Ariana Genovese, Sahar Borna, Cesar A Gomez-Cabello, Syed Ali Haider, Srinivasagam Prabha, Antonio J Forte, Benjamin R Veenstra
{"title":"临床环境中的人工智能:对其在语言翻译和口译中的作用的系统回顾。","authors":"Ariana Genovese, Sahar Borna, Cesar A Gomez-Cabello, Syed Ali Haider, Srinivasagam Prabha, Antonio J Forte, Benjamin R Veenstra","doi":"10.21037/atm-24-162","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Addressing language barriers through accurate interpretation is crucial for providing quality care and establishing trust. While the ability of artificial intelligence (AI) to translate medical documentation has been studied, its role for patient-provider communication is less explored. This review evaluates AI's effectiveness in clinical translation by assessing accuracy, usability, satisfaction, and feedback on its use.</p><p><strong>Methods: </strong>A systematic search was conducted on July 11, 2024, across Cumulated Index in Nursing and Allied Health Literature (CINAHL), Institute of Electrical and Electronics Engineers (IEEE) Xplore, PubMed, Scopus, Web of Science, and Google Scholar. Inclusion criteria required AI to translate clinical information for a real or theoretical consultation. Exclusion criteria included reviews, correspondence, educational materials, non-peer-reviewed or retracted reports, non-English translations, pre-2016 publications, and reports on sign language or patient education. Search strings representing AI, language interpretation, and healthcare were used. Two investigators independently conducted the screening, extraction, synthesis of results, and bias assessments using Risk Of Bias In Non-randomized Studies - of Interventions (ROBINS-I), Mixed Methods Appraisal Tool (MMAT), and the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Qualitative Research. A third investigator resolved conflicts.</p><p><strong>Results: </strong>Of 1,095 reports, 9 studies were analyzed, evaluating AI translation platforms Google Translate, Microsoft Translator, Apple iTranslate, AwezaMed, Pocketalk W, and the Asynchronous Telepsychiatry (ATP) App. Investigations occurred in the US, France, Switzerland, and South Africa, with publications from 2019-2024. AI medical translation shows promise, typically providing accurate translations for brief communications in limited languages, though human translation is often necessary. Accuracy scores ranged from 83-97.8% when translating from English, and 36-76% when translating to English. Usability scores were 76.7-96.7%. Patients were more satisfied than clinicians, with 84-96.6% and 53.8-86.7% satisfied, respectively. Clinicians were hesitant to use AI due to questions of respect, quality, reliability, and misunderstanding. AI is being used as a last-resort option, to assist fluent, non-certified providers and lay interpreters, and for brief communications.</p><p><strong>Conclusions: </strong>Limitations include few languages tested, unidirectional translation, simulation, and evolving translation tools. AI shows promise in clinical translation, but the complexity of medical consultations requires a balanced approach combining AI and human translation services for quality care.</p>","PeriodicalId":8216,"journal":{"name":"Annals of translational medicine","volume":"12 6","pages":"117"},"PeriodicalIF":0.0000,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11729812/pdf/","citationCount":"0","resultStr":"{\"title\":\"Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation.\",\"authors\":\"Ariana Genovese, Sahar Borna, Cesar A Gomez-Cabello, Syed Ali Haider, Srinivasagam Prabha, Antonio J Forte, Benjamin R Veenstra\",\"doi\":\"10.21037/atm-24-162\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Addressing language barriers through accurate interpretation is crucial for providing quality care and establishing trust. While the ability of artificial intelligence (AI) to translate medical documentation has been studied, its role for patient-provider communication is less explored. This review evaluates AI's effectiveness in clinical translation by assessing accuracy, usability, satisfaction, and feedback on its use.