{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T15:38:14Z","timestamp":1789486694788,"version":"build-2803163510"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Epidemiol."],"abstract":"\n Background<\/jats:title>\n The evaluation of binary classifiers under real-world conditions requires metrics that account for the dependence of predictive performance on disease prevalence. Classical accuracy metrics, including the Youden index, condition on the true class and remain invariant to changes in class distribution, making them unable to reflect the practical question of whether a positive classification is trustworthy in a given deployment context.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n The Bayesian Youden Index is derived analytically as a prevalence-dependent extension of the classical Youden index, grounded in the equivalence between Bayesian and classical sensitivity and specificity. Its behavior is characterized across the full prevalence range, and uncertainty in all point estimates is quantified through parametric bootstrap with B\u2009=\u20092,000 replications. The framework is illustrated using HOMA-IR for insulin resistance detection (\n n<\/jats:italic>\n \u2009=\u200993) and is applicable to any binary classification task with a known confusion matrix and operational prevalence.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The Bayesian Youden Index reaches a maximum of 0.913 (95% CI:0.823,0.997) at a prevalence of 0.334 (95% CI:0.027,0.575), compared to the constant classical value of 0.890 (95% CI:0.782,0.978). At the observed prevalence of 0.484 the Bayesian value is 0.898. Two intersection points were identified at which the Bayesian and classical formulations coincide:\n \n \n \n P<\/mml:mi>\n 1<\/mml:mn>\n <\/mml:msub>\n =<\/mml:mo>\n 0.190<\/mml:mn>\n <\/mml:math>\n <\/jats:inline-formula>\n (95% CI:0.118,0.542) and\n \n \n \n P<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msub>\n =<\/mml:mo>\n 0518<\/mml:mn>\n <\/mml:math>\n <\/jats:inline-formula>\n (95% CI:0.504,0.652), defining three distinct prevalence regimes with different implications for classifier deployment. The index exhibits asymmetric behavior across the prevalence range, showing that a classifier's inherent sensitivity-specificity profile can be strategically leveraged through prevalence-aware threshold selection to manage class imbalance without resorting to artificial balancing techniques.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The Bayesian Youden Index positions itself not merely as a measure of statistical fit but as a robust calibration tool that decomposes overall classifier performance into predictive confidence under realistic prevalence conditions. The findings caution against prematurely discarding results from imbalanced datasets or automatically applying balancing methods, advocating instead for a nuanced analysis in which imbalance, mediated by classifier characteristics, can sometimes enhance rather than hinder evaluated performance.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fepid.2026.1839151","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:03:38Z","timestamp":1787724218000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Bayesian Youden index for algorithmic evaluation under class imbalance: mathematical foundations with applications to insulin resistance and diabetes progression"],"prefix":"10.3389","volume":"6","author":[{"given":"Aquiles","family":"Darghan","sequence":"first","affiliation":[{"name":"Faculty of Agricultural Sciences, Universidad Nacional de Colombia","place":["Bogot\u00e1, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ariel Iv\u00e1n","family":"Ruiz-Parra","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Universidad Nacional de Colombia","place":["Bogot\u00e1, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge Eduardo","family":"Caminos","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Universidad Nacional de Colombia","place":["Bogot\u00e1, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nair","family":"Gonz\u00e1lez","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, Universidad Nacional de Colombia","place":["Bogot\u00e1, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Darghan","sequence":"additional","affiliation":[{"name":"Data Science Engineering, Universidad EAN","place":["Bogot\u00e1, Colombia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofia