{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T02:39:14Z","timestamp":1792895954352,"version":"4.5.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":68,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["75N920202D00021"],"award-info":[{"award-number":["75N920202D00021"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["75N920202D00021"],"award-info":[{"award-number":["75N920202D00021"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000070","name":"National Institute of Biomedical Imaging and Bioengineering","doi-asserted-by":"publisher","award":["75N920202D00021"],"award-info":[{"award-number":["75N920202D00021"]}],"id":[{"id":"10.13039\/100000070","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF CAREER Award","award":["2145640"],"award-info":[{"award-number":["2145640"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02685-4","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T15:06:28Z","timestamp":1777561588000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reinforcement learning improves LLM accuracy and reasoning in disease classification from radiology reports"],"prefix":"10.1038","volume":"9","author":[{"given":"Yishu","family":"Wei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Flanders","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Shih","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,30]]},"reference":[{"key":"2685_CR1","unstructured":"Jain, S. et al. RadGraph: Extracting clinical entities and relations from radiology reports. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1), pp. 1\u201312 (2021)"},{"key":"2685_CR2","unstructured":"Chambon, P. et al. CheXpert plus: Augmenting a large chest X-ray dataset with text radiology reports, patient demographics and additional image formats. arXiv [cs.CL] (2024) arXiv:2405.19538 [cs.CL]"},{"key":"2685_CR3","doi-asserted-by":"publisher","first-page":"1821","DOI":"10.1093\/jamia\/ocae122","volume":"31","author":"H Tran","year":"2024","unstructured":"Tran, H., Yang, Z., Yao, Z. & Yu, H. BioInstruct: instruction tuning of large language models for biomedical natural language processing. J. Am. Med. Inform. Assoc. 31, 1821\u20131832, https:\/\/doi.org\/10.1093\/jamia\/ocae122 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2685_CR4","doi-asserted-by":"crossref","unstructured":"Garg, M., Raza, S., Rayana, S., Liu, X., Sohn, S. The rise of small language models in healthcare: A comprehensive survey. arXiv [cs.CL] (2025) arXiv:2504.17119 [cs.CL].","DOI":"10.1016\/j.cosrev.2026.100999"},{"key":"2685_CR5","first-page":"0000680","volume":"3","author":"O Ben Shoham","year":"2024","unstructured":"Ben Shoham, O. & Rappoport, N. CPLLM: Clinical prediction with large language models. PLOS Digit. Health 3, 0000680 (2024).","journal-title":"Health"},{"key":"2685_CR6","first-page":"120","volume":"29","author":"Y Jiang","year":"2024","unstructured":"Jiang, Y., Irvin, J. A., Ng, A. Y. & Zou, J. VetLLM: Large language model for predicting diagnosis from veterinary notes. Pac. Symp. Biocomput. 29, 120\u2013133 (2024).","journal-title":"Pac. Symp. Biocomput."},{"key":"2685_CR7","unstructured":"Wei, Y. et al. Enhancing disease detection in radiology reports through fine-tuning lightweight LLM on weak labels. arXiv [cs.AI] (2024) arXiv:2409.16563 [cs.AI]."},{"key":"2685_CR8","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","volume":"645","author":"D Guo","year":"2025","unstructured":"Guo, D. et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645, 633\u2013638, https:\/\/doi.org\/10.1038\/s41586-025-09422-z (2025).","journal-title":"Nature"},{"key":"2685_CR9","doi-asserted-by":"crossref","unstructured":"Setlur, A. R. et al. RL on incorrect synthetic data scales the e\u201dciency of LLM math reasoning by eight-fold. Neural. Inf. Process Syst. abs\/2406.14532, 43000\u201343031 (2024).","DOI":"10.52202\/079017-1361"},{"key":"2685_CR10","unstructured":"Havrilla, A. et al. Teaching large language models to reason with reinforcement learning. arXiv [cs.LG] (2024) arXiv:2403.04642 [cs.LG]"},{"key":"2685_CR11","doi-asserted-by":"publisher","unstructured":"Wang, X. et al: ChestX-Ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3462\u20133471 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.369.","DOI":"10.1109\/CVPR.2017.369"},{"key":"2685_CR12","doi-asserted-by":"publisher","first-page":"233270","DOI":"10.1148\/radiol.233270","volume":"311","author":"Y Zhou","year":"2024","unstructured":"Zhou, Y. et al. Evaluating GPT-V4 (GPT-4 with vision) on detection of radiologic findings on chest radiographs. Radiology 311, 233270 (2024).","journal-title":"Radiology"},{"key":"2685_CR13","unstructured":"Grattafiori, A. et al. The llama 3 herd of models. arXiv [cs.AI] (2024) arXiv:2407.21783 [cs.AI]."