Implementing Large Language Models in Health Care: Clinician-Focused Review With Interactive Guideline

Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work. We aimed to provide clini...

Full description

Saved in:
Bibliographic Details
Published inJournal of medical Internet research Vol. 27; no. 8; p. e71916
Main Authors Li, HongYi, Fu, Jun-Fen, Python, Andre
Format Journal Article
LanguageEnglish
Published Canada Journal of Medical Internet Research 11.07.2025
JMIR Publications
Subjects
Online AccessGet full text
ISSN1438-8871
1439-4456
1438-8871
DOI10.2196/71916

Cover

Abstract Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work. We aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care. We conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies. We collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings. In this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.
AbstractList Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work. We aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care. We conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies. We collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings. In this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.
BackgroundLarge language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work. ObjectiveWe aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care. MethodsWe conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies. ResultsWe collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings. ConclusionsIn this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.
Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work.BACKGROUNDLarge language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work.We aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care.OBJECTIVEWe aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care.We conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies.METHODSWe conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies.We collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings.RESULTSWe collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings.In this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.CONCLUSIONSIn this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.
Background Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work. Objective We aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care. Methods We conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies. Results We collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings. Conclusions In this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.
Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid development of LLMs, clinicians face a growing challenge in determining the most suitable algorithms to support their work. We aimed to provide clinicians and other health care practitioners with systematic guidance in selecting an LLM that is relevant and appropriate to their needs and facilitate the integration process of LLMs in health care. We conducted a literature search of full-text publications in English on clinical applications of LLMs published between January 1, 2022, and March 31, 2025, on PubMed, ScienceDirect, Scopus, and IEEE Xplore. We excluded papers from journals below a set citation threshold, as well as papers that did not focus on LLMs, were not research based, or did not involve clinical applications. We also conducted a literature search on arXiv within the same investigated period and included papers on the clinical applications of innovative multimodal LLMs. This led to a total of 270 studies. We collected 330 LLMs and recorded their application frequency in clinical tasks and frequency of best performance in their context. On the basis of a 5-stage clinical workflow, we found that stages 2, 3, and 4 are key stages in the clinical workflow, involving numerous clinical subtasks and LLMs. However, the diversity of LLMs that may perform optimally in each context remains limited. GPT-3.5 and GPT-4 were the most versatile models in the 5-stage clinical workflow, applied to 52% (29/56) and 71% (40/56) of the clinical subtasks, respectively, and they performed best in 29% (16/56) and 54% (30/56) of the clinical subtasks, respectively. General-purpose LLMs may not perform well in specialized areas as they often require lightweight prompt engineering methods or fine-tuning techniques based on specific datasets to improve model performance. Most LLMs with multimodal abilities are closed-source models and, therefore, lack of transparency, model customization, and fine-tuning for specific clinical tasks and may also pose challenges regarding data protection and privacy, which are common requirements in clinical settings. In this review, we found that LLMs may help clinicians in a variety of clinical tasks. However, we did not find evidence of generalist clinical LLMs successfully applicable to a wide range of clinical tasks. Therefore, their clinical deployment remains challenging. On the basis of this review, we propose an interactive online guideline for clinicians to select suitable LLMs by clinical task. With a clinical perspective and free of unnecessary technical jargon, this guideline may be used as a reference to successfully apply LLMs in clinical settings.