</p><p><strong>Methods: </strong>A systematic search was conducted on July 11, 2024, across Cumulated Index in Nursing and Allied Health Literature (CINAHL), Institute of Electrical and Electronics Engineers (IEEE) Xplore, PubMed, Scopus, Web of Science, and Google Scholar. Inclusion criteria required AI to translate clinical information for a real or theoretical consultation. Exclusion criteria included reviews, correspondence, educational materials, non-peer-reviewed or retracted reports, non-English translations, pre-2016 publications, and reports on sign language or patient education. Search strings representing AI, language interpretation, and healthcare were used. Two investigators independently conducted the screening, extraction, synthesis of results, and bias assessments using Risk Of Bias In Non-randomized Studies - of Interventions (ROBINS-I), Mixed Methods Appraisal Tool (MMAT), and the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Qualitative Research. A third investigator resolved conflicts.</p><p><strong>Results: </strong>Of 1,095 reports, 9 studies were analyzed, evaluating AI translation platforms Google Translate, Microsoft Translator, Apple iTranslate, AwezaMed, Pocketalk W, and the Asynchronous Telepsychiatry (ATP) App. Investigations occurred in the US, France, Switzerland, and South Africa, with publications from 2019-2024. AI medical translation shows promise, typically providing accurate translations for brief communications in limited languages, though human translation is often necessary. Accuracy scores ranged from 83-97.8% when translating from English, and 36-76% when translating to English. Usability scores were 76.7-96.7%. Patients were more satisfied than clinicians, with 84-96.6% and 53.8-86.7% satisfied, respectively. Clinicians were hesitant to use AI due to questions of respect, quality, reliability, and misunderstanding. AI is being used as a last-resort option, to assist fluent, non-certified providers and lay interpreters, and for brief communications.</p><p><strong>Conclusions: </strong>Limitations include few languages tested, unidirectional translation, simulation, and evolving translation tools. AI shows promise in clinical translation, but the complexity of medical consultations requires a balanced approach combining AI and human translation services for quality care.</p>\",\"PeriodicalId\":8216,\"journal\":{\"name\":\"Annals of translational medicine\",\"volume\":\"12 6\",\"pages\":\"117\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-12-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11729812/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annals of translational medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.21037/atm-24-162\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/12/17 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of translational medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.21037/atm-24-162","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/12/17 0:00:00","PubModel":"Epub","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
背景:通过准确的口译来解决语言障碍对于提供高质量的护理和建立信任至关重要。虽然人工智能(AI)翻译医疗文件的能力已经被研究过,但它在医患沟通中的作用却很少被探索。本综述通过评估准确性、可用性、满意度和使用反馈来评估人工智能在临床翻译中的有效性。方法:于2024年7月11日系统检索护理与相关健康文献累积索引(CINAHL)、电气与电子工程师学会(IEEE) Xplore、PubMed、Scopus、Web of Science和谷歌Scholar。纳入标准要求人工智能翻译临床信息以进行实际或理论咨询。排除标准包括综述、通信、教育材料、未经同行评审或撤回的报告、非英文翻译、2016年以前的出版物以及关于手语或患者教育的报告。使用了表示人工智能、语言解释和医疗保健的搜索字符串。两名研究人员独立进行筛选、提取、结果综合和偏倚评估,使用非随机干预研究的偏倚风险(ROBINS-I)、混合方法评估工具(MMAT)和乔安娜布里格斯研究所(JBI)定性研究关键评估清单。第三位调查员解决了冲突。结果:在1095份报告中,我们分析了9项研究,评估了人工智能翻译平台谷歌Translate、微软Translator、苹果ittranslate、AwezaMed、Pocketalk W和异步远程精神病学(ATP) App。调查发生在美国、法国、瑞士和南非,发表时间为2019-2024年。人工智能医学翻译显示出前景,通常为有限语言的简短交流提供准确的翻译,尽管人工翻译通常是必要的。从英语翻译的准确率为83-97.8%,从英语翻译的准确率为36-76%。可用性得分为76.7-96.7%。患者满意度高于临床医生,满意度分别为84-96.6%和53.8-86.7%。由于尊重、质量、可靠性和误解等问题,临床医生对使用人工智能犹豫不决。人工智能被用作最后的选择,以协助流利的、未经认证的提供者和非专业口译员,并用于简短的通信。结论:局限性包括测试语言少、单向翻译、模拟和不断发展的翻译工具。人工智能在临床翻译中显示出前景,但医疗咨询的复杂性需要一种平衡的方法,将人工智能和人工翻译服务结合起来,以提供高质量的护理。
Artificial intelligence in clinical settings: a systematic review of its role in language translation and interpretation.
