journal article·2025-04-07

Application of large language models in medicine

Fenglin Liu, Hongjian Zhou, Boyang Gu, Xinyu Zou, Jinfa Huang, Jinge Wu, Yiru Li, Sam S. Chen, Yining Hua, Peilin Zhou, Junling Liu, Chengfeng Mao, Chenyu You, Xian Wu, Yefeng Zheng, Lei Clifton, Zheng Li, Jiebo Luo, David A. Clifton

Nature Reviews Bioengineering· Volume 3· Issue 6
Publisher page

Abstract

Large language models (LLMs), such as ChatGPT, have received great attention owing to their capabilities for understanding and generating human language. Despite a trend in researching the application of LLMs in supporting different medical tasks (such as enhancing clinical diagnostics and providing medical education), a comprehensive assessment of their development, practical applications and outcomes in the medical space is still missing. Therefore, this Review aims to provide an overview of the development and deployment of LLMs in medicine, including the challenges and opportunities they face. In terms of development, we discuss the principles of existing medical LLMs, including their basic model structures, number of parameters, and sources and scales of data used for model development. In terms of deployment, we compare different LLMs across various medical tasks and with state-of-the-art lightweight models.
Source: openaire · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Machine Learning in Healthcare · Topic Modeling · Artificial Intelligence in Healthcare and Education

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (100+)

Show source-provided references
1. Zhao, W. X. et al. A survey of large language models. Preprint at arXiv https://doi.org/10.48550/arXiv.2303.18223 (2023).10.48550/arXiv.2303.18223 ↗
2. Yang, J. et al. Harnessing the power of LLMs in practice: a survey on ChatGPT and beyond. ACM Trans. Knowl. Discov. Data 18, 160 (2024).10.1145/3649506 ↗
3. Chowdhery, A. et al. PaLM: scaling language modeling with pathways. Preprint at arXiv https://doi.org/10.48550/arXiv.2204.02311 (2022).10.48550/arXiv.2204.02311 ↗
4. Touvron, H. et al. LLaMA: open and efficient foundation language models. Preprint at arXiv https://doi.org/10.48550/arXiv.2302.13971 (2023).10.48550/arXiv.2302.13971 ↗
5. Touvron, H. et al. Llama 2: open foundation and fine-tuned chat models. Preprint at arXiv https://doi.org/10.48550/arXiv.2307.09288 (2023).10.48550/arXiv.2307.09288 ↗
6. Brown, T. et al. Language models are few-shot learners. In Proc. 34th Int. Conf. Neural Inform. Process. Syst.s (eds Larochelle, H. et al.) 1877–1901 (2020).
7. OpenAI et al. GPT-4 technical report. Preprint at arXiv https://doi.org/10.48550/arXiv.2303.08774 (2023).10.48550/arXiv.2303.08774 ↗
8. Du, Z. et al. GLM: general language model pretraining with autoregressive blank infilling. In Proc. 60th Annu. Meet. Assoc. Comput. Linguist. (eds Muresan, S. et al.) 320–335 (ACL, 2022).10.18653/v1/2022.acl-long.26 ↗
9. Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172–180 (2023).10.1038/s41586-023-06291-2 ↗
10. Singhal, K. et al. Toward expert-level medical question answering with large language models. Nat. Med. https://doi.org/10.1038/s41591-024-03423-7 (2025).10.1038/s41591-024-03423-7 ↗
11. Nori, H. et al. Can generalist foundation models outcompete special-purpose tuning? Case study in medicine. Preprint at arXiv https://doi.org/10.48550/arXiv.2311.16452 (2023).10.48550/arXiv.2311.16452 ↗
12. Wu, C. et al. PMC-LLaMA: toward building open-source language models for medicine. J. Am. Med. Inform. Assoc. 31, 1833–1843 (2024).10.1093/jamia/ocae045 ↗
13. Jin, D. et al. What disease does this patient have? A large-scale open domain question answering dataset from medical exams. Appl. Sci. 11, 6421 (2021).10.3390/app11146421 ↗
