{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:46:47Z","timestamp":1790876807299,"version":"4.1.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T00:00:00Z","timestamp":1784678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2024-00335644"],"award-info":[{"award-number":["RS-2024-00335644"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005006","name":"Asan Institute for Life Sciences, Asan Medical Center","doi-asserted-by":"publisher","award":["2025IP0016"],"award-info":[{"award-number":["2025IP0016"]}],"id":[{"id":"10.13039\/501100005006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02467-y","type":"journal-article","created":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:34:24Z","timestamp":1784698464000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Large language models for interpretation of health checkup results"],"prefix":"10.1038","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9036-8400","authenticated-orcid":false,"given":"Jiwon","family":"You","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3353-0310","authenticated-orcid":false,"given":"Hangsik","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,22]]},"reference":[{"key":"2467_CR1","doi-asserted-by":"publisher","first-page":"2294","DOI":"10.1001\/jama.2021.6524","volume":"325","author":"DT Liss","year":"2021","unstructured":"Liss, D. T., Uchida, T., Wilkes, C. L., Radakrishnan, A. & Linder, J. A. General health checks in adult primary care: a review. JAMA 325, 2294\u20132306 (2021).","journal-title":"JAMA"},{"key":"2467_CR2","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/informatics11030057","volume":"11","author":"ZA Nazi","year":"2024","unstructured":"Nazi, Z. A. & Peng, W. Large language models in healthcare and medical domain: A review. Informatics 11, 57 (2024).","journal-title":"Informatics"},{"key":"2467_CR3","doi-asserted-by":"publisher","first-page":"210","DOI":"10.7326\/M23-2772","volume":"177","author":"JA Omiye","year":"2024","unstructured":"Omiye, J. A., Gui, H., Rezaei, S. J., Zou, J. & Daneshjou, R. Large language models in medicine: the potentials and pitfalls: a narrative review. Ann. Intern. Med. 177, 210\u2013220 (2024).","journal-title":"Ann. Intern. Med."},{"key":"2467_CR4","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1001\/jama.2023.14217","volume":"330","author":"NH Shah","year":"2023","unstructured":"Shah, N. H., Entwistle, D. & Pfeffer, M. A. Creation and adoption of large language models in medicine. JAMA 330, 866\u2013869 (2023).","journal-title":"JAMA"},{"key":"2467_CR5","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A. J. et al. Large language models in medicine. Nat. Med. 29, 1930\u20131940 (2023).","journal-title":"Nat. Med."},{"key":"2467_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson, A. E. et al. MIMIC-III, a freely accessible critical care database. Sci. Data 3, 1\u20139 (2016).","journal-title":"Sci. Data"},{"key":"2467_CR7","unstructured":"Wang, L. L., Lo, K., Chandrasekhar, Y., Reas, R., Yang, J., Burdick, D., et al. CORD-19: The COVID-19 Open Research Dataset. Proceeding 1st Workshop on NLP for COVID-19 at ACL (2020)."},{"key":"2467_CR8","doi-asserted-by":"publisher","first-page":"e0000198","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"TH Kung","year":"2023","unstructured":"Kung, T. H. et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLoS Digit. Health 2, e0000198 (2023).","journal-title":"PLoS Digit. Health"},{"key":"2467_CR9","doi-asserted-by":"publisher","unstructured":"Nori, H., King, N., McKinney, S. M., Carignan, D. & Horvitz, E. Capabilities of GPT-4 on medical challenge problems. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2303.13375 (2023).","DOI":"10.48550\/arXiv.2303.13375"},{"key":"2467_CR10","doi-asserted-by":"crossref","unstructured":"Singhal, K. et al. Toward expert-level medical question answering with large language models. Nat. Med. 31, 943\u2013950 (2025).","DOI":"10.1038\/s41591-024-03423-7"},{"key":"2467_CR11","doi-asserted-by":"publisher","first-page":"e0000341","DOI":"10.1371\/journal.pdig.0000341","volume":"3","author":"AJ Thirunavukarasu","year":"2024","unstructured":"Thirunavukarasu, A. J. et al. Large language models approach expert-level clinical knowledge and reasoning in ophthalmology: a head-to-head cross-sectional study. PLOS Digit. Health 3, e0000341 (2024).","journal-title":"PLOS Digit. Health"},{"key":"2467_CR12","doi-asserted-by":"crossref","unstructured":"Zhang, J. et al. The potential and pitfalls of using a large language model such as ChatGPT, GPT-4, or LLaMA as a clinical assistant. J. Am. Med. Inform. Assoc. 31, 1884\u20131891 (2024).","DOI":"10.1093\/jamia\/ocae184"},{"key":"2467_CR13","doi-asserted-by":"publisher","unstructured":"Safavi-Naini, S. A. A. et al. Vision-language and large language model performance in gastroenterology: GPT, Claude, Llama, Phi, Mistral, Gemma, and quantized models. