{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:50:53Z","timestamp":1792785053872,"version":"4.5.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T00:00:00Z","timestamp":1783728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":93,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Intermountain Medical Center","id":[{"id":"https:\/\/ror.org\/009c06z12","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-61766-2","type":"journal-article","created":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T06:14:52Z","timestamp":1783750492000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large language models generate diagnostic likelihood ratios with low mean bias but wide dispersion"],"prefix":"10.1038","volume":"16","author":[{"given":"Paul","family":"Chong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhan","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kian","family":"Samadian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amal","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyu","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Chua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cory","family":"Rohlfsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian W.","family":"Locke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,11]]},"reference":[{"key":"61766_CR1","doi-asserted-by":"publisher","unstructured":"McGee, S. (ed) Evidence-Based Physical Diagnosis. Fourth Edition. https:\/\/doi.org\/10.1016\/B978-0-323-39276-1.12001-3 (Elsevier, 2018).","DOI":"10.1016\/B978-0-323-39276-1.12001-3"},{"key":"61766_CR2","doi-asserted-by":"crossref","unstructured":"Newman, T. B. & Kohn, M. A. Evidence-Based Diagnosis: An Introduction to Clinical Epidemiology (Cambridge University Press, 2020).","DOI":"10.1017\/9781108500111"},{"issue":"9","key":"61766_CR3","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1001\/jama.1994.03510330081039","volume":"271","author":"R Jaeschke","year":"1994","unstructured":"Jaeschke, R. et al. Users\u2019 Guides to the Medical Literature: III. How to Use an Article About a Diagnostic Test B. What Are the Results and Will They Help Me in Caring for My Patients? JAMA 271 (9), 703\u2013707. https:\/\/doi.org\/10.1001\/jama.1994.03510330081039 (1994).","journal-title":"JAMA"},{"issue":"9469","key":"61766_CR4","doi-asserted-by":"publisher","first-page":"1500","DOI":"10.1016\/S0140-6736(05)66422-7","volume":"365","author":"DA Grimes","year":"2005","unstructured":"Grimes, D. A. & Schulz, K. F. Refining clinical diagnosis with likelihood ratios. Lancet 365 (9469), 1500\u20131505. https:\/\/doi.org\/10.1016\/S0140-6736(05)66422-7 (2005).","journal-title":"Lancet"},{"key":"61766_CR5","unstructured":"Zellner, A. Optimal Information Processing and Bayes\u2019s Theorem. Am Stat. Published online November 1, Accessed September 16, 2025. https:\/\/www.tandfonline.com\/doi\/abs\/doi.org\/10.1080\/00031305.1988.10475585 (1988).\u00a0"},{"issue":"12","key":"61766_CR6","doi-asserted-by":"publisher","first-page":"e1918023","DOI":"10.1001\/jamanetworkopen.2019.18023","volume":"2","author":"JE Brush Jr","year":"2019","unstructured":"Brush, J. E. Jr, Lee, M., Sherbino, J., Taylor-Fishwick, J. C. & Norman, G. Effect of Teaching Bayesian Methods Using Learning by Concept vs Learning by Example on Medical Students\u2019 Ability to Estimate Probability of a Diagnosis: A Randomized Clinical Trial. JAMA Netw. Open. 2 (12), e1918023\u2013e1918023. https:\/\/doi.org\/10.1001\/jamanetworkopen.2019.18023 (2019).","journal-title":"JAMA Netw. Open."},{"issue":"6","key":"61766_CR7","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/j.amjmed.2017.01.045","volume":"130","author":"JE Brush Jr","year":"2017","unstructured":"Brush, J. E. Jr, Sherbino, J. & Norman, G. R. How expert clinicians intuitively recognize a medical diagnosis. Am. J. Med. 130 (6), 629\u2013634. https:\/\/doi.org\/10.1016\/j.amjmed.2017.01.045 (2017).","journal-title":"Am. J. Med."},{"issue":"4","key":"61766_CR8","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/s0002-9343(98)00054-0","volume":"104","author":"MC Reid","year":"1998","unstructured":"Reid, M. C., Lane, D. A. & Feinstein, A. R. Academic calculations versus clinical judgments: practicing physicians\u2019 use of quantitative measures of test accuracy. Am. J. Med. 104 (4), 374\u2013380. https:\/\/doi.org\/10.1016\/s0002-9343(98)00054-0 (1998).","journal-title":"Am. J. Med."