Large Language Models for Clinical Knowledge Extraction
Keywords:
Large language models, electronic health records, clinical informatics, natural language processing, named entity recognition, relation extraction, automatic reasoning, automatic summarization, region-based visual question answering, open information extraction.Abstract
Large Language Models (LLMs) can facilitate structured knowledge extraction from unstructured clinical information sources, such as electronic health records (EHRs), clinical text notes, and clinical trial protocols. This capability bridging heterogeneous data modalities has the potential to power a broad range of downstream clinical decision support and data mining tasks.
Clinical informatics research often relies on specific types of information that are not readily available in explicitly structured form in the corresponding data repositories. These “structured knowledge” types are prevalent in a variety of clinical data sources, such as coded EHRs, but LLMs can offer a different, complementary approach. The task of mapping raw unlabeled text to structured knowledge types involves providing rich supervision during LLM training—using either fine-tuning or prompting mechanisms—to create and support structured knowledge extraction capabilities.
References
1. Al Nazi, Z., & Peng, W. (2024). Large language models in healthcare and medical domain: A review. Informatics, 11(3), 57.
2. Wang, D., & Zhang, S. (2024). Large language models in medical and healthcare fields: Applications, advances, and challenges. Artificial Intelligence Review, 57, 299.
3. Cascella, M., Semeraro, F., Montomoli, J., Bellini, V., Piazza, O., & Bignami, E. (2024). The breakthrough of large language models release for medical applications: 1-year timeline and perspectives. Journal of Medical Systems, 48(1), 22.
4. Nerella, S., Bandyopadhyay, S., Zhang, J., Contreras, M., Siegel, S., Bumin, A., Silva, B., Sena, J., Shickel, B., Bihorac, A., Khezeli, K., & Rashidi, P. (2024). Transformers and large language models in healthcare: A review. Artificial Intelligence in Medicine, 154, 102900.
5. Denecke, K., May, R., & Rivera-Romero, O. (2024). Transformer models in healthcare: A survey and thematic analysis of potentials, shortcomings and risks. Journal of Medical Systems, 48(1), 23.
6. Zhang, Y., Wang, X., Li, H., Chen, Y., & Sun, J. (2024). The application of large language models in medicine: A scoping review. iScience, 27(5), 109713.
7. Omar, M., Patel, V., Shah, N., & Singh, A. (2024). Large language models in medicine: A review of current clinical trials across healthcare applications. PLOS Digital Health, 3(11), e0000662.
8. Liu, F., Zhou, H., Hua, Y., Rohanian, O., Clifton, L., & Clifton, D. A. (2024). Large language models in healthcare: A comprehensive benchmark. medRxiv.
9. Gema, A. P., Lee, C., Minervini, P., Daines, L., Simpson, T. I., & Alex, B. (2024). Edinburgh Clinical NLP at MEDIQA-CORR 2024: Guiding large language models with hints. arXiv Preprint arXiv:2405.18028.
10. Jullien, M., Valentino, M., & Freitas, A. (2024). SemEval-2024 Task 2: Safe biomedical natural language inference for clinical trials. arXiv Preprint arXiv:2404.04963.
11. Wu, S., Roberts, K., Datta, S., Du, J., Ji, Z., Si, Y., Soni, S., Wang, Q., Wei, Q., Xiang, Y., Zhao, B., & Xu, H. (2024). Deep learning in clinical natural language processing: Progress and future directions. Journal of Biomedical Informatics, 149, 104563.
12. Lehman, E., Jain, S., Pfohl, S., Wallace, B. C., & Johnson, A. E. W. (2024). Clinical language models and the future of healthcare AI. Nature Medicine, 30(4), 812–820.
13. Singhal, K., Azizi, S., Tu, T., Mahdavi, S., Wei, J., Chung, H., Scales, N., et al. (2024). Large language models encode clinical knowledge. Nature, 630(8016), 172–180.
14. Tu, T., Azizi, S., Driess, D., Schaekermann, M., Amin, M., Chang, P. C., Carroll, A., et al. (2024). Towards generalist biomedical AI. Nature, 627(8004), 555–563.
