{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T23:24:02Z","timestamp":1779924242404,"version":"3.53.1"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes and Digestive and Kidney Diseases","doi-asserted-by":"publisher","award":["1R01DK116790"],"award-info":[{"award-number":["1R01DK116790"]}],"id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Assessing glomerular filtration rate (GFR) is critical for diagnosis, staging, and management of kidney disease. However, accuracy of estimated GFR (eGFR) is limited by large errors (&gt;30% error present in &gt;10\u201350% of patients), adversely impacting patient care. Errors often result from variation across populations of non-GFR determinants affecting the filtration markers used to estimate GFR. We hypothesized that combining multiple filtration markers with non-overlapping non-GFR determinants into a panel GFR could improve eGFR accuracy, extending current recognition that adding cystatin C to serum creatinine improves accuracy. Non-GFR determinants of markers can affect the accuracy of eGFR in two ways: first, increased variability in the non-GFR determinants of some filtration markers among application populations compared to the development population may result in outlying values for those markers. Second, systematic differences in the non-GFR determinants of some markers between application and development populations can lead to biased estimates in the application populations. Here, we propose and evaluate methods for estimating GFR based on multiple markers in applications with potentially higher rates of outlying predictors than in development data. We apply transfer learning to address systematic differences between application and development populations. We evaluated a panel of 8 markers (5 metabolites and 3 low molecular weight proteins) in 3,554 participants from 9 studies. Results show that contamination in two strongly predictive markers can increase imprecision by more than two-fold, but outlier identification with robust estimation can restore precision nearly fully to uncontaminated data. Furthermore, transfer learning can yield similar results with even modest training set sample size. Combining both approaches addresses both sources of error in GFR estimates. Once the laboratory challenge of developing a validated targeted assay for additional metabolites is overcome, these methods can inform the use of a panel eGFR across diverse clinical settings, ensuring accuracy despite differing non-GFR determinants.<\/jats:p>","DOI":"10.1371\/journal.pone.0313154","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:35:16Z","timestamp":1733164516000},"page":"e0313154","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Panel estimated Glomerular Filtration Rate (GFR): Statistical considerations for maximizing accuracy in diverse clinical populations"],"prefix":"10.1371","volume":"19","author":[{"given":"Nora F.","family":"Fino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2820-9482","authenticated-orcid":true,"given":"Lesley A.","family":"Inker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Greene","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7475-4171","authenticated-orcid":true,"given":"Ogechi M.","family":"Adingwupu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Josef","family":"Coresh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesse","family":"Seegmiller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael G.","family":"Shlipak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tazeen H.","family":"Jafar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberto","family":"Kalil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8211-018X","authenticated-orcid":true,"given":"Veronica T.","family":"Costa e Silva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5696-0084","authenticated-orcid":true,"given":"Vilmundur","family":"Gudnason","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew S.","family":"Levey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Haaland","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"issue":"4s","key":"pone.0313154.ref001","first-page":"S117","article-title":"KDIGO 2024 Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease","volume":"105","year":"2024","journal-title":"Kidney Int"},{"issue":"5","key":"pone.0313154.ref002","doi-asserted-by":"crossref","first-page":"112","DOI":"10.4330\/wjc.v2.i5.112","article-title":"Heart failure in subjects with chronic kidney disease: best management