},{"key":"61766_CR9","doi-asserted-by":"publisher","first-page":"h5527","DOI":"10.1136\/bmj.h5527","volume":"351","author":"PM Bossuyt","year":"2015","unstructured":"Bossuyt, P. M. et al. STARD 2015: an updated list of essential items for reporting diagnostic accuracy studies. BMJ 351, h5527. https:\/\/doi.org\/10.1136\/bmj.h5527 (2015).","journal-title":"BMJ"},{"issue":"11","key":"61766_CR10","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.1111\/acem.12255","volume":"20","author":"MA Kohn","year":"2013","unstructured":"Kohn, M. A., Carpenter, C. R. & Newman, T. B. Understanding the direction of bias in studies of diagnostic test accuracy. Acad. Emerg. Med. Off J. Soc. Acad. Emerg. Med. 20 (11), 1194\u20131206. https:\/\/doi.org\/10.1111\/acem.12255 (2013).","journal-title":"Acad. Emerg. Med. Off J. Soc. Acad. Emerg. Med."},{"key":"61766_CR11","doi-asserted-by":"publisher","unstructured":"Usher-Smith, J. A., Sharp, S. J. & Griffin, S. J. The spectrum effect in tests for risk prediction, screening, and diagnosis. BMJ 353 https:\/\/doi.org\/10.1136\/bmj.i3139 (2016).","DOI":"10.1136\/bmj.i3139"},{"key":"61766_CR12","doi-asserted-by":"publisher","unstructured":"Shmatko, A. et al. Learning the natural history of human disease with generative transformers. Nature Published online September 17, 2025:1\u20139. https:\/\/doi.org\/10.1038\/s41586-025-09529-3","DOI":"10.1038\/s41586-025-09529-3"},{"issue":"7972","key":"61766_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 (7972), 172\u2013180. https:\/\/doi.org\/10.1038\/s41586-023-06291-2 (2023).","journal-title":"Nature"},{"key":"61766_CR14","unstructured":"Brown, T. et al. Language Models are Few-Shot Learners. In: Advances in Neural Information Processing Systems. Vol 33. 1877\u20131901. . https:\/\/papers.nips.cc\/paper\/2020\/hash\/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html (Curran Associates, Inc., 2020).\u00a0Accessed September 17, 2025."},{"issue":"3","key":"61766_CR15","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1001\/jama.2023.25057","volume":"331","author":"MD Howell","year":"2024","unstructured":"Howell, M. D., Corrado, G. S. & DeSalvo, K. B. Three Epochs of Artificial Intelligence in Health Care. JAMA 331 (3), 242\u2013244. https:\/\/doi.org\/10.1001\/jama.2023.25057 (2024).","journal-title":"JAMA"},{"issue":"10","key":"61766_CR16","doi-asserted-by":"publisher","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh, E. et al. Large Language Model Influence on Diagnostic Reasoning: A Randomized Clinical Trial. JAMA Netw. Open. 7 (10), e2440969. https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.40969 (2024).","journal-title":"JAMA Netw. Open."},{"issue":"9","key":"61766_CR17","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med. 30 (9), 2613\u20132622. https:\/\/doi.org\/10.1038\/s41591-024-03097-1 (2024).","journal-title":"Nat. Med."},{"issue":"9","key":"61766_CR18","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.1093\/jamia\/ocae074","volume":"31","author":"SS Sahoo","year":"2024","unstructured":"Sahoo, S. S. et al. Large language models for biomedicine: foundations, opportunities, challenges, and best practices. J. Am. Med. Inf. Assoc. JAMIA. 31 (9), 2114\u20132124. https:\/\/doi.org\/10.1093\/jamia\/ocae074 (2024).","journal-title":"J. Am. Med. Inf. Assoc. JAMIA"},{"issue":"8476","key":"61766_CR19","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","volume":"1","author":"JM Bland","year":"1986","unstructured":"Bland, J. M. & Altman, D. G. Statistical methods for assessing agreement between two methods of clinical measurement. Lancet Lond. Engl. 1 (8476), 307\u2013310 (1986).","journal-title":"Lancet Lond. Engl."},{"key":"61766_CR20","unstructured":"Good, I. J. Weight of evidence: a brief survey. In Bayesian Statistics 2: Proceedings of the Second Valencia International Meeting, September 6\u201310, 1983 (eds Bernardo, J. M., DeGroot, M. H., Lindley, D. V. & Smith, A. F. M.) 249\u2013270 (North-Holland, 1985)."},{"issue":"1\/2","key":"61766_CR21","doi-asserted-by":"publisher","first-page":"9","DOI":"10.2307\/2334971","volume":"31","author":"E Pitman","year":"1939","unstructured":"Pitman, E. A note on normal correlation. Biometrika 31 (1\/2), 9\u201312 (1939).","journal-title":"Biometrika"},{"issue":"1\/2","key":"61766_CR22","doi-asserted-by":"publisher","first-page":"13","DOI":"10.2307\/2334972","volume":"31","author":"W Morgan","year":"1939","unstructured":"Morgan, W. A test for the significance of the difference between the two variances in a sample from a normal bivariate population. Biometrika 31 (1\/2), 13\u201319 (1939).","journal-title":"Biometrika"},{"issue":"5","key":"61766_CR23","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1037\/h0028106","volume":"72","author":"JL Fleiss","year":"1969","unstructured":"Fleiss, J. L., Cohen, J. & Everitt, B. S. Large sample standard errors of kappa and weighted kappa. Psychol. Bull. 72 (5), 323. https:\/\/doi.org\/10.1037\/h0028106 (1969).","journal-title":"Psychol. Bull."