:75-79. doi: 10.1016/j.ijporl.2018.05.031. Epub 2018 May 26.
10
Pediatric Emergency Department Discharge Instructions for Spanish-Speaking Families: Are We Getting It Right?
Pediatr Emerg Care. 2022 Feb 1;38(2):e867-e870. doi: 10.1097/PEC.0000000000002470.

引用本文的文献

1
Unveiling the gaps: A comprehensive, equity-focused observational examination of Emergency Department discharge.
PLoS One. 2025 Aug 28;20(8):e0331226. doi: 10.1371/journal.pone.0331226. eCollection 2025.
2
Scoping Review of Adult Emergency Department Discharge Interventions.
West J Emerg Med. 2025 Jul 13;26(4):823-834. doi: 10.5811/westjem.35264.
6
Usability of technological tools to overcome language barriers in healthcare- a scoping review.
Arch Public Health. 2025 Feb 25;83(1):52. doi: 10.1186/s13690-025-01543-1.
8
What makes a 'good' decision with artificial intelligence? A grounded theory study in paediatric care.
BMJ Evid Based Med. 2025 May 20;30(3):183-193. doi: 10.1136/bmjebm-2024-112919.
9
Artificial Intelligence-Driven Translation Tools in Intensive Care Units for Enhancing Communication and Research.
Int J Environ Res Public Health. 2025 Jan 12;22(1):95. doi: 10.3390/ijerph22010095.
10
Victorian Institute of Sport Assessment questionnaire specifically tailored for greater trochanteric pain syndrome for the Dutch population.
J Hip Preserv Surg. 2024 Aug 28;11(4):257-262. doi: 10.1093/jhps/hnae026. eCollection 2024 Dec.

本文引用的文献

1
The factor structure of a short acculturation scale for Filipino Americans in an adult U.S.-born sample.
J Community Psychol. 2018 Jul;46(5):535-550. doi: 10.1002/jcop.21955. Epub 2018 May 21.
2
3
Evaluating the Accuracy of Google Translate for Diabetes Education Material.
JMIR Diabetes. 2016 Jun 28;1(1):e3. doi: 10.2196/diabetes.5848.
4
The Association Between Limited English Proficiency and Unplanned Emergency Department Revisit Within 72 Hours.
Ann Emerg Med. 2016 Aug;68(2):213-21. doi: 10.1016/j.annemergmed.2016.02.042. Epub 2016 Mar 29.
5
Use of Google Translate in medical communication: evaluation of accuracy.
BMJ. 2014 Dec 15;349:g7392. doi: 10.1136/bmj.g7392.
6
Hospital language service programs: a closer look at translation practices.
J Health Care Poor Underserved. 2014 Nov;25(4):2003-18. doi: 10.1353/hpu.2014.0162.
7
Parental language and dosing errors after discharge from the pediatric emergency department.
Pediatr Emerg Care. 2013 Sep;29(9):982-7. doi: 10.1097/PEC.0b013e3182a269ec.
8
Using machine translation in clinical practice.
Can Fam Physician. 2013 Apr;59(4):382-3.
9
Language barriers and understanding of hospital discharge instructions.
Med Care. 2012 Apr;50(4):283-9. doi: 10.1097/MLR.0b013e318249c949.
10
Try Google Translate to overcome language barriers.
BMJ. 2011 Nov 15;343:d7217. doi: 10.1136/bmj.d7217.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验