{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T03:13:00Z","timestamp":1778814780862,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:00:00Z","timestamp":1771545600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02441-8","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T09:37:56Z","timestamp":1771580276000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["CancerLLM: a large language model in cancer domain"],"prefix":"10.1038","volume":"9","author":[{"given":"Mingchen","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaifu","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jeremy","family":"Yeung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne","family":"Blaes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steven","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongfang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,20]]},"reference":[{"key":"2441_CR1","unstructured":"Achiam, J. et al Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"2441_CR2","unstructured":"Touvron, H. et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"2441_CR3","doi-asserted-by":"crossref","unstructured":"Li, M., Zhou, H., Yang, H. & Zhang, R. RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognition. J. Am. Med. Inform. Assoc. 31, 1929\u20131938 (2024).","DOI":"10.1093\/jamia\/ocae095"},{"key":"2441_CR4","doi-asserted-by":"publisher","first-page":"104769","DOI":"10.1016\/j.jbi.2024.104769","volume":"162","author":"M Li","year":"2025","unstructured":"Li, M., Kilicoglu, H., Xu, H. & Zhang, R. Biomedrag: A retrieval augmented large language model for biomedicine. J. Biomed. Inform 162, 104769 (2025).","journal-title":"J. Biomed. Inform"},{"key":"2441_CR5","doi-asserted-by":"publisher","first-page":"eadr1443","DOI":"10.1126\/sciadv.adr1443","volume":"11","author":"M Li","year":"2025","unstructured":"Li, M. et al. Benchmarking retrieval-augmented large language models in biomedical NLP: Application, robustness, and self-awareness. Sci. Adv. 11, eadr1443 (2025).","journal-title":"Sci. Adv."},{"key":"2441_CR6","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Yang, Y. & Chen, B. Prompt tuning for few-shot relation extraction via modeling global and local graphs. In Proc. 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), (eds. Calzolari, N. et al.) 13233\u201313242. https:\/\/aclanthology.org\/2024.lrec-main.1158. (ELRA and ICCL, 2024).","DOI":"10.63317\/3ehsmnvdxvv3"},{"key":"2441_CR7","doi-asserted-by":"crossref","unstructured":"Li, M., Ling, C., Zhang, R. & Zhao, L. Zero-shot link prediction in knowledge graphs with large language models. In 2024 IEEE International Conference on Data Mining (ICDM) (pp. 753\u2013760) (IEEE, 2024).","DOI":"10.1109\/ICDM59182.2024.00088"},{"key":"2441_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3580514","volume":"18","author":"M Liu","year":"2024","unstructured":"Liu, M. et al. Behaviornet: a fine-grained behavior-aware network for dynamic link prediction. ACM Trans. Web 18, 1\u201326 (2024).","journal-title":"ACM Trans. Web"},{"key":"2441_CR9","doi-asserted-by":"crossref","unstructured":"Li, M. et al. A hierarchical n-gram framework for zero-shot link prediction. In Findings of the Association for Computational Linguistics. (pp. 2498\u20132509) (EMNLP, 2022).","DOI":"10.18653\/v1\/2022.findings-emnlp.184"},{"key":"2441_CR10","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Yu, Y., Wang, K., Sun, H. & Zhang, C. Toolqa: a dataset for LLM question answering with external tools. Adv. Neural Inform. Process. Syst. 36, 50117\u201350143 (2024).","DOI":"10.52202\/075280-2180"},{"key":"2441_CR11","doi-asserted-by":"crossref","unstructured":"Jiang, F. et al. Enhancing question answering for enterprise knowledge bases using large language models. In Proc. Database Systems for Advanced Applications: 29th International Conference, DASFAA 2024, Gifu, Japan Part IV (pp. 273\u2013290) (Springer, 2024).","DOI":"10.1007\/978-981-97-5562-2_18"},{"key":"2441_CR12","unstructured":"Huang, J. et al. Ritek: A dataset for large language models complex reasoning over textual knowledge graphs. arXiv e-prints, arXiv-2410 (2024)."},{"key":"2441_CR13","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"2441_CR14","unstructured":"Toma, A. et al. Clinical camel: An open expert-level medical language model with dialogue-based knowledge encoding. arXiv preprint arXiv:2305.12031 (2023)."},{"key":"2441_CR15","unstructured":"Ankit Pal, M.S. Openbiollms: advancing open-source large language models for healthcare and life sciences. https:\/\/huggingface.co\/aaditya\/OpenBioLLM-Llama3-70B (2024)."