{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:03:18Z","timestamp":1774026198625,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T00:00:00Z","timestamp":1746316800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T00:00:00Z","timestamp":1746316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"NIH","award":["R01 LM014306"],"award-info":[{"award-number":["R01 LM014306"]}]},{"name":"NIH","award":["U24 TR004111"],"award-info":[{"award-number":["U24 TR004111"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"DOI":"10.1038\/s41746-025-01576-4","type":"journal-article","created":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T01:28:38Z","timestamp":1746322118000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Mitigating the risk of health inequity exacerbated by large language models"],"prefix":"10.1038","volume":"8","author":[{"given":"Yuelyu","family":"Ji","sequence":"first","affiliation":[]},{"given":"Wenhe","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Sonish","family":"Sivarajkumar","sequence":"additional","affiliation":[]},{"given":"Hang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Eugene M","family":"Sadhu","sequence":"additional","affiliation":[]},{"given":"Zhuochun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xizhi","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Shyam","family":"Visweswaran","sequence":"additional","affiliation":[]},{"given":"Yanshan","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,4]]},"reference":[{"key":"1576_CR1","unstructured":"Achiam, J. et al. Gpt-4 technical report. arXiv https:\/\/arxiv.org\/abs\/2303.08774 (2023)."},{"key":"1576_CR2","unstructured":"Dubey, A. et al. The llama 3 herd of models. arXiv https:\/\/arxiv.org\/abs\/2407.21783 (2024)."},{"key":"1576_CR3","unstructured":"Grosse, R. et al. Studying large language model generalization with influence functions. arXiv https:\/\/arxiv.org\/abs\/2308.03296 (2023)."},{"key":"1576_CR4","doi-asserted-by":"publisher","first-page":"e2343689","DOI":"10.1001\/jamanetworkopen.2023.43689","volume":"6","author":"M Benary","year":"2023","unstructured":"Benary, M. et al. Leveraging large language models for decision support in personalized oncology. JAMA Network Open 6, e2343689\u2013e2343689 (2023).","journal-title":"JAMA Network Open"},{"key":"1576_CR5","doi-asserted-by":"crossref","unstructured":"Zhou, L. et al. Larger and more instructable language models become less reliable. Nature 634, 61\u201368 (2024).","DOI":"10.1038\/s41586-024-07930-y"},{"key":"1576_CR6","unstructured":"Kaplan, J. et al. Scaling laws for neural language models. arXiv https:\/\/arxiv.org\/abs\/2001.08361 (2020)."},{"key":"1576_CR7","doi-asserted-by":"crossref","unstructured":"Jin, Q. et al. Matching patients to clinical trials with large language models. Nat. Commun. 15, 9074 (2023).","DOI":"10.1038\/s41467-024-53081-z"},{"key":"1576_CR8","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.3390\/app11146421","volume":"11","author":"D Jin","year":"2021","unstructured":"Jin, D. et al. What disease does this patient have? a large-scale open domain question answering dataset from medical exams. Appl. Sci. 11, 6421 (2021).","journal-title":"Appl. Sci."},{"key":"1576_CR9","unstructured":"Pal, A., Umapathi, L. K. & Sankarasubbu, M. Medmcqa: a large-scale multi-subject multi-choice dataset for medical domain question answering. arXiv https:\/\/arxiv.org\/abs\/2203.14371 (2022)."},{"key":"1576_CR10","unstructured":"Acikgoz, E. C. et al. Hippocrates: an open-source framework for advancing large language models in healthcare. arXiv https:\/\/arxiv.org\/abs\/2404.16621 (2024)."},{"key":"1576_CR11","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":"1576_CR12","unstructured":"Nori, H., King, N., McKinney, S. M., Carignan, D. & Horvitz, E. Capabilities of gpt-4 on medical challenge problems. arXiv https:\/\/arxiv.org\/abs\/2303.13375 (2023)."},{"key":"1576_CR13","unstructured":"Nori, H. et al. Can generalist foundation models outcompete special-purpose tuning? case study in medicine. arXiv https:\/\/arxiv.org\/abs\/2311.16452 (2023)."