Alexandra","family":"Caminos Cepeda","sequence":"additional","affiliation":[{"name":"School of Medicine, Universidad Pompeu Fabra","place":["Barcelona, Spain"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"B1","volume-title":"Handbook for Designing and Conducting Clinical and Translational Research","author":"Eltorai","year":"2023"},{"key":"B2","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-1-59745-448-3_15","article-title":"Hyperinsulinemic-euglycemic clamp to assess insulin sensitivity in vivo","volume":"560","author":"Kim","year":"2009","journal-title":"Methods Mol Biol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3390\/medicina61010083","article-title":"Identification of interactive genetic loci linked to insulin resistance in metabolic syndrome \u2014 an update","volume":"61","author":"Elfaki","year":"2025","journal-title":"Medicina (B Aires)"},{"key":"B4","doi-asserted-by":"publisher","first-page":"36","DOI":"10.4239\/wjd.v1.i2.36","article-title":"Surrogate markers of insulin resistance: a review","volume":"1","author":"Singh","year":"2010","journal-title":"World J Diabetes"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13098-021-00679-2","article-title":"Indirect insulin resistance indices and their cut-off values for the prediction of post-transplantation diabetes mellitus in kidney transplant recipients","volume":"13","author":"Sokooti","year":"2021","journal-title":"Diabetol Metab Syndr"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1343641","DOI":"10.3389\/fendo.2024.1343641","article-title":"Surrogate indices of insulin resistance using the Matsuda index as reference in adult men \u2014 a computational approach","volume":"15","author":"Malag\u00f3n-Soriano","year":"2024","journal-title":"Front Endocrinol"},{"key":"B7","volume-title":"Bayesian Logical Data Analysis for the Physical Sciences: A Comparative Approach with Mathematica Support","author":"Gregory","year":"2010"},{"key":"B8","doi-asserted-by":"publisher","first-page":"109835","DOI":"10.1016\/j.patcog.2023.109835","article-title":"Convgen: a convex space learning approach for deep-generative oversampling and imbalanced classification of small tabular datasets","volume":"145","author":"Schultz","year":"2023","journal-title":"Pattern Recognit"},{"key":"B9","doi-asserted-by":"publisher","first-page":"62","DOI":"10.3109\/02813432.2014.909204","article-title":"A home-based method for the detection of impaired glucose tolerance in hypertensive primary care patients","volume":"32","author":"Zand\u00e9n","year":"2014","journal-title":"Scand J Prim Health Care"},{"key":"B10","doi-asserted-by":"publisher","first-page":"7637","DOI":"10.1039\/d5sc00270b","article-title":"A review of machine learning methods for imbalanced data challenges in chemistry","volume":"16","author":"Jiang","year":"2025","journal-title":"Chem Sci"},{"key":"B11","first-page":"21","article-title":"Estimation of sensitivity and specificity for clustered data","volume":"35","author":"Gen\u00e7","year":"2005","journal-title":"Turk J Med Sci"},{"key":"B12","doi-asserted-by":"crossref","DOI":"10.1002\/9781119942412","volume-title":"Bayesian Biostatistics","author":"Lesaffre","year":"2012"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1552","DOI":"10.1136\/bmj.308.6943.1552","article-title":"Diagnostic tests 1: sensitivity and specificity","volume":"308","author":"Altman","year":"1994","journal-title":"Br Med J"},{"key":"B14","doi-asserted-by":"publisher","first-page":"6086","DOI":"10.1038\/s41598-024-56706-x","article-title":"Evaluation metrics and statistical tests for machine learning","volume":"14","author":"Rainio","year":"2024","journal-title":"Sci Rep"},{"key":"B15","doi-asserted-by":"publisher","first-page":"479","DOI":"10.7197\/223.v39i29491.316368","article-title":"Assessment of the relationship between insulin resistance, atherogenic index of plasma and white blood cell count: a data mining study","volume":"39","author":"Do\u011fan","year":"2017","journal-title":"Cumhuriyet Med J"},{"key":"B16","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/1472-6823-13-47","article-title":"Insulin resistance (HOMA-IR) cut-off values and the metabolic syndrome in a general adult population: effect of gender and age: EPIRCE cross-sectional study","volume":"13","author":"Gayoso-Diz","year":"2013","journal-title":"BMC Endocr Disord"},{"key":"B17","first-page":"1","article-title":"Detection of Parkinson's Disease by