{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T03:03:04Z","timestamp":1790391784641,"version":"4.1.0"},"reference-count":24,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006545","name":"National Institute on Minority Health and Health Disparities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006545","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["2U54MD007597"],"award-info":[{"award-number":["2U54MD007597"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Three LDL cholesterol (LDL-C) estimation equations (Friedewald, Sampson\/NIH, and Martin-Hopkins) can be calculated from every standard lipid panel, yet laboratories typically report only one. We tested whether disagreement identifies misclassification risk at clinical thresholds and whether simple calibration improves accuracy in this subgroup.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed 10 799 All of Us lipid panels using direct LDL-C as the reference standard. At 70, 100, and 130\u2005mg\/dL [1.81, 2.59, and 3.36\u2005mmol\/L], panels were classified as Agree if all 3 equations fell on the same side and Disagree otherwise. A regime-aware calibration model was compared with 7 machine learning (ML) methods using 5-fold cross-validation and tested in 14 549 hospital-based Medical Information Mart for Intensive Care IV panels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>When equations agreed (86%\u201392% of panels), accuracy was 92% to 96%; when they disagreed (8%\u201314%), accuracy fell to 48%\u201361%. The model\u2019s mean absolute error was 8.98\u2005mg\/dL (0.232\u2005mmol\/L), matching the best ML ensemble (9.01\u2005mg\/dL [0.233\u2005mmol\/L]; 95% CI for the difference, \u22120.35 to 0.29\u2005mg\/dL [\u22120.009 to 0.008\u2005mmol\/L]). In external validation, among split-threshold panels, the model outperformed the best-performing individual equation at each threshold by 3.5 to 9.0 percentage points and the majority vote by 18.5 to 25.2 percentage points. Calibration improved accuracy by 19 to 25 percentage points; hybrid routing achieved 90%\u201393% accuracy internally and 90%\u201394% externally.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Equation disagreement is a zero-cost uncertainty signal identifying patients at highest misclassification risk. A simple, interpretable calibration model improves classification while matching the best-performing ML ensemble.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jalm\/jfag139","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T11:46:49Z","timestamp":1787226409000},"source":"Crossref","is-referenced-by-count":0,"title":["Equation Disagreement as a Zero-Cost Uncertainty Signal for LDL-C Classification: An Interpretable Regime-Aware Calibration Model Rescues Misclassification at Treatment Thresholds"],"prefix":"10.1093","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4471-8420","authenticated-orcid":false,"given":"Ronald","family":"Doku","sequence":"first","affiliation":[{"name":"Department of Biochemistry and Molecular Biology, Howard University College of Medicine , Washington, DC ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nana Yaw A","family":"Osafo","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Molecular Biology, Howard University College of Medicine , Washington, DC ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Kwagyan","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Molecular Biology, Howard University College of Medicine , Washington, DC ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William M","family":"Southerland","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Molecular Biology, Howard University College of Medicine , Washington, DC ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,26]]},"reference":[{"key":"2026092522342145400_jfag139-B1","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1093\/clinchem\/18.6.499","article-title":"Estimation of the concentration of low-density lipoprotein cholesterol in plasma, without use of the preparative ultracentrifuge","volume":"18","author":"Friedewald","year":"1972","journal-title":"Clin Chem"},{"key":"2026092522342145400_jfag139-B2","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1001\/jamacardio.2020.0013","article-title":"A new equation for calculation of low-density lipoprotein cholesterol in patients with normolipidemia and\/or hypertriglyceridemia","volume":"5","author":"Sampson","year":"2020","journal-title":"JAMA Cardiol"},{"key":"2026092522342145400_jfag139-B3","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1001\/jama.2013.280532","article-title":"Comparison of a novel method vs the Friedewald equation for estimating low-density lipoprotein cholesterol levels from the standard lipid profile","volume":"310","author":"Martin","year":"2013","journal-title":"JAMA"},{"key":"2026092522342145400_jfag139-B4","doi-asserted-by":"crossref","first-page":"36","DOI":"10.5334\/gh.1214","article-title":"Accuracy of 23 equations for estimating LDL cholesterol in a clinical laboratory database of 5,051,467 patients","volume":"18","author":"Samuel","year":"2023","journal-title":"Glob Heart"},{"key":"2026092522342145400_jfag139-B5","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2021.28817","article-title":"Comparison of methods to estimate low-density lipoprotein cholesterol in patients with high triglyceride levels","volume":"4","author":"Sajja","year":"2021","journal-title":"JAMA Netw Open"},{"key":"2026092522342145400_jfag139-B6","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1093\/clinchem\/hvad190","article-title":"The Sampson-NIH equation is the preferred calculation method for LDL-C","volume":"70","author":"Sampson","year":"2024","journal-title":"Clin