},{"key":"1576_CR14","doi-asserted-by":"crossref","unstructured":"Singhal, K. et al. Towards expert-level medical question answering with large language models. Nat. Med. 31, 943\u2013950 (2023).","DOI":"10.1038\/s41591-024-03423-7"},{"key":"1576_CR15","unstructured":"Bai, X., Wang, A., Sucholutsky, I. & Griffiths, T. L. Measuring implicit bias in explicitly unbiased large language models. arXiv https:\/\/arxiv.org\/abs\/2402.04105 (2024)."},{"key":"1576_CR16","unstructured":"Yu, C. et al. Credit card fraud detection using advanced transformer model. arXiv https:\/\/arxiv.org\/abs\/2406.03733 (2024)."},{"key":"1576_CR17","unstructured":"Dai, S. et al. Unifying bias and unfairness in information retrieval: a survey of challenges and opportunities with large language models. arXiv https:\/\/arxiv.org\/abs\/2404.11457 (2024)."},{"key":"1576_CR18","unstructured":"Tu, T. et al. Towards conversational diagnostic AI. arXiv https:\/\/arxiv.org\/abs\/2401.05654 (2024)."},{"key":"1576_CR19","doi-asserted-by":"publisher","first-page":"AIoa2300138","DOI":"10.1056\/AIoa2300138","volume":"1","author":"T Tu","year":"2024","unstructured":"Tu, T. et al. Towards generalist biomedical AI. NEJM AI 1, AIoa2300138 (2024).","journal-title":"NEJM AI"},{"key":"1576_CR20","doi-asserted-by":"crossref","unstructured":"Tanno, R. et al. Consensus, dissensus and synergy between clinicians and specialist foundation models in radiology report generation (2024).","DOI":"10.21203\/rs.3.rs-3940387\/v1"},{"key":"1576_CR21","unstructured":"Dash, D. et al. Evaluation of gpt-3.5 and gpt-4 for supporting real-world information needs in healthcare delivery. arXiv https:\/\/arxiv.org\/abs\/2304.13714 (2023)."},{"key":"1576_CR22","first-page":"8765","volume":"33","author":"C-Y Chuang","year":"2020","unstructured":"Chuang, C.-Y., Robinson, J., Lin, Y.-C., Torralba, A. & Jegelka, S. Debiased contrastive learning. Adv. Neural Inf. Process Syst. 33, 8765\u20138775 (2020).","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"1576_CR23","first-page":"6827","volume":"33","author":"Y Tian","year":"2020","unstructured":"Tian, Y. et al. What makes for good views for contrastive learning? Adv. Neural Inf. Process Syst. 33, 6827\u20136839 (2020).","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"1576_CR24","unstructured":"Rim, D. N., Heo, D. & Choi, H. Adversarial training with contrastive learning in nlp. arXiv https:\/\/arxiv.org\/abs\/2109.09075 (2021)."},{"key":"1576_CR25","doi-asserted-by":"publisher","first-page":"107977","DOI":"10.1016\/j.compbiomed.2024.107977","volume":"170","author":"JP V","year":"2024","unstructured":"V, J. P., S, A. A. V., P, G. K. & N,K, K. A novel attention-based cross-modal transfer learning framework for predicting cardiovascular disease. Comput. Biol. Med. 170, 107977 (2024).","journal-title":"Comput. Biol. Med."},{"key":"1576_CR26","doi-asserted-by":"publisher","unstructured":"Prakash, V. J. & Vijay, S. A. A. A unified framework for analyzing textual context and intent in social media. ACM Trans. Intell. Syst. Technol.15, https:\/\/doi.org\/10.1145\/3682064 (2024).","DOI":"10.1145\/3682064"},{"key":"1576_CR27","doi-asserted-by":"crossref","unstructured":"Koopman, B. & Zuccon, G. A test collection for matching patients to clinical trials. Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval. https:\/\/api.semanticscholar.org\/CorpusID:5630619 (2016).","DOI":"10.1145\/2911451.2914672"},{"key":"1576_CR28","doi-asserted-by":"crossref","unstructured":"Roberts, K., Demner-Fushman, D., Voorhees, E. M., Bedrick, S. & Hersh, W. R. Overview of the trec 2022 clinical trials track. https:\/\/trec.nist.gov\/pubs\/trec31\/papers\/Overview_trials.pdf (2022).","DOI":"10.6028\/NIST.SP.500-338.trials-overview"},{"key":"1576_CR29","unstructured":"Team, G. et al. Gemini: a family of highly capable multimodal models. arXiv https:\/\/arxiv.org\/abs\/2312.11805 (2023)."},{"key":"1576_CR30","unstructured":"The claude 3 model family: Opus, sonnet, haiku. https:\/\/api.semanticscholar.org\/CorpusID:268232499."},{"key":"1576_CR31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.jbi.2018.10.005","volume":"88","author":"S Velupillai","year":"2018","unstructured":"Velupillai, S. et al. Using clinical natural language processing for health outcomes research: overview and actionable suggestions for future advances. J. Biomed. Inform. 88, 11\u201319 (2018).","journal-title":"J. Biomed. Inform."