A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions
This systematic review evaluates recent literature from January 2021 to March 2024 on large language model (LLM) applications across diverse medical specialties. Searching PubMed, Web of Science, and Scopus, we included 84 studies. LLMs were applied to tasks such as clinical natural language process...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/16/6/489 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849472417537196032 |
|---|---|
| author | Asma Musabah Alkalbani Ahmed Salim Alrawahi Ahmad Salah Venus Haghighi Yang Zhang Salam Alkindi Quan Z. Sheng |
| author_facet | Asma Musabah Alkalbani Ahmed Salim Alrawahi Ahmad Salah Venus Haghighi Yang Zhang Salam Alkindi Quan Z. Sheng |
| author_sort | Asma Musabah Alkalbani |
| collection | DOAJ |
| description | This systematic review evaluates recent literature from January 2021 to March 2024 on large language model (LLM) applications across diverse medical specialties. Searching PubMed, Web of Science, and Scopus, we included 84 studies. LLMs were applied to tasks such as clinical natural language processing, medical decision support, education, and aiding diagnostic processes. While studies reported benefits such as improved efficiency and, in some specific NLP tasks, high accuracy above 90%, significant challenges persist concerning reliability, ethical implications, and performance consistency, with accuracy in broader diagnostic support applications showing substantial variability, with some as low as 3%. The overall risk of bias in the reviewed literature was considerably low in 72 studies. Key findings highlight a substantial heterogeneity in LLM performance across different medical tasks and contexts, preventing meta-analysis due to a lack of standardized methodologies. Future efforts should prioritize developing domain-specific LLMs using robust medical data and establishing rigorous validation standards to ensure their safe and effective clinical integration. Trial registration: PROSPERO (CRD42024561381). |
| format | Article |
| id | doaj-art-9fbbdcd8c95b4d6e9217766d8a961df2 |
| institution | Kabale University |
| issn | 2078-2489 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj-art-9fbbdcd8c95b4d6e9217766d8a961df22025-08-20T03:24:33ZengMDPI AGInformation2078-24892025-06-0116648910.3390/info16060489A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future DirectionsAsma Musabah Alkalbani0Ahmed Salim Alrawahi1Ahmad Salah2Venus Haghighi3Yang Zhang4Salam Alkindi5Quan Z. Sheng6Department of Information Technology, College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 511, OmanDepartment of Information Technology, College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 511, OmanDepartment of Information Technology, College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 511, OmanSchool of Computing, Macquarie University, Sydney, NSW 2109, AustraliaThe Anuradha and Vikas Sinha Department of Data Science, University of North Texas, Denton, TX 76203, USADepartment of Hematology, College of Medicine & Health Science, Sultan Qaboos University, Muscat 123, OmanSchool of Computing, Macquarie University, Sydney, NSW 2109, AustraliaThis systematic review evaluates recent literature from January 2021 to March 2024 on large language model (LLM) applications across diverse medical specialties. Searching PubMed, Web of Science, and Scopus, we included 84 studies. LLMs were applied to tasks such as clinical natural language processing, medical decision support, education, and aiding diagnostic processes. While studies reported benefits such as improved efficiency and, in some specific NLP tasks, high accuracy above 90%, significant challenges persist concerning reliability, ethical implications, and performance consistency, with accuracy in broader diagnostic support applications showing substantial variability, with some as low as 3%. The overall risk of bias in the reviewed literature was considerably low in 72 studies. Key findings highlight a substantial heterogeneity in LLM performance across different medical tasks and contexts, preventing meta-analysis due to a lack of standardized methodologies. Future efforts should prioritize developing domain-specific LLMs using robust medical data and establishing rigorous validation standards to ensure their safe and effective clinical integration. Trial registration: PROSPERO (CRD42024561381).https://www.mdpi.com/2078-2489/16/6/489artificial intelligenceclinical decision support systemslarge language modelsclinical natural language processingmedical specialties |
| spellingShingle | Asma Musabah Alkalbani Ahmed Salim Alrawahi Ahmad Salah Venus Haghighi Yang Zhang Salam Alkindi Quan Z. Sheng A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions Information artificial intelligence clinical decision support systems large language models clinical natural language processing medical specialties |
| title | A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions |
| title_full | A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions |
| title_fullStr | A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions |
| title_full_unstemmed | A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions |
| title_short | A Systematic Review of Large Language Models in Medical Specialties: Applications, Challenges and Future Directions |
| title_sort | systematic review of large language models in medical specialties applications challenges and future directions |
| topic | artificial intelligence clinical decision support systems large language models clinical natural language processing medical specialties |
| url | https://www.mdpi.com/2078-2489/16/6/489 |
| work_keys_str_mv | AT asmamusabahalkalbani asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT ahmedsalimalrawahi asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT ahmadsalah asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT venushaghighi asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT yangzhang asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT salamalkindi asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT quanzsheng asystematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT asmamusabahalkalbani systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT ahmedsalimalrawahi systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT ahmadsalah systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT venushaghighi systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT yangzhang systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT salamalkindi systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections AT quanzsheng systematicreviewoflargelanguagemodelsinmedicalspecialtiesapplicationschallengesandfuturedirections |