practices","volume":"2","author":"F. Aslam","year":"2010","journal-title":"World journal of cardiology"},{"issue":"4","key":"pone.0313154.ref003","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1016\/j.jhep.2011.10.016","article-title":"Renal failure and cirrhosis: a systematic review of mortality and prognosis","volume":"56","author":"G. Fede","year":"2012","journal-title":"Journal of hepatology"},{"issue":"2","key":"pone.0313154.ref004","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.jhep.2014.03.034","article-title":"Chronic kidney disease and associated mortality after liver transplantation\u2013a time-dependent analysis using measured glomerular filtration rate","volume":"61","author":"A.M. Allen","year":"2014","journal-title":"Journal of hepatology"},{"issue":"10","key":"pone.0313154.ref005","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1056\/NEJMoa021744","article-title":"Chronic renal failure after transplantation of a nonrenal organ","volume":"349","author":"A.O. Ojo","year":"2003","journal-title":"New England Journal of Medicine"},{"issue":"5","key":"pone.0313154.ref006","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1161\/CIRCULATIONAHA.105.580506","article-title":"Renal function as a predictor of outcome in a broad spectrum of patients with heart failure","volume":"113","author":"H.L. Hillege","year":"2006","journal-title":"Circulation"},{"issue":"1","key":"pone.0313154.ref007","first-page":"1","article-title":"KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease","volume":"3","author":"Outcomes, K.D.I.G. and C.W. Group","year":"2013","journal-title":"Kidney Int"},{"issue":"12","key":"pone.0313154.ref008","doi-asserted-by":"crossref","first-page":"2994","DOI":"10.1681\/ASN.2021070988","article-title":"A unifying approach for GFR estimation: recommendations of the NKF-ASN task force on reassessing the inclusion of race in diagnosing kidney disease","volume":"32","author":"C. Delgado","year":"2021","journal-title":"Journal of the American Society of Nephrology"},{"issue":"19","key":"pone.0313154.ref009","doi-asserted-by":"crossref","first-page":"1737","DOI":"10.1056\/NEJMoa2102953","article-title":"New Creatinine- and Cystatin C-Based Equations to Estimate GFR without Race","volume":"385","author":"L.A. Inker","year":"2021","journal-title":"N Engl J Med"},{"issue":"4","key":"pone.0313154.ref010","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1093\/clinchem\/hvab278","article-title":"National Kidney Foundation Laboratory Engagement Working Group Recommendations for Implementing the CKD-EPI 2021 Race-Free Equations for Estimated Glomerular Filtration Rate: Practical Guidance for Clinical Laboratories","volume":"68","author":"W.G. Miller","year":"2021","journal-title":"Clinical Chemistry"},{"issue":"1","key":"pone.0313154.ref011","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1038\/s41581-019-0191-y","article-title":"Measured and estimated glomerular filtration rate: current status and future directions","volume":"16","author":"A.S. Levey","year":"2020","journal-title":"Nature Reviews Nephrology"},{"issue":"6","key":"pone.0313154.ref012","doi-asserted-by":"crossref","first-page":"461","DOI":"10.7326\/0003-4819-130-6-199903160-00002","article-title":"A more accurate method to estimate glomerular filtration rate from serum creatinine: a new prediction equation","volume":"130","author":"A.S. Levey","year":"1999","journal-title":"Annals of internal medicine"},{"issue":"5","key":"pone.0313154.ref013","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1093\/ndt\/gfy094","article-title":"Metabolomic profiling to improve glomerular filtration rate estimation: a proof-of-concept study","volume":"34","author":"J. Coresh","year":"2019","journal-title":"Nephrology Dialysis Transplantation"},{"issue":"2","key":"pone.0313154.ref014","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1053\/j.ajkd.2016.09.016","article-title":"Cystatin C versus creatinine for GFR estimation in CKD due to heart failure","volume":"69","author":"D. Kervella","year":"2017","journal-title":"American Journal of Kidney Diseases"},{"issue":"2","key":"pone.0313154.ref015","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1053\/j.ajkd.2015.09.022","article-title":"Creatinine versus cystatin C for estimating GFR in patients with liver cirrhosis","volume":"67","author":"A. Torre","year":"2016","journal-title":"American Journal of Kidney Diseases"},{"key":"pone.0313154.ref016","doi-asserted-by":"crossref","first-page":"100727","DOI":"10.1016\/j.xkme.2023.100727","article-title":"Cystatin