Audience Academic
Author Fu, Jun-Fen
Python, Andre
Li, HongYi
AuthorAffiliation 1 Center for Data Science Zhejiang University Hangzhou China
5 National Regional Center for Children’s Health Hangzhou China
6 School of Medicine Zhejiang University Hangzhou China
7 Centre for Human Genetics Nuffield Department of Medicine University of Oxford Oxford United Kingdom
3 School of Medicine Children’s Hospital of Zhejiang University Hangzhou China
4 National Clinical Research Center for Child Health Hangzhou China
2 School of Mathematical Sciences Zhejiang University Hangzhou China
AuthorAffiliation_xml – name: 7 Centre for Human Genetics Nuffield Department of Medicine University of Oxford Oxford United Kingdom
– name: 2 School of Mathematical Sciences Zhejiang University Hangzhou China
– name: 3 School of Medicine Children’s Hospital of Zhejiang University Hangzhou China
– name: 1 Center for Data Science Zhejiang University Hangzhou China
– name: 5 National Regional Center for Children’s Health Hangzhou China
– name: 4 National Clinical Research Center for Child Health Hangzhou China
– name: 6 School of Medicine Zhejiang University Hangzhou China
Author_xml – sequence: 1
  givenname: HongYi
  orcidid: 0009-0000-0471-8624
  surname: Li
  fullname: Li, HongYi
– sequence: 2
  givenname: Jun-Fen
  orcidid: 0000-0001-6405-1251
  surname: Fu
  fullname: Fu, Jun-Fen
– sequence: 3
  givenname: Andre
  orcidid: 0000-0001-8094-7226
  surname: Python
  fullname: Python, Andre
BackLink https://www.ncbi.nlm.nih.gov/pubmed/40644686$$D View this record in MEDLINE/PubMed
BookMark eNp1kltrFDEUgAep2Iv9CzIgii9Tc5uZxBcpi20XVgRRfAxnkzPTlEyyZma29N-bdmvpghJIwsmXLzknOS4OQgxYFKeUnDGqmo8tVbR5URxRwWUlZUsPns0Pi-NxvCGEEaHoq-JQkEaIRjZHRbccNh4HDJMLfbmC1GPuQz9DnnyNFv1YulBeIfjpulxAwk_lwrvgjINQXUQzj2jL77h1eFv-cplZhgkTmMltsbycXTa4gK-Llx34EU8fx5Pi58WXH4uravXtcrk4X1VGNHyqamMIW5um7hCoJC0jkjBjBRLJcpbSAlijuAJjlRCMMis5yVFLDKs5bfhJsdx5bYQbvUlugHSnIzj9EIip15AmZzzqdddx2fKWrBURUnKloBZZg7KmvK1Vdr3fueawgbtb8P5JSIm-L7p-KHoGP-_Azbwe0JpczAR-7_T9leCudR-3mjKmlKpJNnx4NKT4e8Zx0oMbDXoPAeM8ap7BOj9fU2f07Q7tISfhQhez0tzj-lyKVtCmZTRTZ_-gcrM4OJN_TudyfG_Dm-c5PF3-70_JwLsdYFIcx4Tdf4rxB9mLyJc
Cites_doi 10.1016/j.ijom.2023.09.005
10.1038/s41746-024-01239-w
10.3389/frai.2023.1169595
10.1007/bf03168435
10.1016/j.compbiomed.2023.107807
10.1038/s41591-024-03328-5
10.1038/s41598-023-41512-8
10.1145/1721654.1721672
10.1016/j.aiopen.2021.08.002
10.1038/s41586-023-05881-4
10.4018/IJEIS.2019070105
10.1038/s41746-024-01258-7
10.1186/s12939-025-02419-0
10.1038/s41746-022-00742-2
10.1016/j.jbi.2025.104791
10.2139/ssrn.4809363
10.3390/informatics11030057
10.1038/s41591-024-03434-4
10.18653/v1/p19-1355
10.1212/wnl.0000000000207967
10.1038/s41586-024-07421-0
10.1007/s10916-024-02045-3
10.3390/jcm14020572
10.1016/S2589-7500(23)00202-9
10.1109/RBME.2025.3531360
10.1038/s41746-023-00970-0
10.1016/j.metrad.2023.100017
10.18653/v1/2023.emnlp-main.67
10.1148/radiol.230970
10.1038/s41746-025-01429-0
10.1016/j.compbiomed.2023.107794
10.35484/ahss.2025(6-I)22
10.1001/jamanetworkopen.2024.0357
10.1093/bib/bbad493
10.1016/s2589-7500(23)00201-7
10.1016/j.jaad.2023.04.005
10.1016/s2589-7500(23)00225-x
10.1038/s41746-024-01029-4
10.3389/fonc.2024.1526288
10.1038/s42256-021-00359-2
10.1038/s41368-023-00239-y
10.1109/rbme.2024.3493775
10.4274/dir.2023.232417
10.1177/17562848231218618
10.1016/j.jacr.2023.06.008
10.1038/s43856-023-00370-1
10.3390/jcm14020322
10.1109/tpami.2018.2857768
10.1056/AIra2400380
10.1038/s41591-023-02504-3
10.18653/v1/2024.emnlp-main.64
10.1001/jamahealthforum.2023.3909
10.1093/postmj/qgae122
10.1016/j.ebiom.2023.104512
10.3390/fi15090286
10.1056/AIoa2300138
10.1038/s41746-023-00837-4
10.1038/s41591-024-03445-1
10.1016/s2589-7500(23)00083-3
10.1038/s43856-024-00717-2
10.1109/ACCESS.2024.3365742
