{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:56:12Z","timestamp":1791305772117,"version":"4.3.1"},"reference-count":21,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Routine laboratory panels are nearly universal, but the panels\u2019 joint information is underused. We evaluated contemporaneous classification of International Statistical Classification of Diseases, Tenth Revision (ICD-10) code groups from same-encounter laboratory results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed 17 eXtreme Gradient Boosting (XGBoost) classifiers in 242\u2009648 adult internal medicine encounters using age, sex, and results from 34 assays, with ICD-10 codes used only as outcomes. Stratified 10-fold cross-validation assessed discrimination, calibration, and decision curve performance. Leakage-free recalibration and fold-specific thresholds targeted 95% specificity. Using an 80-patient temporal holdout cohort, we compared the model with 3 large language models accessed through an application programming interface and findings from 1 specialist physician.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The mean cross-validated area under the curve (AUC) was 0.893. With identical preprocessing, the mean AUC was 0.892 for XGBoost and 0.809 for logistic regression. Recalibration changed the mean intercept and slope to \u22120.002 and 0.999, respectively, and the Brier score from 0.099 to 0.044. The holdout micro-averaged AUC was 0.880 vs 0.729 to 0.739 for language models; paired differences were 0.141 to 0.151 (all P\u2009&amp;lt;\u2009.005). Matched-specificity sensitivity differences favored the model but were imprecise.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Routine panels contain substantial information about contemporaneous ICD-10 coding, supporting prospective multicenter evaluation rather than a diagnostic claim.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/labmed\/lmag074","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T11:44:50Z","timestamp":1789213490000},"source":"Crossref","is-referenced-by-count":0,"title":["Routine laboratory panels classify internal medicine\n                    <i>ICD-10<\/i>\n                    code groups: comparison with frontier large language models and laboratory-only specialist assessment"],"prefix":"10.1093","volume":"57","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5932-5617","authenticated-orcid":false,"given":"Yusuf","family":"Yesil","sequence":"first","affiliation":[{"name":"Department of Biochemistry, Istanbul Faculty of Medicine, Istanbul University , Istanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5829-9186","authenticated-orcid":false,"given":"Alpay","family":"Medetalibeyoglu","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Istanbul Faculty of Medicine, Istanbul University , Istanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2933-3119","authenticated-orcid":false,"given":"Evin","family":"Ademoglu","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, Istanbul Faculty of Medicine, Istanbul University , Istanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,6]]},"reference":[{"key":"2026100612332582000_lmag074-B1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1111\/ijlh.13537","article-title":"Machine learning in health care and laboratory medicine: general overview of supervised learning and Auto-ML","volume":"43 Suppl 1","author":"Rashidi","year":"2021","journal-title":"Int J Lab Hematol"},{"key":"2026100612332582000_lmag074-B2","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1093\/clinchem\/hvab165","article-title":"Artificial intelligence and mapping a new direction in laboratory medicine: a review","volume":"67","author":"Herman","year":"2021","journal-title":"Clin Chem"},{"key":"2026100612332582000_lmag074-B3","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1016\/j.clinbiochem.2016.07.013","article-title":"Clinical chemistry in higher dimensions: machine-learning and enhanced prediction from routine clinical chemistry data","volume":"49","author":"Richardson","year":"2016","journal-title":"Clin Biochem"},{"key":"2026100612332582000_lmag074-B4","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1007\/s10916-011-9668-3","article-title":"Artificial intelligence models for predicting iron deficiency anemia and iron serum level based on accessible laboratory data","volume":"36","author":"Azarkhish","year":"2012","journal-title":"J Med Syst"},{"key":"2026100612332582000_lmag074-B5","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/s41591-018-0239-8","article-title":"Predicting the early risk of chronic kidney disease in patients with diabetes using real-world