},{"key":"1576_CR32","unstructured":"Nazi, Z. A. & Peng, W. Large language models in healthcare and medical domain: a review. arXiv https:\/\/arxiv.org\/abs\/2401.06775 (2024)."},{"key":"1576_CR33","doi-asserted-by":"publisher","first-page":"e0298892","DOI":"10.1371\/journal.pone.0298892","volume":"19","author":"N Tavabi","year":"2024","unstructured":"Tavabi, N., Singh, M., Pruneski, J. & Kiapour, A. M. Systematic evaluation of common natural language processing techniques to codify clinical notes. Plos One 19, e0298892 (2024).","journal-title":"Plos One"},{"key":"1576_CR34","doi-asserted-by":"crossref","unstructured":"Li, J. & Li, G. The triangular trade-off between robustness, accuracy and fairness in deep neural networks: a survey. ACM Comput. Surv. 57, 6 (2024).","DOI":"10.1145\/3645088"},{"key":"1576_CR35","unstructured":"Kirchdorfer, L. et al. Analytical uncertainty-based loss weighting in multi-task learning. arXiv https:\/\/arxiv.org\/abs\/2408.07985 (2024)."},{"key":"1576_CR36","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s00371-023-02809-x","volume":"40","author":"H Wu","year":"2024","unstructured":"Wu, H., Li, B., Tian, L., Feng, J. & Dong, C. An adaptive loss weighting multi-task network with attention-guide proposal generation for small size defect inspection. Vis. Comput. 40, 681\u2013698 (2024).","journal-title":"Vis. Comput."},{"key":"1576_CR37","doi-asserted-by":"crossref","unstructured":"Kundi, B., El Morr, C., Gorman, R. & Dua, E. Artificial intelligence and bias: a scoping review. AI Soc. 10, 510 (2023).","DOI":"10.1201\/9781003261247-15"},{"key":"1576_CR38","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/sci6010003","volume":"6","author":"E Ferrara","year":"2023","unstructured":"Ferrara, E. Fairness and bias in artificial intelligence: A brief survey of sources, impacts, and mitigation strategies. Sci 6, 3 (2023).","journal-title":"Sci"},{"key":"1576_CR39","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-023-01056-8","volume":"7","author":"RJ Chen","year":"2023","unstructured":"Chen, R. J. et al. Algorithmic fairness in artificial intelligence for medicine and healthcare. Nat. Biomed. Eng. 7, 719\u2013742 (2023).","journal-title":"Nat. Biomed. Eng."},{"key":"1576_CR40","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1177\/17456916221134490","volume":"18","author":"AC Timmons","year":"2023","unstructured":"Timmons, A. C. et al. A call to action on assessing and mitigating bias in artificial intelligence applications for mental health. Perspect. Psychol. Sci. 18, 1062\u20131096 (2023).","journal-title":"Perspect. Psychol. Sci."},{"key":"1576_CR41","doi-asserted-by":"crossref","unstructured":"Polevikov, S. Advancing AI in healthcare: a comprehensive review of best practices. Clin Chim. Acta 548, 117519 (2023).","DOI":"10.1016\/j.cca.2023.117519"},{"key":"1576_CR42","first-page":"361","volume":"33","author":"Y Romano","year":"2020","unstructured":"Romano, Y., Bates, S. & Candes, E. Achieving equalized odds by resampling sensitive attributes. Adv. Neural Inform. Process. Syst. 33, 361\u2013371 (2020).","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"1576_CR43","unstructured":"Roelofs, R., Cain, N., Shlens, J. & Mozer, M. C. Mitigating bias in calibration error estimation. arxiv https:\/\/arxiv.org\/abs\/2012.08668 (2022)."},{"key":"1576_CR44","unstructured":"Xiao, T., Wang, X., Efros, A. A. & Darrell, T. What should not be contrastive in contrastive learning. arXiv https:\/\/arxiv.org\/abs\/2008.05659 (2020)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01576-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01576-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01576-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T01:28:48Z","timestamp":1746322128000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-01576-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,4]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1576"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-01576-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,4]]},"assertion":[{"value":"25 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Y.W. has ownership and equity in BonafideNLP, LLC, and S.V. has ownership and equity in Kvatchii, Ltd., READE.ai, Inc., and ThetaRho, Inc. The other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"246"}}