C as a GFR estimation marker in acute and chronic illness: a systematic review","author":"O.M. Adingwupu","year":"2023","journal-title":"Kidney Medicine"},{"issue":"1","key":"pone.0313154.ref017","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1053\/j.ackd.2017.10.004","article-title":"Estimated glomerular filtration rate from a panel of filtration markers\u2014hope for increased accuracy beyond measured glomerular filtration rate?","volume":"25","author":"L.A. Inker","year":"2018","journal-title":"Advances in chronic kidney disease"},{"issue":"2","key":"pone.0313154.ref018","doi-asserted-by":"crossref","first-page":"348","DOI":"10.2215\/CJN.02870707","article-title":"Influence of Muscle Mass and Physical Activity on Serum and Urinary Creatinine and Serum Cystatin C","volume":"3","author":"A.C. Baxmann","year":"2008","journal-title":"Clinical Journal of the American Society of Nephrology"},{"issue":"3","key":"pone.0313154.ref019","doi-asserted-by":"crossref","first-page":"c187","DOI":"10.1159\/000328911","article-title":"Trimethoprim, creatinine and creatinine-based equations","volume":"119","author":"P. Delanaye","year":"2011","journal-title":"Nephron Clinical Practice"},{"issue":"5","key":"pone.0313154.ref020","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1053\/j.ajkd.2021.04.016","article-title":"Measurement and Estimation of GFR for Use in Clinical Practice: Core Curriculum 2021","volume":"78","author":"L.A. Inker","year":"2021","journal-title":"Am J Kidney Dis"},{"issue":"5","key":"pone.0313154.ref021","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1053\/j.ajkd.2013.12.006","article-title":"GFR estimation: from physiology to public health","volume":"63","author":"A.S. Levey","year":"2014","journal-title":"American Journal of Kidney Diseases"},{"key":"pone.0313154.ref022","article-title":"Evaluation of novel candidate filtration markers from a global metabolomic discovery for glomerular filtration rate estimation","author":"N. Fino","year":"2023","journal-title":"Kidney International"},{"issue":"2","key":"pone.0313154.ref023","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1177\/1094428112470848","article-title":"Best-practice recommendations for defining, identifying, and handling outliers","volume":"16","author":"H. Aguinis","year":"2013","journal-title":"Organizational Research Methods"},{"key":"pone.0313154.ref024","volume-title":"Robust regression and outlier detection","author":"P.J. Rousseeuw","year":"2005"},{"key":"pone.0313154.ref025","volume-title":"Robust statistics: theory and methods (with R)","author":"R.A. Maronna","year":"2019"},{"issue":"1\u20132","key":"pone.0313154.ref026","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.aca.2011.03.055","article-title":"Review of robust multivariate statistical methods in high dimension","volume":"705","author":"P. Filzmoser","year":"2011","journal-title":"Analytica chimica acta"},{"issue":"480","key":"pone.0313154.ref027","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1198\/016214507000000950","article-title":"Robust linear model selection based on least angle regression","volume":"102","author":"J.A. Khan","year":"2007","journal-title":"Journal of the American Statistical Association"},{"issue":"2","key":"pone.0313154.ref028","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1002\/cem.1195","article-title":"A robust partial least squares regression method with applications","volume":"23","author":"J. Gonz\u00e1lez","year":"2009","journal-title":"Journal of Chemometrics: A Journal of the Chemometrics Society"},{"issue":"10","key":"pone.0313154.ref029","doi-asserted-by":"crossref","first-page":"e109743","DOI":"10.1371\/journal.pone.0109743","article-title":"A new modified CKD-EPI equation for Chinese patients with type 2 diabetes","volume":"9","author":"X. Liu","year":"2014","journal-title":"PloS one"},{"issue":"2","key":"pone.0313154.ref030","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1053\/j.ajkd.2012.07.007","article-title":"GFR estimation using standardized serum cystatin C in Japan","volume":"61","author":"M. Horio","year":"2013","journal-title":"American Journal of Kidney Diseases"},{"issue":"1","key":"pone.0313154.ref031","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1053\/j.ajkd.2013.07.023","article-title":"Estimation of GFR in South Asians: a study from the general population in Pakistan","volume":"63","author":"S. Jessani","year":"2014","journal-title":"Am J Kidney Dis"},{"issue":"12","key":"pone.0313154.ref032","doi-asserted-by":"crossref","first-page":"656","DOI":"10.11622\/smedj.2014181","article-title":"Performance of the CKD-EPI creatinine-cystatin C glomerular filtration rate estimation equations in a multiethnic Asian population","volume":"55","author":"B.W. Teo","year":"2014","journal-title":"Singapore medical journal"},{"key":"pone.0313154.ref033","unstructured":"Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) 2023; Available from: https:\/\/www.tuftsmedicalcenter.org\/research-clinical-trials\/institutes-centers-labs\/chronic-kidney-disease-epidemiology-collaboration\/overview."