data","volume":"25","author":"Ravizza","year":"2019","journal-title":"Nat Med"},{"key":"2026100612332582000_lmag074-B6","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1186\/s12882-017-0744-x","article-title":"The prevalence and mortality of hyponatremia is seriously underestimated in Chinese general medical patients","volume":"18","author":"Hao","year":"2017","journal-title":"BMC Nephrol"},{"key":"2026100612332582000_lmag074-B7","doi-asserted-by":"crossref","first-page":"617486","DOI":"10.3389\/fmed.2021.617486","article-title":"Early detection of sepsis with machine learning techniques: a brief clinical perspective","volume":"8","author":"Giacobbe","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"2026100612332582000_lmag074-B8","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1038\/s41598-017-18564-8","article-title":"An application of machine learning to hematological diagnosis","volume":"8","author":"Gun\u010dar","year":"2018","journal-title":"Sci Rep"},{"key":"2026100612332582000_lmag074-B9","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1186\/s12911-020-01332-6","article-title":"Explainability for artificial intelligence in healthcare: a multidisciplinary perspective","volume":"20","author":"Amann","year":"2020","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026100612332582000_lmag074-B10","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"2026100612332582000_lmag074-B11","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1001\/jama.2023.8288","article-title":"Accuracy of a generative artificial intelligence model in a complex diagnostic challenge","volume":"330","author":"Kanjee","year":"2023","journal-title":"JAMA"},{"key":"2026100612332582000_lmag074-B12","doi-asserted-by":"crossref","first-page":"e2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","article-title":"Large language model influence on diagnostic reasoning: a randomized clinical trial","volume":"7","author":"Goh","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2026100612332582000_lmag074-B13","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1038\/s41746-025-01556-8","article-title":"Preliminary analysis of the impact of lab results on large language model generated differential diagnoses","volume":"8","author":"Bhasuran","year":"2025","journal-title":"Npj Digit Med"},{"key":"2026100612332582000_lmag074-B14","doi-asserted-by":"publisher","first-page":"327","DOI":"10.3343\/alm.2025.0200","article-title":"Evaluation of the performance of Advanced Large Language Models in laboratory medicine using residency examinations","volume":"46","author":"Jung","year":"2026","journal-title":"Ann Lab Med"},{"key":"2026100612332582000_lmag074-B15","doi-asserted-by":"publisher","first-page":"ooaf055","DOI":"10.1093\/jamiaopen\/ooaf055","article-title":"Comparative analysis of large language models in clinical diagnosis: performance evaluation across common and complex medical cases","volume":"8","author":"Dinc","year":"2025","journal-title":"JAMIA Open"},{"key":"2026100612332582000_lmag074-B16","first-page":"507","author":"Grinsztajn","year":"2022"},{"key":"2026100612332582000_lmag074-B17","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular data: deep learning is not all you need","volume":"81","author":"Shwartz-Ziv","year":"2022","journal-title":"Information Fusion"},{"key":"2026100612332582000_lmag074-B18","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med Decis Making"},{"key":"2026100612332582000_lmag074-B19","first-page":"18932","article-title":"Revisiting deep learning models for tabular data","volume":"34","author":"Gorishniy","year":"2021","journal-title":"NeurIPS"},{"key":"2026100612332582000_lmag074-B20","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"2026100612332582000_lmag074-B21","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ."}],"container-title":["Laboratory Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/labmed\/article-pdf\/57\/6\/lmag074\/71628247\/lmag074.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/labmed\/article-pdf\/57\/6\/lmag074\/71628247\/lmag074.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T16:33:38Z","timestamp":1791304418000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/labmed\/article\/doi\/10.1093\/labmed\/lmag074\/8869107"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":21,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,10,5]]}},"URL":"https:\/\/doi.org\/10.1093\/labmed\/lmag074","relation":{},"ISSN":["0007-5027","1943-7730"],"issn-type":[{"value":"0007-5027","type":"print"},{"value":"1943-7730","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,11]]},"published":{"date-parts":[[2026,10,5]]},"article-number":"lmag074"}}