15. Yang, X., Chen, A., PourNejatian, N., Shin, H. C., Smith, K., Parisien, C., Compas, C., et al. (2024). GatorTronGPT: A large clinical language model for healthcare applications. NPJ Digital Medicine, 7(1), 41.
16. Agrawal, M., Hegselmann, S., Lang, H., Kim, Y., Fridman, D., & Sontag, D. (2024). Large language models are few-shot clinical information extractors. Proceedings of the AAAI Conference on Artificial Intelligence, 38(1), 1–9.
17. Li, Y., Chen, Q., Huang, X., & Xu, H. (2024). Clinical named entity recognition using large language models. Journal of Biomedical Informatics, 148, 104512.
18. Zhang, H., Wang, J., Liu, Y., & Roberts, K. (2024). Prompt engineering for clinical information extraction with large language models. Artificial Intelligence in Medicine, 152, 102854.
19. Xu, J., Wang, Z., Zhao, Y., & Du, J. (2024). Retrieval-augmented generation for clinical knowledge extraction from electronic health records. NPJ Digital Medicine, 7(1), 95.
20. Chen, L., Wei, Q., Wang, Y., & Xu, H. (2024). Evaluating ChatGPT for clinical concept extraction tasks. Journal of the American Medical Informatics Association, 31(4), 854–864.
21. Huang, K., Altosaar, J., & Ranganath, R. (2024). Clinical foundation models for healthcare data mining. Nature Biomedical Engineering, 8(3), 201–214.
22. Patel, S., Lam, K., & Fleming, S. (2024). Generative AI for clinical documentation and knowledge extraction. BMJ Health & Care Informatics, 31(1), e100912.
23. Roberts, K., Demner-Fushman, D., & Kilicoglu, H. (2024). Biomedical information extraction in the era of large language models. Briefings in Bioinformatics, 25(2), bbae074.
24. Luo, R., Sun, L., Xia, Y., Qin, T., Zhang, S., Poon, H., & Liu, T. Y. (2024). BioGPT and the evolution of biomedical language models. Patterns, 5(2), 100982.
25. Fries, J. A., Steinberg, E., Khattar, S., Fleming, S., & Shah, N. H. (2024). Foundation models for electronic health records. Nature Medicine, 30(2), 295–304.
26. Jin, Q., Kim, W., Chen, Q., & Lu, Z. (2024). PubMedGPT and biomedical knowledge discovery. Bioinformatics, 40(5), btae112.
27. Wang, Q., Wei, Q., Ji, Z., & Xu, H. (2024). Clinical relation extraction with generative language models. Journal of Biomedical Informatics, 150, 104589.
28. Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y., Madotto, A., & Fung, P. (2024). Survey of hallucination in natural language generation and healthcare applications. ACM Computing Surveys, 56(6), 1–38.
29. Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, E., Feng, M., & Mark, R. G. (2024). Clinical language technologies for EHR intelligence. NPJ Digital Medicine, 7(1), 68.
30. Shickel, B., Tighe, P. J., Bihorac, A., & Rashidi, P. (2024). Deep EHR understanding with transformer models. Artificial Intelligence in Medicine, 151, 102835.
31. Zhou, H., Liu, F., Hua, Y., & Clifton, D. A. (2024). Open-ended evaluation of healthcare large language models. medRxiv.
32. Li, X., Sun, Y., Wang, H., & Chen, M. (2024). Knowledge graph enhanced large language models for clinical decision support. Expert Systems with Applications, 245, 123107.
33. Chen, T., Liu, Z., & Wang, X. (2024). Medical question answering using retrieval-augmented large language models. Information Processing & Management, 61(4), 103749.
34. Gupta, P., Sharma, A., & Singh, D. (2024). Clinical event extraction using generative transformers. Computer Methods and Programs in Biomedicine, 248, 108107.
35. Park, S., Kim, H., & Lee, J. (2024). Large language models for temporal clinical information extraction. BMC Medical Informatics and Decision Making, 24(1), 114.
36. Zhao, X., Wang, J., & Roberts, K. (2024). Few-shot biomedical relation extraction with GPT-based models. Bioinformatics, 40(6), btae201.