10.1093/eurheartj/ehad838
10.21203/rs.3.rs-3324530/v1
10.1038/s41586-023-06291-2
10.1007/s10115-021-01605-0
10.36227/techrxiv.23589741.v2
10.1002/hcs2.61
10.1145/3641289
10.1007/s00330-024-11115-6
10.1093/nsr/nwae403
10.1038/s41591-023-02448-8
10.1001/jamanetworkopen.2024.40969
10.1038/s41746-023-00952-2
10.18653/v1/2020.blackboxnlp-1.14
10.2478/jagi-2014-0001
10.1186/s13000-024-01464-7
10.1038/s41746-024-01157-x
10.18653/v1/2021.acl-long.416
10.1056/NEJMra2301725
10.3390/healthcare11162308
10.1038/s41746-023-00896-7
10.1038/s41746-025-01443-2
10.1038/s41746-019-0158-1
10.1038/s41746-024-01356-6
10.2196/50638
10.1001/jamanetworkopen.2023.25000
10.1101/2023.11.09.566468
10.1016/s2589-7500(23)00179-6
10.3390/electronics13152961
10.1145/3571730
10.1056/nejmsr2214184
10.1001/jamanetworkopen.2023.43689
10.1145/3386252
10.1038/s41591-024-03097-1
10.1162/tacl_a_00324
10.1109/tkde.2021.3090866
10.1001/jamanetworkopen.2023.27647
10.1101/2023.02.19.23286155
10.1038/s41586-020-2973-6
10.1148/radiol.232756
10.7326/M23-2772
10.1038/s41591-024-03423-7
10.3389/fdmed.2024.1456208
10.1001/jamanetworkopen.2024.57879
10.1038/s41591-024-03258-2
10.1001/jamanetworkopen.2023.46721
10.1093/clinchem/hvad106
10.1109/tmi.2016.2535302
10.3389/fmed.2024.1380148
10.1038/s41746-023-00879-8
10.1145/3712001
ContentType Journal Article
Copyright HongYi Li, Jun-Fen Fu, Andre Python. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 11.07.2025.
COPYRIGHT 2025 Journal of Medical Internet Research
HongYi Li, Jun-Fen Fu, Andre Python. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 11.07.2025. 2025
Copyright_xml – notice: HongYi Li, Jun-Fen Fu, Andre Python. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 11.07.2025.
– notice: COPYRIGHT 2025 Journal of Medical Internet Research
– notice: HongYi Li, Jun-Fen Fu, Andre Python. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 11.07.2025. 2025
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
ADTOC
UNPAY
DOA
DOI 10.2196/71916
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE

MEDLINE - Academic


Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 4
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Library & Information Science
EISSN 1438-8871
ExternalDocumentID oai_doaj_org_article_bff387370b90488399a54c25e8513759
10.2196/71916
PMC12299950
A847416721
40644686
10_2196_71916
Genre Journal Article
Review
GeographicLocations China
GeographicLocations_xml – name: China
GroupedDBID ---
.4I
.DC
29L
2WC
36B
53G
5GY
5VS
77I
77K
7RV
7X7
8FI
8FJ
AAFWJ
AAKPC
AAWTL
AAYXX
ABDBF
ABIVO
ABUWG
ACGFO
ADBBV
AEGXH
AENEX
AFKRA
AFPKN
AIAGR
ALMA_UNASSIGNED_HOLDINGS
ALSLI
AOIJS
BAWUL
BCNDV
BENPR
CCPQU
CITATION
CNYFK
CS3
DIK
DU5
DWQXO
E3Z
EAP
EBD
EBS
EJD
ELW
EMB
EMOBN
ESX
F5P
FRP
FYUFA
GROUPED_DOAJ
GX1
HMCUK
HYE
IAO
ICO
IEA
IHR
INH
ISN
ITC
KQ8
M1O
M48
NAPCQ
OK1
OVT
P2P
PGMZT
PHGZM
PHGZT
PIMPY
PPXIY
PQQKQ
PRQQA
PUEGO
RNS
RPM
SJN
SV3
TR2
UKHRP
XSB
ACUHS
ALIPV
CGR
CUY
CVF
ECM
EIF
NPM
7X8
5PM
ADRAZ
ADTOC
C1A
O5R
O5S
UNPAY
WOQ
ID FETCH-LOGICAL-c463t-5cc02bc65fea180720802cd4e0822198daadc939acd944212d8308dad0c253163
IEDL.DBID DOA
ISSN 1438-8871
1439-4456
IngestDate Fri Oct 03 12:44:45 EDT 2025
Sun Oct 26 04:17:05 EDT 2025
Tue Sep 30 17:02:11 EDT 2025
Fri Sep 05 15:41:03 EDT 2025
Mon Oct 20 22:40:18 EDT 2025
Mon Oct 20 16:51:53 EDT 2025
Fri Aug 01 03:41:24 EDT 2025
Wed Oct 01 05:46:01 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 8
Keywords clinical
digital health
LLM review
AI
LLM
large language model
artificial intelligence
Language English
License HongYi Li, Jun-Fen Fu, Andre Python. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 11.07.2025.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research (ISSN 1438-8871), is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.