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2409.00084 (2024).","DOI":"10.48550\/arXiv.2409.00084"},{"key":"2467_CR14","unstructured":"National Health Insurance Service. General health check-up target population and examinee status. https:\/\/kosis.kr\/statHtml\/statHtml.do?sso=ok&returnurl=https%3A%2F%2Fwww.kosis.kr%3A443%2FstatHtml%2FstatHtml.do%3Flist_id%3D350_35007_A001%26obj_var_id%3D%26seqNo%3D%26tblId%3DDT_35007_N144_1%26vw_cd%3DMT_OTITLE%26orgId%3D350%26path%3D%252FstatisticsList%252FstatisticsListIndex.do%26conn_path%3DMT_OTITLE%26itm_id%3D%26lang_mode%3Dko%26scrId%3D%26 (2022)."},{"key":"2467_CR15","doi-asserted-by":"publisher","first-page":"e18725","DOI":"10.2196\/18725","volume":"22","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z. et al. Patient challenges and needs in comprehending laboratory test results: mixed methods study. J. Med. Internet Res. 22, e18725 (2020).","journal-title":"J. Med. Internet Res."},{"key":"2467_CR16","doi-asserted-by":"publisher","unstructured":"Achiam, J. et al. GPT-4 technical report. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2303.08774 (2023).","DOI":"10.48550\/arXiv.2303.08774"},{"key":"2467_CR17","unstructured":"AI Anthropic. System Card: Claude Opus 4 & Claude Sonnet 4. Claude-4 Model Card (2025)."},{"key":"2467_CR18","doi-asserted-by":"publisher","unstructured":"Comanici, G. et al. Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2507.06261 (2025).","DOI":"10.48550\/arXiv.2507.06261"},{"key":"2467_CR19","doi-asserted-by":"publisher","unstructured":"Hurst, A. et al. GPT-4o System Card. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2410.21276 (2024).","DOI":"10.48550\/arXiv.2410.21276"},{"key":"2467_CR20","doi-asserted-by":"publisher","unstructured":"Touvron, H. et al. LLaMA: open and efficient foundation language models. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2302.13971 (2023).","DOI":"10.48550\/arXiv.2302.13971"},{"key":"2467_CR21","doi-asserted-by":"publisher","unstructured":"Wang, S. et al. Reinforcement learning enhanced LLMs: a survey. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2412.10400 (2024).","DOI":"10.48550\/arXiv.2412.10400"},{"key":"2467_CR22","doi-asserted-by":"crossref","unstructured":"Huang, C., Li, Y., Loy, C. C. & Tang, X. Learning deep representation for imbalanced classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5375\u20135384 (2016).","DOI":"10.1109\/CVPR.2016.580"},{"key":"2467_CR23","doi-asserted-by":"publisher","unstructured":"Alhoshan, W., Ferrari, A. & Zhao, L. How effective are generative large language models in performing requirements classification? Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2504.16768 (2025).","DOI":"10.48550\/arXiv.2504.16768"},{"key":"2467_CR24","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1093\/oxfordjournals.aje.a008733","volume":"143","author":"D Gallagher","year":"1996","unstructured":"Gallagher, D. et al. How useful is body mass index for comparison of body fatness across age, sex, and ethnic groups? Am. J. Epidemiol. 143, 228\u2013239 (1996).","journal-title":"Am. J. Epidemiol."},{"key":"2467_CR25","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1161\/HYPERTENSIONAHA.114.03617","volume":"65","author":"Z Sun","year":"2015","unstructured":"Sun, Z. Aging, arterial stiffness, and hypertension. Hypertension 65, 252\u2013256 (2015).","journal-title":"Hypertension"},{"key":"2467_CR26","first-page":"384","volume":"39","author":"D Wang","year":"2020","unstructured":"Wang, D. et al. Gender and age-specific reference intervals of common biochemical analytes in Chinese population: derivation using real laboratory data. J. Med. Biochem. 39, 384 (2020).","journal-title":"J. Med. Biochem."},{"key":"2467_CR27","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.cca.2016.09.015","volume":"467","author":"K Ichihara","year":"2017","unstructured":"Ichihara, K. et al. A global multicenter study on reference values: 2. Exploration of sources of variation across the countries. Clin. Chim. Acta 467, 83\u201397 (2017).","journal-title":"Clin. Chim. Acta"},{"key":"2467_CR28","doi-asserted-by":"publisher","unstructured":"Tanwar, E., Nathani, D., Wang, W. Y. & Chakraborty, T. Understanding the effects of domain finetuning on LLMs. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2510.09359 (2025).","DOI":"10.48550\/arXiv.2510.09359"},{"key":"2467_CR29","doi-asserted-by":"publisher","first-page":"e56655","DOI":"10.2196\/56655","volume":"26","author":"Z He","year":"2024","unstructured":"He, Z. et al. Quality of answers of generative large language models versus peer users for interpreting laboratory test results for lay patients: evaluation study. J. Med. Internet Res. 26, e56655 (2024).","journal-title":"J. Med. Internet Res."},{"key":"2467_CR30","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02838-z","volume":"25","author":"X Yang","year":"2025","unstructured":"Yang, X. et al. Enhancing doctor-patient communication using large language models for pathology report interpretation. BMC Med. Inform. Decis. Mak. 25, 36 (2025).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2467_CR31","unstructured":"National Health Insurance Service. Health checkup information. https:\/\/www.data.go.kr\/data\/15007122\/fileData.do# (2024)."