},{"key":"2685_CR14","unstructured":"Qwen Yang A, et al Qwen2.5 technical report. arXiv [cs.CL] (2024) arXiv:2412.15115 [cs.CL]."},{"key":"2685_CR15","unstructured":"Abdin, M. et al. Phi-3 technical report: A highly capable language model locally on your phone. arXiv [cs.CL] (2024) arXiv:2404.14219 [cs.CL]."},{"key":"2685_CR16","unstructured":"Han, T. et al. Medalpaca\u2013an open-source collection of medical conversational ai models and training data. arXiv preprint arXiv:2304.08247 (2023)"},{"key":"2685_CR17","doi-asserted-by":"crossref","unstructured":"Alsentzer, E. et al: Publicly available clinical bert embeddings. In: Proceedings of the 2nd Clinical Natural Language Processing Workshop, pp. 72\u201378 (2019).","DOI":"10.18653\/v1\/W19-1909"},{"key":"2685_CR18","unstructured":"Team, G. et al. Gemini: A family of highly capable multimodal models, 2024. arXiv preprint arXiv:2312.11805 10 (2024)."},{"key":"2685_CR19","doi-asserted-by":"crossref","unstructured":"Fan, Z. et al. ChestX-reasoner: Advancing radiology foundation models with reasoning through step-by-step verification. arXiv [cs.AI] (2025) arXiv:2504.20930 [cs.AI].","DOI":"10.1038\/s43856-026-01654-y"},{"key":"2685_CR20","unstructured":"Gu, J. et al. A survey on LLM-as-a-judge. arXiv [cs.CL] (2024) arXiv:2411.15594 [cs.CL]."},{"key":"2685_CR21","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J. et al. Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. USA. 114, 3521\u20133526 (2017).","journal-title":"Proc. Natl. Acad. Sci. USA."},{"key":"2685_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-34938-7","volume":"13","author":"T Tadros","year":"2022","unstructured":"Tadros, T., Krishnan, G. P., Ramyaa, R. & Bazhenov, M. Sleep-like unsupervised replay reduces catastrophic forgetting in artificial neural networks. Nat. Commun. 13, 7742. https:\/\/doi.org\/10.1038\/s41467-022-34938-7 (2022).","journal-title":"Nat. Commun."},{"key":"2685_CR23","unstructured":"Johnson, A. E. W. et al: MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs. arXiv [cs.CV] (2019) arXiv:1901.07042 [cs.CV]"},{"key":"2685_CR24","doi-asserted-by":"publisher","first-page":"3197","DOI":"10.1007\/s11845-023-03377-8","volume":"192","author":"E Waisberg","year":"2023","unstructured":"Waisberg, E. et al. GPT-4: a new era of artificial intelligence in medicine. Ir. J.Med. Sci 192, 3197\u20133200, https:\/\/doi.org\/10.1007\/s11845-023-03377-8 (2023).","journal-title":"Ir. J.Med. Sci"},{"key":"2685_CR25","unstructured":"Hu, J. E. et al. LoRA: Low-rank adaptation of large language models. Int Conf Learn Represent abs\/2106.09685 (2021) 2106.09685"},{"key":"2685_CR26","unstructured":"Werra, L. et al. TRL: Transformer Reinforcement Learning. GitHub (2020)"},{"key":"2685_CR27","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D. Y., Ermon, S., Rudra, A., R\u2019e, C. FlashAttention: Fast and memory-e\u201dcient exact attention with IO-awareness. Neural Inf Process Syst abs\/2205.14135, 16344\u201316359 (2022)","DOI":"10.52202\/068431-1189"}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02685-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02685-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02685-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T23:33:49Z","timestamp":1783380829000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02685-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,30]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2685"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02685-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,30]]},"assertion":[{"value":"25 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 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":"515"}}