cc-by
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c463t-5cc02bc65fea180720802cd4e0822198daadc939acd944212d8308dad0c253163
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
ObjectType-Review-3
content type line 23
ORCID 0009-0000-0471-8624
0000-0001-8094-7226
0000-0001-6405-1251
OpenAccessLink https://doaj.org/article/bff387370b90488399a54c25e8513759
PMID 40644686
PQID 3229500265
PQPubID 23479
ParticipantIDs doaj_primary_oai_doaj_org_article_bff387370b90488399a54c25e8513759
unpaywall_primary_10_2196_71916
pubmedcentral_primary_oai_pubmedcentral_nih_gov_12299950
proquest_miscellaneous_3229500265
gale_infotracmisc_A847416721
gale_infotracacademiconefile_A847416721
pubmed_primary_40644686
crossref_primary_10_2196_71916
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2025-07-11
PublicationDateYYYYMMDD 2025-07-11
PublicationDate_xml – month: 07
  year: 2025
  text: 2025-07-11
  day: 11
PublicationDecade 2020
PublicationPlace Canada
PublicationPlace_xml – name: Canada
– name: Toronto, Canada
PublicationTitle Journal of medical Internet research
PublicationTitleAlternate J Med Internet Res
PublicationYear 2025
Publisher Journal of Medical Internet Research
JMIR Publications
Publisher_xml – name: Journal of Medical Internet Research
– name: JMIR Publications
References ref57
ref56
ref59
Vaswani, A (ref8)
ref58
ref53
ref52
Moell, B (ref141)
ref55
ref54
Rawte, V (ref38)
Ghaffarzadeh-Esfahani, M (ref86)
ref51
ref50
ref46
ref45
ref48
ref47
Pellegrini, C (ref94)
ref42
ref41
ref44
ref43
Ouyang, L (ref9)
ref49
Perez, F (ref125)
Ziaei, R (ref108)
ref7
ref4
ref3
ref6
ref5
Hisamoto, S (ref124)
ref100
ref101
ref40
ref35
ref34
ref37
ref36
Yuan, M (ref82)
ref148
ref149
ref33
ref146
ref32
Gollub, RL (ref137) 2021
ref147
ref39
Wu, C (ref68)
Hu, M (ref80)
Wu, J (ref99)
Thoppilan, R (ref62)
Brown, TB (ref65)
ref24
Bai, Y (ref30)
ref26
ref25
ref20
ref22
ref21
He, T (ref78)
ref28
ref27
Haux, R (ref83) 2004
Zhang, H (ref31)
ref13
ref12
ref15
ref128
ref14
ref129
ref126
ref96
ref127
ref11
ref10
ref17
ref16
ref19
ref18
Lehman, E (ref93)
ref133
ref92
ref134
ref95
ref131
ref132
ref130
ref91
ref90
Zhang, K (ref98)
Mukherjee, S (ref104)
ref89
ref139
Kim, K (ref102)
ref85
ref138
ref88
ref135
ref87
ref136
Khanmohammadi, R (ref73)
ref144
ref81
ref145
ref84
ref142
ref143
ref140
ref79
ref109
ref106
ref107
ref75
ref74
ref105
ref77
ref76
ref103
ref2
ref1
Li, ZZ (ref29)
Liu, H (ref118)
ref71
ref111
ref70
ref112
ref72
ref110
ref119
ref67
ref117
ref69
ref64
ref115
ref63
ref116
Wu, D (ref150)
ref66
ref113
ref114
Zhang, D (ref23)
Zhou, HY (ref97)
ref60
ref122
ref123
ref120
ref61
ref121
References_xml – ident: ref76
  doi: 10.1016/j.ijom.2023.09.005
– ident: ref26
  doi: 10.1038/s41746-024-01239-w
– ident: ref36
  doi: 10.3389/frai.2023.1169595
– ident: ref84
  doi: 10.1007/bf03168435
– ident: ref118
  publication-title: arXiv
– ident: ref139
  doi: 10.1016/j.compbiomed.2023.107807
– ident: ref134
  doi: 10.1038/s41591-024-03328-5
– ident: ref9
  publication-title: arXiv
– ident: ref88
  doi: 10.1038/s41598-023-41512-8
– ident: ref127
  doi: 10.1145/1721654.1721672
– ident: ref27
  doi: 10.1016/j.aiopen.2021.08.002
– ident: ref82
  publication-title: arXiv
– ident: ref86
  publication-title: arXiv
– ident: ref141
  publication-title: arXiv