14. Li, Y. et al. ChatDoctor: a medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge. Cureus 15, 6 (2023).
15. Han, T. et al. MedAlpaca — an open-source collection of medical conversational AI models and training data. Preprint at arXiv https://doi.org/10.48550/arXiv.2304.08247 (2023).10.48550/arXiv.2304.08247 ↗
16. Wang, H. et al. HuaTuo: tuning LLaMA model with Chinese medical knowledge. Preprint at arXiv https://doi.org/10.48550/arXiv.2304.06975 (2023).10.48550/arXiv.2304.06975 ↗
17. Toma, A. et al. Clinical Camel: an open-source expert-level medical language model with dialogue-based knowledge encoding. Preprint at arXiv https://doi.org/10.48550/arXiv.2305.12031 (2023).10.48550/arXiv.2305.12031 ↗
18. Thirunavukarasu, A. J. et al. Large language models in medicine. Nat. Med. 29, 1930–1940 (2023).10.1038/s41591-023-02448-8 ↗
19. Patel, S. B. & Lam, K. ChatGPT: the future of discharge summaries? Lancet Digit. Health 5, e107–e108 (2023).10.1016/S2589-7500(23)00021-3 ↗
20. Yang, X. et al. A large language model for electronic health records. npj Digit. Med. 5, 194 (2022).10.1038/s41746-022-00742-2 ↗
21. Abd-Alrazaq, A. et al. Large language models in medical education: opportunities, challenges, and future directions. JMIR Med. Educ. 9, e48291 (2023).10.2196/48291 ↗
22. Peng, C. et al. A study of generative large language model for medical research and healthcare. npj Digit. Med. 6, 210 (2023).10.1038/s41746-023-00958-w ↗
23. Alsentzer, E. et al. Publicly available clinical BERT embeddings. Preprint at arXiv https://doi.org/10.48550/arXiv.1904.03323 (2019).10.48550/arXiv.1904.03323 ↗
24. Johnson, A. E. W. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 (2016).10.1038/sdata.2016.35 ↗
25. Wu, J. et al. Clinical text datasets for medical artificial intelligence and large language models — a systematic review. NEJM AI 1, AIra2400012 (2024).10.1056/AIra2400012 ↗
26. Lee, J. et al. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36, 1234–1240 (2020).10.1093/bioinformatics/btz682 ↗
27. Gu, Y. et al. Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthc. 3, 1–23 (2021).10.1145/3458754 ↗
28. Luo, R. et al. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Brief. Bioinform. 23, bbac409 (2022).10.1093/bib/bbac409 ↗
29. Ye, Q. et al. Qilin-Med: multi-stage knowledge injection advanced medical large language model. Preprint at arXiv https://doi.org/10.48550/arXiv.2310.09089 (2023).10.48550/arXiv.2310.09089 ↗
30. Xiong, H. et al. DoctorGLM: fine-tuning your Chinese doctor is not a herculean task. Preprint at arXiv https://doi.org/10.48550/arXiv.2304.01097 (2023).10.48550/arXiv.2304.01097 ↗
31. Yang, S. et al. Zhongjing: enhancing the Chinese medical capabilities of large language model through expert feedback and real-world multi-turn dialogue. In Proc. AAAI Conf. Artif. Intell. (eds Wooldridge, M.J. et al.) 19368–19376 (AAAI, 2023).10.1609/aaai.v38i17.29907 ↗
32. Zhang, S. et al. Instruction tuning for large language models: a survey. Preprint at arXiv https://doi.org/10.48550/arXiv.2308.10792 (2023).10.48550/arXiv.2308.10792 ↗
33. He, K. et al. A survey of large language models for healthcare: from data, technology, and applications to accountability and ethics. Inf. Fusion 118, 102963 (2025).10.1016/j.inffus.2025.102963 ↗
34. Byambasuren, O. et al. Preliminary study on the construction of Chinese medical knowledge graph. J. Chin. Inf. Process. 33, 1–9 (2019).
