{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:40:11Z","timestamp":1784821211411,"version":"3.55.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T00:00:00Z","timestamp":1782691200000},"content-version":"vor","delay-in-days":67,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/100000133","name":"Agency for Healthcare Research and Quality","doi-asserted-by":"publisher","award":["R21HS029969"],"award-info":[{"award-number":["R21HS029969"]}],"id":[{"id":"10.13039\/100000133","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","award":["UM1TR005128"],"award-info":[{"award-number":["UM1TR005128"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["P30AG073105"],"award-info":[{"award-number":["P30AG073105"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-026-02632-3","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T02:46:26Z","timestamp":1776912386000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of causal reasoning for large language models in contextualized clinical scenarios of laboratory test interpretation"],"prefix":"10.1038","volume":"9","author":[{"given":"Balu","family":"Bhasuran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mattia","family":"Prosperi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karim","family":"Hanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Petrilli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caretia JeLayne","family":"Washington","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"2632_CR1","doi-asserted-by":"publisher","unstructured":"OpenAI. GPT-4 Technical Report. https:\/\/doi.org\/10.48550\/ARXIV.2303.08774 (2023).","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"2632_CR2","doi-asserted-by":"publisher","unstructured":"G, Team. et al. Gemini: a family of highly capable multimodal models. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2312.11805 (2023).","DOI":"10.48550\/ARXIV.2312.11805"},{"key":"2632_CR3","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal, K. et al. Toward expert-level medical question answering with large language models. Nat. Med 31, 943\u2013950 (2025).","journal-title":"Nat. Med"},{"key":"2632_CR4","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41746-025-01556-8","volume":"8","author":"B Bhasuran","year":"2025","unstructured":"Bhasuran, B. et al. Preliminary analysis of the impact of lab results on large language model generated differential diagnoses. NPJ Digit Med. 8, 166 (2025).","journal-title":"NPJ Digit Med."},{"key":"2632_CR5","doi-asserted-by":"publisher","unstructured":"Williams, C. Y. K. et al. Physician- and large language model\u2013generated hospital discharge summaries. JAMA Intern. Med. https:\/\/doi.org\/10.1001\/jamainternmed.2025.0821 (2025).","DOI":"10.1001\/jamainternmed.2025.0821"},{"key":"2632_CR6","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1093\/jamia\/ocae142","volume":"31","author":"S Liu","year":"2024","unstructured":"Liu, S. et al. Using large language model to guide patients to create efficient and comprehensive clinical care message. J. Am. Med. Inform. Assoc. 31, 1665\u20131670 (2024).","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2632_CR7","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":"2632_CR8","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","volume":"30","author":"D Van Veen","year":"2024","unstructured":"Van Veen, D. et al. Adapted large language models can outperform medical experts in clinical text summarization. Nat. Med. 30, 1134\u20131142 (2024).","journal-title":"Nat. Med."},{"key":"2632_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53081-z","volume":"15","author":"Q Jin","year":"2024","unstructured":"Jin, Q. et al. Matching patients to clinical trials with large language models. Nat. Commun. 15, 9074 (2024).","journal-title":"Nat. Commun."},{"key":"2632_CR10","doi-asserted-by":"publisher","unstructured":"OpenAI et al. OpenAI o1 System Card. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2412.16720 (2024).","DOI":"10.48550\/ARXIV.2412.16720"},{"key":"2632_CR11","unstructured":"Gemini: Our most intelligent AI models. https:\/\/deepmind.google\/models\/gemini\/pro\/."},{"key":"2632_CR12","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 (2025).","journal-title":"Nature"},{"key":"2632_CR13","unstructured":"Introducing Claude 4. https:\/\/www.anthropic.com\/news\/claude-4."},{"key":"2632_CR14","doi-asserted-by":"publisher","unstructured":"Brodeur, P. G. et al. Superhuman performance of a large language model on the reasoning tasks of a physician. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2412.10849 (2024).","DOI":"10.48550\/ARXIV.2412.10849"},{"key":"2632_CR15","doi-asserted-by":"publisher","unstructured":"Tordjman, M. et al. Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-025-03726-3 (2025).","DOI":"10.1038\/s41591-025-03726-3"},{"key":"2632_CR16","doi-asserted-by":"crossref","unstructured":"Petersen, M., Alaa, A., K\u0131c\u0131man, E., Holmes, C. & Van Der Laan, M. Artificial intelligence\u2013based copilots to generate causal evidence. NEJM AI 1, (2024).","DOI":"10.1056\/AIp2400727"},{"key":"2632_CR17","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1038\/s42256-020-0197-y","volume":"2","author":"M Prosperi","year":"2020","unstructured":"Prosperi, M. et al. Causal inference and counterfactual prediction in machine learning for actionable healthcare. Nat. Mach. Intell. 2, 369\u2013375 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"2632_CR18","doi-asserted-by":"publisher","first-page":"Article 7","DOI":"10.2202\/1557-4679.1203","volume":"6","author":"J Pearl","year":"2010","unstructured":"Pearl, J. An introduction to causal inference. Int J. Biostat. 6, Article 7 (2010).","journal-title":"Int J. Biostat."},{"key":"2632_CR19","doi-asserted-by":"crossref","unstructured":"Jin, Z. et al. CLADDER: assessing causal reasoning in language models. in Proceedings of the 37th International Conference on Neural Information Processing Systems (Curran Associates Inc., Red Hook, NY, USA, 2023).","DOI":"10.52202\/075280-1353"},{"key":"2632_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z. CausalBench: A Comprehensive Benchmark for Evaluating Causal Reasoning Capabilities of Large Language Models. in Proceedings of the 10th SIGHAN Workshop on Chinese Language Processing (SIGHAN-10) (eds. Wong, K. F. et al.) 143\u2013151 (Association for Computational Linguistics, Bangkok, Thailand, 2024).","DOI":"10.18653\/v1\/2024.sighan-1.17"},{"key":"2632_CR21","doi-asserted-by":"publisher","unstructured":"Chen, S. et al. Causal Evaluation of Language Models. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2405.00622 (2024).","DOI":"10.48550\/ARXIV.2405.00622"},{"key":"2632_CR22","doi-asserted-by":"publisher","unstructured":"Khatibi, E., Abbasian, M., Yang, Z., Azimi, I. & Rahmani, A. M. ALCM: Autonomous LLM-Augmented Causal Discovery Framework. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2405.01744 (2024).","DOI":"10.48550\/ARXIV.2405.01744"},{"key":"2632_CR23","doi-asserted-by":"publisher","unstructured":"Vashishtha, A. et al. Causal Order: The Key to Leveraging Imperfect Experts in Causal Inference. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2310.15117 (2023).","DOI":"10.48550\/ARXIV.2310.15117"},{"key":"2632_CR24","doi-asserted-by":"publisher","unstructured":"K\u0131c\u0131man, E., Ness, R., Sharma, A. & Tan, C. Causal reasoning and large language models: opening a new frontier for causality. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2305.00050 (2023).","DOI":"10.48550\/ARXIV.2305.00050"},{"key":"2632_CR25","doi-asserted-by":"publisher","DOI":"10.1017\/cts.2023.635","volume":"7","author":"LE Dang","year":"2023","unstructured":"Dang, L. E. et al. A causal roadmap for generating high-quality real-world evidence. J. Clin. Transl. Sci. 7, e212 (2023).","journal-title":"J. Clin. Transl. Sci."},{"key":"2632_CR26","doi-asserted-by":"publisher","unstructured":"Yang, A. et al. Qwen3 Technical Report. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2505.09388 (2025).","DOI":"10.48550\/ARXIV.2505.09388"},{"key":"2632_CR27","doi-asserted-by":"publisher","unstructured":"OpenAI et al. gpt-oss-120b & gpt-oss-20b Model Card. Preprint at https:\/\/doi.org\/10.48550\/ARXIV.2508.10925 (2025).","DOI":"10.48550\/ARXIV.2508.10925"},{"key":"2632_CR28","unstructured":"The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/."},{"key":"2632_CR29","unstructured":"Claude Opus 4.5 System Card. https:\/\/www.anthropic.com\/claude-opus-4-5-system-card."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02632-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02632-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02632-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T07:12:16Z","timestamp":1782717136000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02632-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2632"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02632-3","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,23]]},"assertion":[{"value":"22 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 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":"487"}}