– ident: ref131
– ident: ref15
  doi: 10.1038/s41586-023-05881-4
– ident: ref16
  doi: 10.4018/IJEIS.2019070105
– ident: ref135
  doi: 10.1038/s41746-024-01258-7
– ident: ref55
  doi: 10.1186/s12939-025-02419-0
– ident: ref62
  publication-title: arXiv
– ident: ref6
  doi: 10.1038/s41746-022-00742-2
– ident: ref149
  doi: 10.1016/j.jbi.2025.104791
– ident: ref72
  doi: 10.2139/ssrn.4809363
– ident: ref44
  doi: 10.3390/informatics11030057
– ident: ref51
  doi: 10.1038/s41591-024-03434-4
– ident: ref18
  doi: 10.18653/v1/p19-1355
– ident: ref112
  doi: 10.1212/wnl.0000000000207967
– ident: ref116
  doi: 10.1038/s41586-024-07421-0
– ident: ref47
  doi: 10.1007/s10916-024-02045-3
– ident: ref143
  doi: 10.3390/jcm14020572
– ident: ref2
  doi: 10.1016/S2589-7500(23)00202-9
– ident: ref29
  publication-title: arXiv
– ident: ref98
  publication-title: arXiv
– ident: ref52
  doi: 10.1109/RBME.2025.3531360
– ident: ref89
  doi: 10.1038/s41746-023-00970-0
– ident: ref35
  doi: 10.1016/j.metrad.2023.100017
– ident: ref30
  publication-title: arXiv
– ident: ref114
  doi: 10.18653/v1/2023.emnlp-main.67
– ident: ref3
  doi: 10.1148/radiol.230970
– ident: ref128
  doi: 10.1038/s41746-025-01429-0
– ident: ref140
  doi: 10.1016/j.compbiomed.2023.107794
– ident: ref58
  doi: 10.35484/ahss.2025(6-I)22
– ident: ref105
  doi: 10.1001/jamanetworkopen.2024.0357
– ident: ref12
  doi: 10.1093/bib/bbad493
– ident: ref85
  doi: 10.1016/s2589-7500(23)00201-7
– ident: ref60
  doi: 10.1016/j.jaad.2023.04.005
– ident: ref123
  doi: 10.1016/s2589-7500(23)00225-x
– ident: ref91
  doi: 10.1038/s41746-024-01029-4
– ident: ref145
  doi: 10.3389/fonc.2024.1526288
– ident: ref121
  doi: 10.1038/s42256-021-00359-2
– ident: ref7
  doi: 10.1038/s41368-023-00239-y
– ident: ref148
  publication-title: arXiv
– ident: ref150
  publication-title: arXiv
– ident: ref81
  doi: 10.1109/rbme.2024.3493775
– ident: ref48
  doi: 10.4274/dir.2023.232417
– ident: ref75
  doi: 10.1177/17562848231218618
– ident: ref142
  doi: 10.1016/j.jacr.2023.06.008
– ident: ref71
  doi: 10.1038/s43856-023-00370-1
– ident: ref146
  doi: 10.3390/jcm14020322
– ident: ref33
  doi: 10.1109/tpami.2018.2857768
– ident: ref8
  publication-title: arXiv
– ident: ref54
  doi: 10.1056/AIra2400380
– ident: ref63
– year: 2004
  ident: ref83
  publication-title: Strategic Information Management in Hospitals: An Introduction to Hospital Information Systems
– ident: ref69
  doi: 10.1038/s41591-023-02504-3
– ident: ref80
  publication-title: arXiv
– ident: ref21
  doi: 10.18653/v1/2024.emnlp-main.64
– ident: ref103
  doi: 10.1001/jamahealthforum.2023.3909
– ident: ref53
  doi: 10.1093/postmj/qgae122
– ident: ref65
  publication-title: arXiv
– ident: ref10
  doi: 10.1016/j.ebiom.2023.104512
– ident: ref41
  doi: 10.3390/fi15090286
– ident: ref95
  doi: 10.1056/AIoa2300138
– ident: ref125
  publication-title: arXiv
– ident: ref99
  publication-title: arXiv
– ident: ref120
  doi: 10.1038/s41746-023-00837-4
– ident: ref126
  doi: 10.1038/s41591-024-03445-1
– ident: ref129
  doi: 10.1016/s2589-7500(23)00083-3
– ident: ref57
  doi: 10.1038/s43856-024-00717-2
– ident: ref102
  publication-title: arXiv
– ident: ref43
  doi: 10.1109/ACCESS.2024.3365742
– ident: ref23