35. Moor, M. et al. Med-Flamingo: a multimodal medical few-shot learner. In Proc. 3rd Mach. Learn. Health Symp. (eds Hegselmann, S. et al.) 353–367 (PMLR, 2023).
36. Li, C. et al. LLaVA-Med: training a large language-and-vision assistant for biomedicine in one day. In Ann. Conf. Neural Inform. Process. Syst. (eds Oh, A. et al.) 28541–28564 (Curran Associates, 2023).10.32388/VLXB6M ↗
37. Saab, K. et al. Capabilities of Gemini models in medicine. Preprint at arXiv https://doi.org/10.48550/arXiv.2404.18416 (2024).10.48550/arXiv.2404.18416 ↗
38. Hyland, S. L. et al. MAIRA-1: a specialised large multimodal model for radiology report generation. Preprint at arXiv https://doi.org/10.48550/arXiv.2311.13668 (2023).10.48550/arXiv.2311.13668 ↗
39. Wu, C., Zhang, X., Zhang, Y., Wang, Y. & Xie, W. Towards generalist foundation model for radiology. Preprint at arXiv https://doi.org/10.48550/arXiv.2308.02463 (2023).10.48550/arXiv.2308.02463 ↗
40. Zhang, X. et al. AlpaCare: instruction-tuned large language models for medical application. Preprint at arXiv https://doi.org/10.48550/arXiv.2310.14558 (2023).10.48550/arXiv.2310.14558 ↗
41. Hu, E. J. et al. LoRA: low-rank adaptation of large language models. Preprint at arXiv https://doi.org/10.48550/arXiv.2106.09685 (2021).10.48550/arXiv.2106.09685 ↗
42. Li, X. L. & Liang, P. Prefix-tuning: optimizing continuous prompts for generation. In Proc. 59th Annu. Meet. Assoc. Comput. Linguist. (eds Zong, C. et al.) 4582–4597 (ACL, 2021).10.18653/v1/2021.acl-long.353 ↗
43. Liu, X. et al. P-Tuning: prompt tuning can be comparable to fine-tuning across scales and tasks. In Proc. 60th Annu. Meet. Assoc. Comput. Linguist. (eds Muresan, S. et al.) 61–68 (ACL, 2022).10.18653/v1/2022.acl-short.8 ↗
44. Houlsby, N. et al. Parameter-efficient transfer learning for NLP. In Proc. 36th Int. Conf. Mach. Learn. (eds Chaudhuri, K. & Salakhutdinov, R.) 2790–2799 (PMLR, 2019).
45. Xu, C., Guo, D., Duan, N. & McAuley, J. Baize: an open-source chat model with parameter-efficient tuning on self-chat data. In Proc. 2023 Conf. Empir. Methods Nat. Lang. Process. (eds Bouamor, H. et al.) 6268–6278 (ACL, 2023).10.18653/v1/2023.emnlp-main.385 ↗
46. Shoham, O. B. & Rappoport, N. CPLLM: clinical prediction with large language models. PLoS Digit. Health 3, e0000680 (2024).10.1371/journal.pdig.0000680 ↗
47. Dong, Q. et al. A survey on in-context learning. In Proc. Conf. Empir. Methods Nat. Lang. Process. (eds Al-Onaizan, Y. et al.) 1107–1128 (ACL, 2024).
48. Wei, J. et al. Chain-of-thought prompting elicits reasoning in large language models. In Proc. 36th Int. Conf. Neural Inform. Process. Syst. (eds Koyejo, S. et al.) 24824–24837 (Curran Associates, 2022).