},{"key":"2467_CR32","doi-asserted-by":"publisher","first-page":"103","DOI":"10.12997\/jla.2022.11.2.103","volume":"11","author":"D-S Kyoung","year":"2021","unstructured":"Kyoung, D.-S. & Kim, H.-S. Understanding and utilizing claim data from the Korean National Health Insurance Service (NHIS) and Health Insurance Review & Assessment (HIRA) database for research. J. Lipid Atheroscler. 11, 103 (2021).","journal-title":"J. Lipid Atheroscler."},{"key":"2467_CR33","first-page":"e15","volume":"46","author":"J Lee","year":"2017","unstructured":"Lee, J., Lee, J. S., Park, S.-H., Shin, S. A. & Kim, K. Cohort profile: the national health insurance service\u2013national sample cohort (NHIS-NSC), South Korea. Int. J. Epidemiol. 46, e15\u2013 (2017).","journal-title":"Int. J. Epidemiol."},{"key":"2467_CR34","unstructured":"Korea Disease Control and Prevention Agency. Reference values of checkup items. https:\/\/health.kdca.go.kr\/healthinfo\/biz\/health\/gnrlzHealthInfo\/gnrlzHealthInfo\/gnrlzHealthInfoMain.do?lclasSn=7 (2024)."},{"key":"2467_CR35","unstructured":"Mayo Clinical Laboratories. Critical values and results. https:\/\/www.mayocliniclabs.com\/test-catalog\/critical-values-and-results (2024)."},{"key":"2467_CR36","doi-asserted-by":"publisher","unstructured":"Hendrycks, D. et al. Measuring massive multitask language understanding. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2009.03300 (2020).","DOI":"10.48550\/arXiv.2009.03300"},{"key":"2467_CR37","unstructured":"AI Anthropic. Claude 3.5 Sonnet model card addendum. Claude-3.5 Model Card 3.6 (2024)."},{"key":"2467_CR38","doi-asserted-by":"publisher","unstructured":"Georgiev, P. et al. Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2403.05530 (2024).","DOI":"10.48550\/arXiv.2403.05530"},{"key":"2467_CR39","doi-asserted-by":"publisher","unstructured":"Grattafiori, A. et al. The Llama 3 herd of models. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2407.21783 (2024).","DOI":"10.48550\/arXiv.2407.21783"},{"key":"2467_CR40","doi-asserted-by":"publisher","unstructured":"Vatsal, S. & Dubey, H. A survey of prompt engineering methods in large language models for different NLP tasks. Preprint at arXiv https:\/\/doi.org\/10.48550\/arXiv.2407.12994 (2024).","DOI":"10.48550\/arXiv.2407.12994"},{"key":"2467_CR41","doi-asserted-by":"crossref","unstructured":"Li, Y. A practical survey on zero-shot prompt design for in-context learning. In Proceedings of the 14th International Conference on Recent Advances in Natural Language Processing, 641\u2013647 (2023).","DOI":"10.26615\/978-954-452-092-2_069"},{"key":"2467_CR42","doi-asserted-by":"crossref","unstructured":"Kong, A., Zhao, S., Chen, H., Li, Q., Qin, Y., Sun, R., et al. Better zero-shot reasoning with role-play prompting. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 4099\u20134113 (2024).","DOI":"10.18653\/v1\/2024.naacl-long.228"},{"key":"2467_CR43","doi-asserted-by":"crossref","unstructured":"Logan IV, R., Bala\u017eevi\u0107, I., Wallace, E., Petroni, F., Singh, S. & Riedel, S. Cutting down on prompts and parameters: Simple few-shot learning with language models. In Findings Assoc. Comput. Linguist.: ACL 2022, 2824\u20132835 (2022).","DOI":"10.18653\/v1\/2022.findings-acl.222"},{"key":"2467_CR44","doi-asserted-by":"crossref","unstructured":"Lu, Y., Bartolo, M., Moore, A., Riedel, S. & Stenetorp, P. Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 8086\u20138098 (2022).","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"2467_CR45","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.1145\/3591300","volume":"7","author":"L Beurer-Kellner","year":"2023","unstructured":"Beurer-Kellner, L., Fischer, M. & Vechev, M. Prompting is programming: a query language for large language models. Proc. ACM Program. Lang. 7, 1946\u20131969 (2023).","journal-title":"Proc. ACM Program. Lang."},{"key":"2467_CR46","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.8.4.e25","volume":"8","author":"M Kastner","year":"2006","unstructured":"Kastner, M., Wilczynski, N. L., Walker-Dilks, C., McKibbon, K. A. & Haynes, B. Age-specific search strategies for Medline. J. Med. Internet Res. 8, e501 (2006).","journal-title":"J. Med. Internet Res."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02467-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02467-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02467-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T05:34:28Z","timestamp":1784698468000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02467-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,22]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2467"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02467-y","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,22]]},"assertion":[{"value":"19 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 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","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"565"}}