  publication-title: arXiv
– ident: ref124
  publication-title: arXiv
– ident: ref74
  doi: 10.1093/eurheartj/ehad838
– ident: ref96
  doi: 10.21203/rs.3.rs-3324530/v1
– ident: ref4
  doi: 10.1038/s41586-023-06291-2
– ident: ref25
  doi: 10.1007/s10115-021-01605-0
– ident: ref37
  doi: 10.36227/techrxiv.23589741.v2
– ident: ref42
  doi: 10.1002/hcs2.61
– ident: ref38
  publication-title: arXiv
– ident: ref73
  publication-title: arXiv
– ident: ref13
  doi: 10.1145/3641289
– ident: ref93
  publication-title: arXiv
– ident: ref31
  publication-title: arXiv
– ident: ref34
– ident: ref90
  doi: 10.1007/s00330-024-11115-6
– ident: ref61
  publication-title: arXiv
– ident: ref24
  doi: 10.1093/nsr/nwae403
– ident: ref1
  doi: 10.1038/s41591-023-02448-8
– ident: ref147
  doi: 10.1001/jamanetworkopen.2024.40969
– ident: ref67
  doi: 10.1038/s41746-023-00952-2
– ident: ref119
  doi: 10.18653/v1/2020.blackboxnlp-1.14
– ident: ref17
  doi: 10.2478/jagi-2014-0001
– ident: ref46
  doi: 10.1186/s13000-024-01464-7
– ident: ref49
  doi: 10.1038/s41746-024-01157-x
– ident: ref117
– ident: ref122
  doi: 10.18653/v1/2021.acl-long.416
– ident: ref40
  doi: 10.1056/NEJMra2301725
– ident: ref94
  publication-title: arXiv
– ident: ref68
  publication-title: arXiv
– ident: ref101
  doi: 10.3390/healthcare11162308
– ident: ref109
  doi: 10.1038/s41746-023-00896-7
– ident: ref132
  doi: 10.1038/s41746-025-01443-2
– ident: ref106
  doi: 10.1038/s41746-019-0158-1
– ident: ref136
  doi: 10.1038/s41746-024-01356-6
– ident: ref14
  doi: 10.2196/50638
– year: 2021
  ident: ref137
  publication-title: Mental Health Informatics
– ident: ref130
– ident: ref100
  doi: 10.1001/jamanetworkopen.2023.25000
– ident: ref70
  doi: 10.1101/2023.11.09.566468
– ident: ref66
  publication-title: arXiv
– ident: ref5
  doi: 10.1016/s2589-7500(23)00179-6
– ident: ref92
  doi: 10.3390/electronics13152961
– ident: ref111
  doi: 10.1145/3571730
– ident: ref64
– ident: ref115
  doi: 10.1056/nejmsr2214184
– ident: ref87
  doi: 10.1001/jamanetworkopen.2023.43689
– ident: ref19
  doi: 10.1145/3386252
– ident: ref107
  doi: 10.1038/s41591-024-03097-1
– ident: ref28
  doi: 10.1162/tacl_a_00324
– ident: ref32
  doi: 10.1109/tkde.2021.3090866
– ident: ref113
  doi: 10.1001/jamanetworkopen.2023.27647
– ident: ref39
  doi: 10.1101/2023.02.19.23286155
– ident: ref22
  doi: 10.1038/s41586-020-2973-6
– ident: ref45
  doi: 10.1148/radiol.232756
– ident: ref97
  publication-title: arXiv
– ident: ref11
  doi: 10.7326/M23-2772
– ident: ref78
  publication-title: arXiv
– ident: ref108
  publication-title: arXiv
– ident: ref110
  doi: 10.1038/s41591-024-03423-7
– ident: ref56
  doi: 10.3389/fdmed.2024.1456208
– ident: ref59
  doi: 10.1001/jamanetworkopen.2024.57879
– ident: ref104
  publication-title: arXiv
– ident: ref133
  doi: 10.1038/s41591-024-03258-2
– ident: ref138
  doi: 10.1001/jamanetworkopen.2023.46721
– ident: ref77
  doi: 10.1093/clinchem/hvad106
– ident: ref20
  doi: 10.1109/tmi.2016.2535302
– ident: ref144
  doi: 10.3389/fmed.2024.1380148
– ident: ref79
  doi: 10.1038/s41746-023-00879-8
– ident: ref50
  doi: 10.1145/3712001
SSID ssj0020491
Score 2.4691615
SecondaryResourceType review_article
Snippet Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the rapid...