49. Liu, Z. et al. DeID-GPT: zero-shot medical text de-identification by GPT-4. Preprint at arXiv https://doi.org/10.48550/arXiv.2303.11032 (2023).10.48550/arXiv.2303.11032 ↗
50. Lester, B., Al-Rfou, R. & Constant, N. The power of scale for parameter-efficient prompt tuning. In Proc. Confe. Empir. Methods Nat. Lang. Process. (eds Moens, M.-F. et al.) 3045–3059 (ACL, 2021).10.18653/v1/2021.emnlp-main.243 ↗
51. Gao, Y. et al. Retrieval-augmented generation for large language models: a survey. Preprint at arXiv https://doi.org/10.48550/arXiv.2312.10997 (2023).10.48550/arXiv.2312.10997 ↗
52. Luo, Y. et al. An empirical study of catastrophic forgetting in large language models during continual fine-tuning. Preprint at arXiv https://doi.org/10.48550/arXiv.2308.08747 (2023).10.48550/arXiv.2308.08747 ↗
53. Xiong, G., Jin, Q., Lu, Z. & Zhang, A. Benchmarking retrieval-augmented generation for medicine. Preprint at arXiv https://doi.org/10.48550/arXiv.2402.13178 (2024).10.48550/arXiv.2402.13178 ↗
54. Li, X. & Li, J. AnglE-optimized text embeddings. Preprint at arXiv https://doi.org/10.48550/arXiv.2309.12871 (2023).10.48550/arXiv.2309.12871 ↗
55. Wang, G. et al. Voyager: an open-ended embodied agent with large language models. Preprint at arXiv https://doi.org/10.48550/arXiv.2305.16291 (2023).10.48550/arXiv.2305.16291 ↗
56. Chen, J. et al. M3-Embedding: multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. In Findings Assoc. Comput. Linguist. (eds Ku, L. et al.) 2318–2335 (ACL, 2024).10.18653/v1/2024.findings-acl.137 ↗
57. Shao, Z. et al. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy. In Findings Assoc. Comput. Linguist. (eds Bouamor, H. et al.) 9248–9274 (ACL, 2023).10.18653/v1/2023.findings-emnlp.620 ↗
58. Trivedi, H., Balasubramanian, N., Khot, T. & Sabharwal, A. Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions. In Proc. 61st Annu. Meet. Asso. Comput. Linguist. (eds Rogers, A. et al.) 10014–10037 (ACL, 2023).10.18653/v1/2023.acl-long.557 ↗
59. Asai, A., Wu, Z., Wang, Y., Sil, A. & Hajishirzi, H. Self-rag: learning to retrieve, generate, and critique through self-reflection. Preprint at arXiv https://doi.org/10.48550/arXiv.2310.11511 (2023).10.48550/arXiv.2310.11511 ↗
60. Zakka, C. et al. Almanac—retrieval-augmented language models for clinical medicine. NEJM AI 1, AIoa2300068 (2024).10.1056/AIoa2300068 ↗
61. Kim, J. & Min, M. From RAG to QA-RAG: integrating generative AI for pharmaceutical regulatory compliance process. Preprint at arXiv https://doi.org/10.48550/arXiv.2402.01717 (2024).10.48550/arXiv.2402.01717 ↗
62. Shi, W. et al. Retrieval-augmented large language models for adolescent idiopathic scoliosis patients in shared decision-making. In Proc. 14th ACM Int. Conf. Bioinform. Comput. Biol. Health Inform. (ACM, 2023).10.1145/3584371.3612956 ↗
63. Tang, L. et al. Evaluating large language models on medical evidence summarization. npj Digit. Med. 6, 158 (2023).10.1038/s41746-023-00896-7 ↗
64. Van Veen, D. et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat. Med. 30, 1134–1142 (2024).10.1038/s41591-024-02855-5 ↗
65. Ondov, B., Attal, K. & Demner-Fushman, D. A survey of automated methods for biomedical text simplification. J. Am. Med. Inform. Assoc. 29, 1976–1988 (2022).10.1093/jamia/ocac149 ↗
66. Liu, F. et al. Retrieve, reason, and refine: generating accurate and faithful patient instructions. In Proc. 36th Int. Conf. Neural Inform. Process. Syst. (eds Koyejo, S. et al.) 18864–18877 (Curran Associates, 2022).