},{"issue":"3","key":"pone.0313154.ref034","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1373\/clinchem.2018.288092","article-title":"Validation of a metabolite panel for a more accurate estimation of glomerular filtration rate using quantitative LC-MS\/MS","volume":"65","author":"T.A. Freed","year":"2019","journal-title":"Clinical chemistry"},{"issue":"5","key":"pone.0313154.ref035","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1053\/j.ajkd.2020.11.005","article-title":"A new panel-estimated GFR, including \u03b22-microglobulin and \u03b2-trace protein and not including race, developed in a diverse population","volume":"77","author":"L.A. Inker","year":"2021","journal-title":"American Journal of Kidney Diseases"},{"issue":"3","key":"pone.0313154.ref036","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1053\/j.ajkd.2014.04.010","article-title":"Measuring GFR: a systematic review","volume":"64","author":"I. Soveri","year":"2014","journal-title":"Am J Kidney Dis"},{"key":"pone.0313154.ref037","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"T. Hastie","year":"2009"},{"key":"pone.0313154.ref038","first-page":"1","article-title":"Transfer learning under high-dimensional generalized linear models","author":"Y. Tian","year":"2022","journal-title":"Journal of the American Statistical Association"},{"issue":"6","key":"pone.0313154.ref039","doi-asserted-by":"crossref","first-page":"765","DOI":"10.1053\/j.ajkd.2020.05.017","article-title":"The Difference Between Cystatin C- and Creatinine-Based Estimated GFR and Associations With Frailty and Adverse Outcomes: A Cohort Analysis of the Systolic Blood Pressure Intervention Trial (SPRINT)","volume":"76","author":"O.A. Potok","year":"2020","journal-title":"Am J Kidney Dis"},{"issue":"10","key":"pone.0313154.ref040","doi-asserted-by":"crossref","first-page":"100710","DOI":"10.1016\/j.xkme.2023.100710","article-title":"Discordance Between Creatinine-Based and Cystatin C-Based Estimated GFR: Interpretation According to Performance Compared to Measured GFR","volume":"5","author":"Y. Wang","year":"2023","journal-title":"Kidney Med"},{"issue":"2","key":"pone.0313154.ref041","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1053\/j.ajkd.2012.04.012","article-title":"Estimating GFR Among Participants in the Chronic Renal Insufficiency Cohort (CRIC) Study","volume":"60","author":"A.H. Anderson","year":"2012","journal-title":"American Journal of Kidney Diseases"},{"issue":"3","key":"pone.0313154.ref042","first-page":"497","article-title":"Estimating glomerular filtration rate for the full age spectrum from serum creatinine and cystatin C","volume":"32","author":"H. Pottel","year":"2017","journal-title":"Nephrol Dial Transplant"},{"issue":"9","key":"pone.0313154.ref043","doi-asserted-by":"crossref","first-page":"883","DOI":"10.1001\/jama.2022.12407","article-title":"Serum Cystatin C for Estimation of GFR","volume":"328","author":"M.G. Shlipak","year":"2022","journal-title":"JAMA"},{"key":"pone.0313154.ref044","doi-asserted-by":"crossref","unstructured":"Liu, F.T., K.M. Ting, and Z.-H. Zhou. Isolation forest. in 2008 eighth ieee international conference on data mining. 2008. IEEE.","DOI":"10.1109\/ICDM.2008.17"},{"key":"pone.0313154.ref045","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., et al. LOF: identifying density-based local outliers. in Proceedings of the 2000 ACM SIGMOD international conference on Management of data. 2000.","DOI":"10.1145\/342009.335388"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0313154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:35:35Z","timestamp":1733164535000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0313154"}},"subtitle":[],"editor":[{"given":"Andrea","family":"Da Porto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":45,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0313154","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]}}}