},{"key":"2441_CR16","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1002\/hcs2.61","volume":"2","author":"R Yang","year":"2023","unstructured":"Yang, R. et al. Large language models in health care: development, applications, and challenges. Health Care Sci. 2, 255\u2013263 (2023).","journal-title":"Health Care Sci."},{"key":"2441_CR17","doi-asserted-by":"publisher","DOI":"10.1186\/s13000-024-01464-7","volume":"19","author":"E Ullah","year":"2024","unstructured":"Ullah, E., Parwani, A., Baig, M. M. & Singh, R. Challenges and barriers of using large language models (LLM) such as chatgpt for diagnostic medicine with a focus on digital pathology\u2013a recent scoping review. Diagn. Pathol. 19, 43 (2024).","journal-title":"Diagn. Pathol."},{"key":"2441_CR18","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s44387-025-00011-z","volume":"1","author":"S Zhou","year":"2025","unstructured":"Zhou, S. et al. Large language models for disease diagnosis: A scoping review. npj Artificial Intelligence 1, 9 (2025).","journal-title":"npj Artificial Intelligence"},{"key":"2441_CR19","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1038\/s41568-024-00694-7","volume":"24","author":"R Perez-Lopez","year":"2024","unstructured":"Perez-Lopez, R., Ghaffari Laleh, N., Mahmood, F. & Kather, J. N. A guide to artificial intelligence for cancer researchers. Nat. Rev. Cancer 24, 427\u2013441 (2024).","journal-title":"Nat. Rev. Cancer"},{"key":"2441_CR20","doi-asserted-by":"publisher","first-page":"2983","DOI":"10.1038\/s41591-023-02594-z","volume":"29","author":"D Truhn","year":"2023","unstructured":"Truhn, D., Reis-Filho, J. S. & Kather, J. N. Large language models should be used as scientific reasoning engines, not knowledge databases. Nat. Med. 29, 2983\u20132984 (2023).","journal-title":"Nat. Med."},{"key":"2441_CR21","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1146\/annurev-biodatasci-103123-095633","volume":"8","author":"KK Tsang","year":"2025","unstructured":"Tsang, K. K. et al. Foundation models for translational cancer biology. Annu. Rev. Biomed. Data Sci. 8, 51\u201380 (2025).","journal-title":"Annu. Rev. Biomed. Data Sci."},{"key":"2441_CR22","doi-asserted-by":"publisher","first-page":"e59505","DOI":"10.2196\/59505","volume":"26","author":"R AlSaad","year":"2024","unstructured":"AlSaad, R. et al. Multimodal large language models in health care: applications, challenges, and future outlook. J. Med. Internet Res. 26, e59505 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2441_CR23","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1093\/jamia\/ocac040","volume":"29","author":"S Zhou","year":"2022","unstructured":"Zhou, S., Wang, N., Wang, L., Liu, H. & Zhang, R. Cancerbert: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records. J. Am. Med. Inform. Assoc. 29, 1208\u20131216 (2022).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2441_CR24","first-page":"38","volume":"119","author":"ANH Zaied","year":"2015","unstructured":"Zaied, A. N. H., Elmogy, M. & Abd Elkader, S. Electronic health records: applications, techniques and challenges. Int. J. Comput. Appl. 119, 38\u201349 (2015).","journal-title":"Int. J. Comput. Appl."},{"key":"2441_CR25","doi-asserted-by":"publisher","first-page":"106073","DOI":"10.1016\/j.compbiomed.2022.106073","volume":"149","author":"RA Dar","year":"2022","unstructured":"Dar, R. A., Rasool, M. & Assad, A. Breast cancer detection using deep learning: datasets, methods, and challenges ahead. Comput. Biol. Med. 149, 106073 (2022).","journal-title":"Comput. Biol. Med."},{"key":"2441_CR26","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.3390\/cancers16061100","volume":"16","author":"EV Varlamova","year":"2024","unstructured":"Varlamova, E. V. et al. Machine learning meets cancer. Cancers 16, 1100 (2024).","journal-title":"Cancers"},{"key":"2441_CR27","doi-asserted-by":"publisher","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","volume":"30","author":"E Vorontsov","year":"2024","unstructured":"Vorontsov, E. et al. A foundation model for clinical-grade computational pathology and rare cancers detection. Nat. Med. 30, 2924\u20132935 (2024).","journal-title":"Nat. Med."},{"key":"2441_CR28","doi-asserted-by":"publisher","first-page":"1833","DOI":"10.1093\/jamia\/ocae045","volume":"31","author":"C Wu","year":"2024","unstructured":"Wu, C. et al. PMC-LLaMA: Toward building open-source language models for medicine. J. Am. Med. Inform Assoc. 31, 1833\u20131843 (2024).","journal-title":"J. Am. Med. Inform Assoc."