67. Joseph, S. et al. Multilingual simplification of medical texts. In Proc. Conf. Empir. Methods Nat. Lang. Process. (eds Bouamor, H. et al.) 16662–16692 (ACL, 2023).10.18653/v1/2023.emnlp-main.1037 ↗
68. Jin, Q., Dhingra, B., Liu, Z., Cohen, W. W. & Lu, X. PubMedQA: a dataset for biomedical research question answering. In Proc. Conf. Empir. Methods Nat. Lang. Process. & 9th Int. Joint Conf. Nat. Lang. Process. (eds Inui, K. et al.) 2567–2577 (ACL, 2019).10.18653/v1/D19-1259 ↗
69. Pal, A., Umapathi, L. K. & Sankarasubbu, M. MedMCQA: a large-scale multi-subject multi-choice dataset for medical domain question answering. In Proc. Conf. Health Inference Learn. (eds Flores, G. et al.) 248–260 (PMLR, 2022).
70. Omar, M., Nadkarni, G. N., Klang, E. & Glicksberg, B. S. Large language models in medicine: a review of current clinical trials across healthcare applications. PLoS Digit. Health 3, e0000662 (2024).10.1371/journal.pdig.0000662 ↗
71. Rajpurkar, P., Chen, E., Banerjee, O. & Topol, E. J. AI in health and medicine. Nat. Med. 28, 31–38 (2022).10.1038/s41591-021-01614-0 ↗
72. Jiang, L. Y. et al. Health system-scale language models are all-purpose prediction engines. Nature 619, 357–362 (2023).10.1038/s41586-023-06160-y ↗
73. Gao, Y. et al. Leveraging a medical knowledge graph into large language models for diagnosis prediction. Preprint at arXiv https://doi.org/10.48550/arXiv.2308.14321 (2023).10.48550/arXiv.2308.14321 ↗
74. Chung, H. W. et al. Scaling instruction-finetuned language models. J. Mach. Learn. Res. 25, 1–53 (2024).
75. McDuff, D. et al. Towards accurate differential diagnosis with large language models. Preprint at arXiv https://doi.org/10.48550/arXiv.2312.00164 (2023).10.48550/arXiv.2312.00164 ↗
76. Kraljevic, Z. et al. Foresight—a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study. Lancet Digit. Health 6, e281–e290 (2024).10.1016/S2589-7500(24)00025-6 ↗
77. Jin, Q. et al. Matching patients to clinical trials with large language models. Na. Commun. 15, 9074 (2024).10.1038/s41467-024-53081-z ↗
78. US National Library of Medicine. ClinicalTrials.gov https://clinicaltrials.gov/study/NCT06002425 (2024).
79. German Clinical Trials Register. drks.de https://drks.de/search/en/trial/DRKS00033775 (2024).
80. Wang, S., Zhao, Z., Ouyang, X., Wang, Q. & Shen, D. Interactive computer-aided diagnosis on medical image using large language models. Commun. Eng. 3, 133 (2024).10.1038/s44172-024-00271-8 ↗
81. Huang, C.-W., Tsai, S.-C. & Chen, Y.-N. PLM-ICD: automatic ICD coding with pretrained language models. In Proc. 4th Clin. Nat. Lang. Process. Workshop (eds Naumann, T et al.) 10–20 (ACL, 2022).10.18653/v1/2022.clinicalnlp-1.2 ↗
82. Wang, H., Gao, C., Dantona, C., Hull, B. & Sun, J. DRG–LLaMA: tuning LLaMA model to predict diagnosis-related group for hospitalized patients. npj Digit. Med. 7, 16 (2024).10.1038/s41746-023-00989-3 ↗
83. Liu, J., Yang, S., Peng, T., Hu, X. & Zhu, Q. ChatICD: prompt learning for few-shot ICD coding through ChatGPT. In 2023 IEEE Int. Conf. Bioinform. Biomed. (eds Jian,g, X. et al.) 4360–4367 (IEEE, 2023).10.1109/BIBM58861.2023.10385482 ↗