employing boosting algorithms","volume-title":"Proceedings of 2021 Joint 10th ICIEV and 5th icIVPR","author":"Nishat","year":"2021"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2957","DOI":"10.1002\/sim.9396","article-title":"Utility based approach in individualized optimal dose selection using machine learning methods","volume":"41","author":"Li","year":"2022","journal-title":"Stat Med"},{"key":"B19","volume-title":"Bayesian Methods in reliability","author":"Shemyakin","year":"2017"},{"key":"B20","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1109\/TSMCC.2008.919172","article-title":"Pareto-based multiobjective machine learning: an overview and case studies","volume":"38","author":"Jin","year":"2008","journal-title":"IEEE Trans Syst Man Cybern C Appl Rev"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.3390\/math12101425","article-title":"Eigenvalue distributions in random confusion matrices: applications to machine learning evaluation","volume":"12","author":"Olaniran","year":"2024","journal-title":"Math"},{"key":"B22","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/BF02127699","article-title":"Barycentric coordinates for convex polytopes","volume":"6","author":"Warren","year":"1996","journal-title":"Adv Comput Math"},{"key":"B23","doi-asserted-by":"crossref","DOI":"10.1007\/978-94-009-4109-0","volume-title":"The Statistical Analysis of Compositional Data","author":"Aitchison","year":"1986"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.26488\/IEJ.12.10.1202","article-title":"Machine learning and class imbalance: a literature survey","volume":"12","author":"Narwane","year":"2019","journal-title":"Ind Eng J"},{"key":"B25","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s13040-021-00244-z","article-title":"The Matthews correlation coefficient (MCC) is more reliable than balanced accuracy, bookmaker informedness, and markedness in two-class confusion matrix evaluation","volume":"14","author":"Chicco","year":"2021","journal-title":"BioData Min"},{"key":"B27","doi-asserted-by":"publisher","first-page":"e0291908","DOI":"10.1371\/journal.pone.0291908","article-title":"Challenges in the real world use of classification accuracy metrics: from recall and precision to the Matthews correlation coefficient","volume":"18","author":"Foody","year":"2023","journal-title":"PLoS One"},{"key":"B28","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1080\/01621459.1987.10478410","article-title":"Better bootstrap confidence intervals","volume":"82","author":"Efron","year":"1987","journal-title":"J Am Stat Assoc"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.2147\/DMSO.S449955","article-title":"Risk prediction of diabetes progression using big data mining with multifarious physical examination indicators","volume":"17","author":"Chen","year":"2024","journal-title":"Diabetes Metab Syndr Obes"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1455442","DOI":"10.3389\/fdata.2025.1455442","article-title":"Impact of imbalanced features on large datasets","volume":"8","author":"Albattah","year":"2025","journal-title":"Front Big Data"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1016\/S0895-4356(03)00177-X","article-title":"The diagnostic odds ratio: a single indicator of test performance","volume":"56","author":"Glas","year":"2003","journal-title":"J Clin Epidemiol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1749570","DOI":"10.3389\/fdgth.2026.1749570","article-title":"A refined SMOTE-ENN optimization method based on machine learning for heart rate variability data classification","volume":"8","author":"Zhang","year":"2026","journal-title":"Front Digit Health"},{"key":"B33","first-page":"42","article-title":"A study of the factors considered when choosing an appropriate data mining algorithm","volume":"4","author":"Chikohora","year":"2014","journal-title":"Int J Soft Comput Eng"}],"container-title":["Frontiers in Epidemiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fepid.2026.1839151\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T13:13:07Z","timestamp":1789477987000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fepid.2026.1839151\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":33,"alternative-id":["10.3389\/fepid.2026.1839151"],"URL":"https:\/\/doi.org\/10.3389\/fepid.2026.1839151","relation":{},"ISSN":["2674-1199"],"issn-type":[{"value":"2674-1199","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1839151"}}