},{"key":"2441_CR29","unstructured":"Han, T. et al. MedAlpaca--an open-source collection of medical conversational AI models and training data. arXiv preprint arXiv:2304.08247 (2023)."},{"key":"2441_CR30","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K. & Liang, P. Squad: 100,000+ questions for machine comprehension of text. In Proc. 2016 conference on empirical methods in natural language processing (pp. 2383-2392) (2016).","DOI":"10.18653\/v1\/D16-1264"},{"key":"2441_CR31","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T. & Zhu, W.-J. Bleu: a method for automatic evaluation of machine translation. In Proc. 40th annual meeting of the Association for Computational Linguistics, 311\u2013318 (ACM, 2002).","DOI":"10.3115\/1073083.1073135"},{"key":"2441_CR32","unstructured":"Cohan, A. & Goharian, N. Revisiting summarization evaluation for scientific articles. In Proc. Tenth International Conference on Language Resources and Evaluation (LREC'16) (pp. 806-813) (2016)."},{"key":"2441_CR33","unstructured":"Canese, K. & Weis, S. Pubmed: the bibliographic database. NCBI Handbook 2, 2013 (2013)."},{"key":"2441_CR34","unstructured":"Jiang, A. Q. et al. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"2441_CR35","unstructured":"Hu, E. J. et al. Lora: Low-rank adaptation of large language models. Iclr 1, 3 (2022)."},{"key":"2441_CR36","doi-asserted-by":"crossref","unstructured":"Wang, S. et al. Gpt-ner: Named entity recognition via large language models. In Findings of the association for computational linguistics: NAACL 2025 (pp. 4257\u20134275) (2025).","DOI":"10.18653\/v1\/2025.findings-naacl.239"},{"key":"2441_CR37","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. In International Conference on Learning Representations (ICLR 2019)."},{"key":"2441_CR38","unstructured":"Bai, J. et al. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"2441_CR39","doi-asserted-by":"crossref","unstructured":"Labrak, Y. et al. Biomistral: A collection of open-source pretrained large language models for medical domains. In Findings of the association for computational linguistics: acl 2024 (pp. 5848-5864) (2024).","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"2441_CR40","unstructured":"Grattafiori, A. et al. The Llama 3 herd of models. In Neural Information Processing Systems. Curran Associates (2024)."},{"key":"2441_CR41","unstructured":"Guo, D. et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"2441_CR42","doi-asserted-by":"crossref","unstructured":"Li, M. & Huang, L. Understand the dynamic world: An end-to-end knowledge informed framework for open domain entity state tracking. In Proc. 46th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 842\u2013851) (2023).","DOI":"10.1145\/3539618.3591781"},{"key":"2441_CR43","doi-asserted-by":"publisher","first-page":"btad651","DOI":"10.1093\/bioinformatics\/btad651","volume":"39","author":"Q Jin","year":"2023","unstructured":"Jin, Q. et al. Medcpt: contrastive pre-trained transformers with large-scale pubmed search logs for zero-shot biomedical information retrieval. Bioinformatics 39, btad651 (2023).","journal-title":"Bioinformatics"},{"key":"2441_CR44","doi-asserted-by":"crossref","unstructured":"Lei, Y. et al. Unsupervised dense retrieval with relevance-aware contrastive pre-training. In Findings of the Association for Computational Linguistics: ACL 2023 (pp. 10932\u201310940). (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.findings-acl.695"},{"key":"2441_CR45","unstructured":"Muennighoff, N. Sgpt: Gpt sentence embeddings for semantic search. arXiv preprint arXiv:2202.08904 (2022)."},{"key":"2441_CR46","doi-asserted-by":"crossref","unstructured":"Singh, A., D\u2019Arcy, M., Cohan, A., Downey, D. & Feldman, S. Scirepeval: A multi-format benchmark for scientific document representations. In Proc. 2023 Conference on Empirical Methods in Natural Language Processing (pp. 5548\u22125566) (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.338"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02441-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02441-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02441-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:48:10Z","timestamp":1774874890000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02441-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,20]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2441"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02441-8","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,20]]},"assertion":[{"value":"1 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"266"}}