Background Large language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the...
BackgroundLarge language models (LLMs) can generate outputs understandable by humans, such as answers to medical questions and radiology reports. With the...
SourceID doaj
unpaywall
pubmedcentral
proquest
gale
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
StartPage e71916
SubjectTerms Algorithms
China
Delivery of Health Care
Humans
Language
Large Language Models
Medical care
Medical research
Medicine, Experimental
Review
Technology application
SummonAdditionalLinks – databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV3db9MwED-NThqTJj4Gg8A6jITgKSNfTmLeCqJMiE08UDGeLMd2oKJKJ9po2v567uy0agaIlyiKncQfd_b97LufAV6gBa8zY4tQ11GJACXiYSUiG-aFNjw1KuGKgpNPz_KTSfbxnJ9vwXAVC7Oxf4-6lL8uEE_kt2A752hqD2B7cvZ59M1FDKGiooLE_l6EGVoCO7DXe6831zhK_j8H3o2Z56ZX5O22uVBXl2o225hyxnf96uDCMRWSp8nP43ZZHevrGzyO_6zNPbjTGZts5KXjPmzZZh-GXagCe8m6WCTqG9Yp-T7snHbb7Q-gdtzBzqGo-c4-kdM4Xv0CJ6NT1GYLNm2YD2ViFMr0hnmiURS6cDzX7cIa5rcf2Ncp5nELkMqNsexDSxRb-KOHMBm___LuJOwOZgh1lqfLkGsdJZXOeW1VXEZFQgG72mSW6ONjURqljBapUNqIjLacTZlG-NREOkGdz9MDGDTzxj4GZlWhq7rkvBAGkSLCG65VhrDF8kSYUgdwtOpCeeH5NyTiFmpN6VozgLfUsetEost2D7DdZad9sqrrtCzSIkI5xBELjTLFMyyLRXszLbgI4BWJhSSlxr7XqotNwDISPZYc4RyOliui5QAOezlRGXUv-flKsCQlkQdbY-ftQqZ0bjohXh7AIy9o6zKjUYWovMS6lD0R7FWqn9JMfzgu8Bg_K_DDATxbS-vfG-rJf3M8hd2ETjcm2tD4EAbLX60dosm1rI46xfsNWcMlVw
  priority: 102
  providerName: Unpaywall
Title Implementing Large Language Models in Health Care: Clinician-Focused Review With Interactive Guideline
URI https://www.ncbi.nlm.nih.gov/pubmed/40644686
https://www.proquest.com/docview/3229500265
https://pubmed.ncbi.nlm.nih.gov/PMC12299950
https://doi.org/10.2196/71916
https://doaj.org/article/bff387370b90488399a54c25e8513759
UnpaywallVersion publishedVersion
Volume 27
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAFT
  databaseName: Open Access Digital Library
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: KQ8
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html
  providerName: Colorado Alliance of Research Libraries
– providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: DOA
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVEBS
  databaseName: EBSCOhost Academic Search Ultimate
  customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: ABDBF
  dateStart: 20050101
  isFulltext: true
  titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn
  providerName: EBSCOhost
– providerCode: PRVBFR
  databaseName: Free Medical Journals
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: DIK
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: http://www.freemedicaljournals.com
  providerName: Flying Publisher
– providerCode: PRVFQY
  databaseName: GFMER Free Medical Journals
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: GX1
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: http://www.gfmer.ch/Medical_journals/Free_medical.php