84. Yang, Z., Batra, S. S., Stremmel, J. & Halperin, E. Surpassing GPT-4 medical coding with a two-stage approach. Preprint at arXiv https://doi.org/10.48550/arXiv.2311.13735 (2023).10.48550/arXiv.2311.13735 ↗
85. Elkin, P. L. & Brown, S. H. in Terminology, Ontology and their Implementations 2nd edn (ed. Elkin, P. L.) 367–370 (Springer, 2023).10.1007/978-3-031-11039-9_14 ↗
86. Liu, Y. et al. RoBERTa: a robustly optimized BERT pretraining approach. Preprint at arXiv https://doi.org/10.48550/arXiv.1907.11692 (2019).10.48550/arXiv.1907.11692 ↗
87. Liu, F., Wu, X., Ge, S., Fan, W. & Zou, Y. Exploring and distilling posterior and prior knowledge for radiology report generation. In 2021 IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) 13748–13757 (IEEE, 2021).10.1109/CVPR46437.2021.01354 ↗
88. Liu, X. et al. Reporting guidelines for clinical trials evaluating artificial intelligence interventions are needed. Nat. Med. 25, 1467–1469 (2019).10.1038/s41591-019-0603-3 ↗
89. Ma, C. et al. An iterative optimizing framework for radiology report summarization with ChatGPT. In IEEE Trans. Artif. Intell. 4163–4175 (IEEE, 2024).10.1109/TAI.2024.3364586 ↗
90. Van Veen, D. et al. RadAdapt: radiology report summarization via lightweight domain adaptation of large language models. Preprint at arXiv https://doi.org/10.48550/arXiv.2305.01146 (2023).10.48550/arXiv.2305.01146 ↗
91. Lin, C.-Y. ROUGE: a package for automatic evaluation of summaries. In Proc. Workshop Text Summarization Branches Out 74–81 (ACL, 2004).
92. Papineni, K., Roukos, S., Ward, T. & Zhu, W. BLEU: a method for automatic evaluation of machine translation. In Proc. 40th Annu. Meet. Assoc. Comput. Linguist. (eds Isabelle, P. et al.) 311–318 (ACL, 2002).10.3115/1073083.1073135 ↗
93. Yu, F. et al. Evaluating progress in automatic chest X-ray radiology report generation. Patterns 4, 100802 (2023).10.1016/j.patter.2023.100802 ↗
94. US National Library of Medicine. ClinicalTrials.gov https://clinicaltrials.gov/study/NCT06263855 (2024).
95. Xie, Q. et al. Faithful AI in medicine: a systematic review with large language models and beyond. Preprint at medRxiv https://doi.org/10.1101/2023.04.18.23288752 (2023).10.1101/2023.04.18.23288752 ↗
96. Dupont, P. E. A decade retrospective of medical robotics research from 2010 to 2020. Sci. Robot. 6, eabi8017 (2021).10.1126/scirobotics.abi8017 ↗
97. Xu, H. et al. Enhancing surgical robots with embodied intelligence for autonomous ultrasound scanning. Preprint at arXiv https://doi.org/10.48550/arXiv.2405.00461 (2024).10.48550/arXiv.2405.00461 ↗
98. Wang, J. et al. Large language models for robotics: opportunities, challenges, and perspectives. Preprint at arXiv https://doi.org/10.48550/arXiv.2401.04334 (2024).10.48550/arXiv.2401.04334 ↗
99. Moghani, M. et al. SuFIA: language-guided augmented dexterity for robotic surgical assistants. Preprint at arXiv https://doi.org/10.48550/arXiv.2405.05226 (2024).10.48550/arXiv.2405.05226 ↗
100. Killeen, B. D., Chaudhary, S., Osgood, G. & Unberath, M. Take a shot! natural language control of intelligent robotic X-ray systems in surgery. Int. J. Comput. Assist. Radiol. Surg. 19, 1165–1173 (2024).10.1007/s11548-024-03120-3 ↗