37. Sun, Z., Liu, H., & Xu, H. (2024). Clinical note summarization with large language models. Journal of Biomedical Informatics, 149, 104570.
38. Yang, J., Li, X., & Chen, Y. (2024). Explainable large language models for clinical NLP. Artificial Intelligence in Medicine, 153, 102881.
39. Wei, Q., Ji, Z., Du, J., & Xu, H. (2024). Benchmarking clinical information extraction using foundation models. Journal of the American Medical Informatics Association, 31(6), 1218–1228.
40. Kim, D., Lee, H., & Park, J. (2024). Biomedical entity linking with large language models. Briefings in Bioinformatics, 25(3), bbae145.
41. Liu, Y., Zhang, Q., & Wang, H. (2024). Generative AI for adverse event extraction from clinical narratives. Drug Safety, 47(5), 611–623.
42. Choi, J., Palumbo, N., Chalasani, P., Engelhard, M., Jha, S., Kumar, A., & Page, D. (2024). MALADE: Orchestration of LLM-powered agents with retrieval augmented generation for pharmacovigilance. Proceedings of Machine Learning for Healthcare 2024.
43. Shen, Y., Heacock, L., Elias, J., Hentel, K. D., Reig, B., Shih, G., & Moy, L. (2024). ChatGPT and large language models in radiology. Radiology, 310(1), e232145.
44. Bhayana, R., Krishna, S., & Bleakney, R. (2024). Clinical applications of generative AI in medical imaging. Radiographics, 44(2), e230169.
45. Guo, Y., Li, H., & Zhang, W. (2024). Knowledge extraction from radiology reports using foundation models. European Radiology, 34(7), 5123–5134.
46. Tang, R., Wang, L., & Chen, J. (2024). LLM-assisted extraction of clinical phenotypes from EHR data. Journal of Biomedical Informatics, 151, 104602.
47. Singh, R., Patel, N., & Shah, P. (2024). Automated disease surveillance using large language models. International Journal of Medical Informatics, 186, 105445.
48. Wu, Y., Zhang, T., & Liu, X. (2024). Clinical concept normalization with large language models. BMC Bioinformatics, 25(1), 118.
49. Ahmed, S., Khan, M., & Ali, H. (2024). Generative AI for biomedical text mining: Opportunities and challenges. Briefings in Bioinformatics, 25(4), bbae233.
50. Rivera, M., Denecke, K., & May, R. (2024). Ethical and trustworthy clinical large language models. Journal of Medical Systems, 48(1), 61.
51. Zhao, L., Chen, M., & Wang, Q. (2024). Clinical knowledge graph construction using large language models. Knowledge-Based Systems, 292, 111621.
52. Patel, R., Gupta, V., & Kumar, A. (2024). Foundation models for biomedical information extraction. Frontiers in Artificial Intelligence, 7, 1398412.
53. Huang, Y., Xu, Z., & Li, J. (2024). Multimodal large language models in healthcare informatics. IEEE Access, 12, 78544–78560.
54. Feng, S., Wang, X., & Liu, J. (2024). Clinical reasoning and knowledge extraction with generative AI. Artificial Intelligence Review, 57(12), 368.
55. Roberts, K., Wang, Y., & Xu, H. (2024). Advances in biomedical natural language processing with large language models. Annual Review of Biomedical Data Science, 7, 231–255.
56. Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2024). BioBERT and next-generation biomedical language models: Recent advances. Briefings in Bioinformatics, 25(2), bbae097.
57. Wang, P., Chen, H., & Zhao, X. (2024). Clinical text mining with retrieval-augmented generation architectures. Information Sciences, 670, 120702.
58. Garcia, G. L., Manesco, J. R. R., Paiola, P. H., Miranda, L., de Salvo, M. P., & Papa, J. P. (2024). A review on scientific knowledge extraction using large language models in biomedical sciences. arXiv Preprint arXiv:2412.03531.
59. Zhang, L., Xu, H., Wei, Q., & Du, J. (2024). Large language models for clinical knowledge extraction and healthcare analytics. Journal of Biomedical Informatics, 152, 104640.