Chem"},{"key":"2026092522342145400_jfag139-B7","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1093\/clinchem\/hvad199","article-title":"Extensive evidence supports the Martin\u2013Hopkins equation as the LDL-C calculation of choice","volume":"70","author":"Grant","year":"2024","journal-title":"Clin Chem"},{"key":"2026092522342145400_jfag139-B8","first-page":"6402","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092522342145400_jfag139-B9","first-page":"13969","article-title":"Can you trust your model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume":"32","author":"Ovadia","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026092522342145400_jfag139-B10","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.ijcard.2022.01.029","article-title":"Estimation of low-density lipoprotein cholesterol levels using machine learning","volume":"352","author":"Oh","year":"2022","journal-title":"Int J Cardiol"},{"key":"2026092522342145400_jfag139-B11","doi-asserted-by":"crossref","DOI":"10.2196\/29331","article-title":"A deep neural network for estimating low-density lipoprotein cholesterol from electronic health records: real-time routine clinical application","volume":"9","author":"Hwang","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2026092522342145400_jfag139-B12","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.19248","article-title":"Machine learning-based prediction of LDL cholesterol: performance evaluation and validation","volume":"13","author":"Meng","year":"2025","journal-title":"PeerJ"},{"key":"2026092522342145400_jfag139-B13","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.1093\/jalm\/jfae057","article-title":"ADLM guidance document on the measurement and reporting of lipids and lipoproteins","volume":"9","author":"Cao","year":"2024","journal-title":"J Appl Lab Med"},{"key":"2026092522342145400_jfag139-B14","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1136\/jcp-2022-208480","article-title":"Best practice for LDL-cholesterol: when and how to calculate","volume":"76","author":"Martins","year":"2023","journal-title":"J Clin Pathol"},{"key":"2026092522342145400_jfag139-B15","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1109\/9.1299","article-title":"The interacting multiple model algorithm for systems with Markovian switching coefficients","volume":"33","author":"Blom","year":"1988","journal-title":"IEEE Trans Automat Contr"},{"key":"2026092522342145400_jfag139-B16","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1056\/NEJMsr1809937","article-title":"The \u201cAll of Us\u201d research program","volume":"381","author":"All of Us Research Program Investigators","year":"2019","journal-title":"N Engl J Med"},{"key":"2026092522342145400_jfag139-B17","article-title":"The All of Us Research Program: data quality, utility, and diversity","volume":"3","author":"Ramirez","year":"2022","journal-title":"Patterns (N Y)"},{"key":"2026092522342145400_jfag139-B18","doi-asserted-by":"publisher","DOI":"10.1093\/jalm\/jfag098","article-title":"Detecting Friedewald-substituted \u201cdirect\u201d LDL cholesterol in a national multi-site electronic health record cohort: prevalence and benchmarking impact","author":"Doku","journal-title":"J Appl Lab Med"},{"key":"2026092522342145400_jfag139-B19","volume-title":"Estimation with applications to tracking and navigation: theory, algorithms and software","author":"Bar-Shalom","year":"2001"},{"key":"2026092522342145400_jfag139-B20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"2026092522342145400_jfag139-B21","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1373\/clinchem.2009.142810","article-title":"Seven direct methods for measuring HDL and LDL cholesterol compared with ultracentrifugation reference measurement procedures","volume":"56","author":"Miller","year":"2010","journal-title":"Clin Chem"},{"key":"2026092522342145400_jfag139-B22","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1093\/clinchem\/48.2.236","article-title":"Methods for measurement of LDL-cholesterol: a critical assessment of direct measurement by homogeneous assays versus calculation","volume":"48","author":"Nauck","year":"2002","journal-title":"Clin Chem"},{"key":"2026092522342145400_jfag139-B23","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.1093\/clinchem\/hvaf099","article-title":"Modern low-density lipoprotein cholesterol formulas outperform direct methods in patients with hypertriglyceridemia and low levels of low-density lipoprotein cholesterol","volume":"71","author":"Meeusen","year":"2025","journal-title":"Clin Chem"},{"key":"2026092522342145400_jfag139-B24","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.cca.2013.04.009","article-title":"Evaluation of four different equations for calculating LDL-C with eight different direct HDL-C assays","volume":"423","author":"Oliveira","year":"2013","journal-title":"Clin Chim Acta"}],"container-title":["The Journal of Applied Laboratory Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jalm\/advance-article-pdf\/doi\/10.1093\/jalm\/jfag139\/71400262\/jfag139.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jalm\/advance-article-pdf\/doi\/10.1093\/jalm\/jfag139\/71400262\/jfag139.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T02:34:31Z","timestamp":1790390071000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jalm\/advance-article\/doi\/10.1093\/jalm\/jfag139\/8836400"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,26]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1093\/jalm\/jfag139","relation":{},"ISSN":["2475-7241"],"issn-type":[{"value":"2475-7241","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,26]]},"article-number":"jfag139"}}