},{"issue":"3","key":"61766_CR24","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1177\/001316447303300309","volume":"33","author":"JL Fleiss","year":"1973","unstructured":"Fleiss, J. L. & Cohen, J. The Equivalence of Weighted Kappa and the Intraclass Correlation Coefficient as Measures of Reliability. Educ. Psychol. Meas. 33 (3), 613\u2013619. https:\/\/doi.org\/10.1177\/001316447303300309 (1973).","journal-title":"Educ. Psychol. Meas."},{"issue":"1","key":"61766_CR25","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis, J. R. & Koch, G. G. The Measurement of Observer Agreement for Categorical Data. Biometrics 33 (1), 159\u2013174. https:\/\/doi.org\/10.2307\/2529310 (1977).","journal-title":"Biometrics"},{"issue":"11","key":"61766_CR26","doi-asserted-by":"publisher","first-page":"e2111547119","DOI":"10.1073\/pnas.2111547119","volume":"119","author":"M Steyvers","year":"2022","unstructured":"Steyvers, M., Tejeda, H., Kerrigan, G. & Smyth, P. Bayesian modeling of human\u2013AI complementarity. Proc. Natl. Acad. Sci. 119 (11), e2111547119. https:\/\/doi.org\/10.1073\/pnas.2111547119 (2022).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"61766_CR27","unstructured":"Simel, D. L. & Rennie, D. Forward. In: The Rational Clinical Examination: Evidence-Based Clinical Diagnosis. McGraw-Hill Education; Accessed September 21, 2025. (2016). http:\/\/jamaevidence.mhmedical.com\/content.aspx?aid=1170154778"},{"issue":"11","key":"61766_CR28","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1001\/jama.282.11.1061","volume":"282","author":"JG Lijmer","year":"1999","unstructured":"Lijmer, J. G. et al. Empirical Evidence of Design-Related Bias in Studies of Diagnostic Tests. JAMA 282 (11), 1061\u20131066. https:\/\/doi.org\/10.1001\/jama.282.11.1061 (1999).","journal-title":"JAMA"},{"issue":"02","key":"61766_CR29","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1142\/S0218001405003983","volume":"19","author":"H Zhang","year":"2005","unstructured":"Zhang, H. Exploring Conditions for the Optimality of Na\u00efve Bayes. Int. J. Pattern Recognit. Artif. Intell. 19 (02), 183\u2013198. https:\/\/doi.org\/10.1142\/S0218001405003983 (2005).","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"61766_CR30","unstructured":"Carlini, N. et al. Quantifying Memorization Across Neural Language Models. In: Accessed September 19, 2025. (2022). https:\/\/openreview.net\/forum?id=TatRHT_1cK"},{"issue":"12","key":"61766_CR31","doi-asserted-by":"publisher","first-page":"e2347075","DOI":"10.1001\/jamanetworkopen.2023.47075","volume":"6","author":"A Rodman","year":"2023","unstructured":"Rodman, A., Buckley, T. A., Manrai, A. K. & Morgan, D. J. Artificial Intelligence vs Clinician Performance in Estimating Probabilities of Diagnoses Before and After Testing. JAMA Netw. Open. 6 (12), e2347075\u2013e2347075. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.47075 (2023).","journal-title":"JAMA Netw. Open."},{"issue":"12","key":"61766_CR32","doi-asserted-by":"publisher","first-page":"899","DOI":"10.1136\/bmjqs-2022-014865","volume":"31","author":"J Staal","year":"2022","unstructured":"Staal, J. et al. Effect on diagnostic accuracy of cognitive reasoning tools for the workplace setting: systematic review and meta-analysis. BMJ Qual. Saf. 31 (12), 899\u2013910. https:\/\/doi.org\/10.1136\/bmjqs-2022-014865 (2022).","journal-title":"BMJ Qual. Saf."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61766-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61766-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61766-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T13:03:38Z","timestamp":1791810218000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61766-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,11]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["61766"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-61766-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,11]]},"assertion":[{"value":"14 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Brian Locke: Dr. Locke claims an equity interest in Mountain Biometrics, a startup focused on machine learning medical time series data. Shuhan He: Dr. Shuhan He is employed by Mass General Physician Organization and Mass General Institute of Health Professions and has received consulting fees from Franchise Medicine. He is an unpaid volunteer at Health Tech Without Borders and ConductScience.org. No other disclosures are reported.Boyu Peng: Mr. Boyu Peng was employed by ConductScience Inc. and serves as Adjunct Faculty at the Massachusetts General Hospital Institute of Health Professions. These affiliations are not relevant to the work presented in this article. No other conflicts of interest are declared.The remaining authors have no conflict of interest to declare.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"31819"}}