Background: Addressing language barriers through accurate interpretation is crucial for providing quality care and establishing trust. While the ability of artificial intelligence (AI) to translate medical documentation has been studied, its role for patient-provider communication is less explored. This review evaluates AI's effectiveness in clinical translation by assessing accuracy, usability, satisfaction, and feedback on its use.
Methods: A systematic search was conducted on July 11, 2024, across Cumulated Index in Nursing and Allied Health Literature (CINAHL), Institute of Electrical and Electronics Engineers (IEEE) Xplore, PubMed, Scopus, Web of Science, and Google Scholar. Inclusion criteria required AI to translate clinical information for a real or theoretical consultation. Exclusion criteria included reviews, correspondence, educational materials, non-peer-reviewed or retracted reports, non-English translations, pre-2016 publications, and reports on sign language or patient education. Search strings representing AI, language interpretation, and healthcare were used. Two investigators independently conducted the screening, extraction, synthesis of results, and bias assessments using Risk Of Bias In Non-randomized Studies - of Interventions (ROBINS-I), Mixed Methods Appraisal Tool (MMAT), and the Joanna Briggs Institute (JBI) Critical Appraisal Checklist for Qualitative Research. A third investigator resolved conflicts.
Results: Of 1,095 reports, 9 studies were analyzed, evaluating AI translation platforms Google Translate, Microsoft Translator, Apple iTranslate, AwezaMed, Pocketalk W, and the Asynchronous Telepsychiatry (ATP) App. Investigations occurred in the US, France, Switzerland, and South Africa, with publications from 2019-2024. AI medical translation shows promise, typically providing accurate translations for brief communications in limited languages, though human translation is often necessary. Accuracy scores ranged from 83-97.8% when translating from English, and 36-76% when translating to English. Usability scores were 76.7-96.7%. Patients were more satisfied than clinicians, with 84-96.6% and 53.8-86.7% satisfied, respectively. Clinicians were hesitant to use AI due to questions of respect, quality, reliability, and misunderstanding. AI is being used as a last-resort option, to assist fluent, non-certified providers and lay interpreters, and for brief communications.
Conclusions: Limitations include few languages tested, unidirectional translation, simulation, and evolving translation tools. AI shows promise in clinical translation, but the complexity of medical consultations requires a balanced approach combining AI and human translation services for quality care.
期刊介绍:
The Annals of Translational Medicine (Ann Transl Med; ATM; Print ISSN 2305-5839; Online ISSN 2305-5847) is an international, peer-reviewed Open Access journal featuring original and observational investigations in the broad fields of laboratory, clinical, and public health research, aiming to provide practical up-to-date information in significant research from all subspecialties of medicine and to broaden the readers’ vision and horizon from bench to bed and bed to bench. It is published quarterly (April 2013- Dec. 2013), monthly (Jan. 2014 - Feb. 2015), biweekly (March 2015-) and openly distributed worldwide. Annals of Translational Medicine is indexed in PubMed in Sept 2014 and in SCIE in 2018. Specific areas of interest include, but not limited to, multimodality therapy, epidemiology, biomarkers, imaging, biology, pathology, and technical advances related to medicine. Submissions describing preclinical research with potential for application to human disease, and studies describing research obtained from preliminary human experimentation with potential to further the understanding of biological mechanism underlying disease are encouraged. Also warmly welcome are studies describing public health research pertinent to clinic, disease diagnosis and prevention, or healthcare policy. With a focus on interdisciplinary academic cooperation, ATM aims to expedite the translation of scientific discovery into new or improved standards of management and health outcomes practice.