Task-Specific Transformer-Based Language Models in Health Care: Scoping Review

BackgroundTransformer-based language models have shown great potential to revolutionize health care by advancing clinical decision support, patient interaction, and disease prediction. However, despite their rapid development, the implementation of transformer-based language...

Full description

Saved in:
Bibliographic Details
Main Authors: Ha Na Cho, Tae Joon Jun, Young-Hak Kim, Heejun Kang, Imjin Ahn, Hansle Gwon, Yunha Kim, Jiahn Seo, Heejung Choi, Minkyoung Kim, Jiye Han, Gaeun Kee, Seohyun Park, Soyoung Ko
Format: Article
Language:English
Published: JMIR Publications 2024-11-01
Series:JMIR Medical Informatics
Online Access:https://medinform.jmir.org/2024/1/e49724
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846163954252906496
author Ha Na Cho
Tae Joon Jun
Young-Hak Kim
Heejun Kang
Imjin Ahn
Hansle Gwon
Yunha Kim
Jiahn Seo
Heejung Choi
Minkyoung Kim
Jiye Han
Gaeun Kee
Seohyun Park
Soyoung Ko
author_facet Ha Na Cho
Tae Joon Jun
Young-Hak Kim
Heejun Kang
Imjin Ahn
Hansle Gwon
Yunha Kim
Jiahn Seo
Heejung Choi
Minkyoung Kim
Jiye Han
Gaeun Kee
Seohyun Park
Soyoung Ko
author_sort Ha Na Cho
collection DOAJ
description BackgroundTransformer-based language models have shown great potential to revolutionize health care by advancing clinical decision support, patient interaction, and disease prediction. However, despite their rapid development, the implementation of transformer-based language models in health care settings remains limited. This is partly due to the lack of a comprehensive review, which hinders a systematic understanding of their applications and limitations. Without clear guidelines and consolidated information, both researchers and physicians face difficulties in using these models effectively, resulting in inefficient research efforts and slow integration into clinical workflows. ObjectiveThis scoping review addresses this gap by examining studies on medical transformer-based language models and categorizing them into 6 tasks: dialogue generation, question answering, summarization, text classification, sentiment analysis, and named entity recognition. MethodsWe conducted a scoping review following the Cochrane scoping review protocol. A comprehensive literature search was performed across databases, including Google Scholar and PubMed, covering publications from January 2017 to September 2024. Studies involving transformer-derived models in medical tasks were included. Data were categorized into 6 key tasks. ResultsOur key findings revealed both advancements and critical challenges in applying transformer-based models to health care tasks. For example, models like MedPIR involving dialogue generation show promise but face privacy and ethical concerns, while question-answering models like BioBERT improve accuracy but struggle with the complexity of medical terminology. The BioBERTSum summarization model aids clinicians by condensing medical texts but needs better handling of long sequences. ConclusionsThis review attempted to provide a consolidated understanding of the role of transformer-based language models in health care and to guide future research directions. By addressing current challenges and exploring the potential for real-world applications, we envision significant improvements in health care informatics. Addressing the identified challenges and implementing proposed solutions can enable transformer-based language models to significantly improve health care delivery and patient outcomes. Our review provides valuable insights for future research and practical applications, setting the stage for transformative advancements in medical informatics.
format Article
id doaj-art-02a024cf23a74934b5889575b88b43a7
institution Kabale University
issn 2291-9694
language English
publishDate 2024-11-01
publisher JMIR Publications
record_format Article
series JMIR Medical Informatics
spelling doaj-art-02a024cf23a74934b5889575b88b43a72024-11-18T17:30:42ZengJMIR PublicationsJMIR Medical Informatics2291-96942024-11-0112e4972410.2196/49724Task-Specific Transformer-Based Language Models in Health Care: Scoping ReviewHa Na Chohttps://orcid.org/0000-0001-8033-6644Tae Joon Junhttps://orcid.org/0000-0002-6808-5149Young-Hak Kimhttps://orcid.org/0000-0002-3610-486XHeejun Kanghttps://orcid.org/0000-0002-0396-2112Imjin Ahnhttps://orcid.org/0000-0003-3929-6390Hansle Gwonhttps://orcid.org/0000-0001-6019-4466Yunha Kimhttps://orcid.org/0000-0001-6713-1900Jiahn Seohttps://orcid.org/0000-0002-3589-1347Heejung Choihttps://orcid.org/0000-0003-2265-1819Minkyoung Kimhttps://orcid.org/0000-0003-4923-5321Jiye Hanhttps://orcid.org/0000-0002-1366-8275Gaeun Keehttps://orcid.org/0000-0002-2377-3503Seohyun Parkhttps://orcid.org/0000-0003-2658-8757Soyoung Kohttps://orcid.org/0009-0003-6268-1534 BackgroundTransformer-based language models have shown great potential to revolutionize health care by advancing clinical decision support, patient interaction, and disease prediction. However, despite their rapid development, the implementation of transformer-based language models in health care settings remains limited. This is partly due to the lack of a comprehensive review, which hinders a systematic understanding of their applications and limitations. Without clear guidelines and consolidated information, both researchers and physicians face difficulties in using these models effectively, resulting in inefficient research efforts and slow integration into clinical workflows. ObjectiveThis scoping review addresses this gap by examining studies on medical transformer-based language models and categorizing them into 6 tasks: dialogue generation, question answering, summarization, text classification, sentiment analysis, and named entity recognition. MethodsWe conducted a scoping review following the Cochrane scoping review protocol. A comprehensive literature search was performed across databases, including Google Scholar and PubMed, covering publications from January 2017 to September 2024. Studies involving transformer-derived models in medical tasks were included. Data were categorized into 6 key tasks. ResultsOur key findings revealed both advancements and critical challenges in applying transformer-based models to health care tasks. For example, models like MedPIR involving dialogue generation show promise but face privacy and ethical concerns, while question-answering models like BioBERT improve accuracy but struggle with the complexity of medical terminology. The BioBERTSum summarization model aids clinicians by condensing medical texts but needs better handling of long sequences. ConclusionsThis review attempted to provide a consolidated understanding of the role of transformer-based language models in health care and to guide future research directions. By addressing current challenges and exploring the potential for real-world applications, we envision significant improvements in health care informatics. Addressing the identified challenges and implementing proposed solutions can enable transformer-based language models to significantly improve health care delivery and patient outcomes. Our review provides valuable insights for future research and practical applications, setting the stage for transformative advancements in medical informatics.https://medinform.jmir.org/2024/1/e49724
spellingShingle Ha Na Cho
Tae Joon Jun
Young-Hak Kim
Heejun Kang
Imjin Ahn
Hansle Gwon
Yunha Kim
Jiahn Seo
Heejung Choi
Minkyoung Kim
Jiye Han
Gaeun Kee
Seohyun Park
Soyoung Ko
Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
JMIR Medical Informatics
title Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
title_full Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
title_fullStr Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
title_full_unstemmed Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
title_short Task-Specific Transformer-Based Language Models in Health Care: Scoping Review
title_sort task specific transformer based language models in health care scoping review
url https://medinform.jmir.org/2024/1/e49724
work_keys_str_mv AT hanacho taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT taejoonjun taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT younghakkim taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT heejunkang taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT imjinahn taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT hanslegwon taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT yunhakim taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT jiahnseo taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT heejungchoi taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT minkyoungkim taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT jiyehan taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT gaeunkee taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT seohyunpark taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview
AT soyoungko taskspecifictransformerbasedlanguagemodelsinhealthcarescopingreview