  providerName: Geneva Foundation for Medical Education and Research
– providerCode: PRVAQN
  databaseName: PubMed Central
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: RPM
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/
  providerName: National Library of Medicine
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: 7X7
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: BENPR
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Library Science Database
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1439-4456
  databaseCode: M1O
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/libraryscience
  providerName: ProQuest
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3db9MwED_BkAYSmmB8hW3FSAieojkfjp29ddPKhGiZEBXlKXJsBypV6UQbIf577py0agCJF17yYEeO4zvn7hff_Q7gFXrwJrVOhqbiCgEKF2GZcxdm0liRWB0LTcnJ40l2NU3fzcRsp9QXxYS19MDtwp2WVZUomUiOQ6CyoT3VIjWxcOgqJFL41D2u8g2Y6qAW-r3RPtynQGdUsVOJqCTrWR5P0P_nZ3jHDv0eI3m3qW_0zx96sdgxQKMHcNB5jmzYzvgh3HL1IZx0eQfsNesSi2ihWbdjD2F_3J2dP4LKEwH76KD6K3tPEeB4bf9WMiqJtlixec3avCRGeUlnrGUNRQ0KR0vTrJxl7VkC-zzHe_zfRO0_mOxtQ3xZ-KDHMB1dfrq4CrsqC6FJs2QdCmN4XJpMVE5HisuYsm-NTR1xwUe5slpbkye5NjZP6fzYqoRjq-UohQTduSewVy9r9wyY09KUlRJC5hZhH2IVYXSKsnAizq0yAQw2EihuWjKNAkEIiajwIgrgnOSy7STua9-AGlF0GlH8SyMCeENSLWiHouiM7hINcI7EdVUM0SCjG4rQN4Dj3p24s0yv--VGLwrqonC02i2bVZFQEXSCryKAp62ebOeMHhJCbIXvonoa1Hupfk89_-aJvSMcNseBA3ixVba_L9Tz_7FQR3AvpmrGRBMaHcPe-nvjTtDFWpcDuC1ncgB3zi8n1x8Hfm_hdRx9wLbp5Hr45Re_Rict
linkProvider Directory of Open Access Journals
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwhV3db9MwED-NThqTJj4Gg8A6jITgKSNfTmLeCqJMiE08UDGeLMd2oKJKJ9po2v567uy0agaIlyiKncQfd_b97LufAV6gBa8zY4tQ11GJACXiYSUiG-aFNjw1KuGKgpNPz_KTSfbxnJ9vwXAVC7Oxf4-6lL8uEE_kt2A752hqD2B7cvZ59M1FDKGiooLE_l6EGVoCO7DXe6831zhK_j8H3o2Z56ZX5O22uVBXl2o225hyxnf96uDCMRWSp8nP43ZZHevrGzyO_6zNPbjTGZts5KXjPmzZZh-GXagCe8m6WCTqG9Yp-T7snHbb7Q-gdtzBzqGo-c4-kdM4Xv0CJ6NT1GYLNm2YD2ViFMr0hnmiURS6cDzX7cIa5rcf2Ncp5nELkMqNsexDSxRb-KOHMBm___LuJOwOZgh1lqfLkGsdJZXOeW1VXEZFQgG72mSW6ONjURqljBapUNqIjLacTZlG-NREOkGdz9MDGDTzxj4GZlWhq7rkvBAGkSLCG65VhrDF8kSYUgdwtOpCeeH5NyTiFmpN6VozgLfUsetEost2D7DdZad9sqrrtCzSIkI5xBELjTLFMyyLRXszLbgI4BWJhSSlxr7XqotNwDISPZYc4RyOliui5QAOezlRGXUv-flKsCQlkQdbY-ftQqZ0bjohXh7AIy9o6zKjUYWovMS6lD0R7FWqn9JMfzgu8Bg_K_DDATxbS-vfG-rJf3M8hd2ETjcm2tD4EAbLX60dosm1rI46xfsNWcMlVw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Implementing+Large+Language+Models+in+Health+Care%3A+Clinician-Focused+Review+With+Interactive+Guideline&rft.jtitle=Journal+of+medical+Internet+research&rft.au=HongYi+Li&rft.au=Jun-Fen+Fu&rft.au=Andre+Python&rft.date=2025-07-11&rft.pub=JMIR+Publications&rft.eissn=1438-8871&rft.volume=27&rft.spage=e71916&rft_id=info:doi/10.2196%2F71916&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_bff387370b90488399a54c25e8513759
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1438-8871&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1438-8871&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1438-8871&client=summon