{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Blanco FJ"],"funding":["Instituto de Salud Carlos III","Axencia Galega de Innovación","Pfizer Foundation"],"pagination":["e006476"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12911737"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["12(1)"],"pubmed_abstract":["<h4>Objective</h4>To develop a pragmatic model to predict total knee replacement (TKR) in knee osteoarthritis using non-imaging clinical, genetic and lifestyle data with machine learning (ML)-guided feature selection.<h4>Methods</h4>We analysed 3790 Osteoarthritis Initiative participants. Nested ML feature selection on the training set identified 15 informative variables. Classifiers were benchmarked, then a multivariable logistic regression was fit on the full cohort. Performance was summarised by discrimination (area under the curve (AUC) with 95% CI) and calibration (Brier score). To assess the incremental value of genetics, we refit an otherwise identical clinical model excluding the Polygenic Risk Score (PRS) and compared specificity at fixed sensitivities using Bonferroni-adjusted Mc"],"journal":["RMD open"],"pubmed_title":["Predicting total knee replacement in knee osteoarthritis using a machine learning-guided approach in patients of the Osteoarthritis Initiative (OAI)."],"pmcid":["PMC12911737"],"funding_grant_id":["PI22/01165","PI22/01155","PMP22/00101","RD24/0007/0026","IN607A 2021/07","IN606A 2022/048","CPII17/00026","ADVANCE (grant ID#64122119)","PMPTA22/00115","PI17/00210","IN607D 2021/13","PI23/00913","RD21/0002/0009"],"pubmed_authors":["de Andres MC","Balboa-Barreiro V","Relano S","Vazquez-Garcia J","Rego-Perez I","Blanco FJ","Oreiro N","Rodriguez-Valle I","Veronese N","Morano-Torres A"],"additional_accession":[]},"is_claimable":false,"name":"Predicting total knee replacement in knee osteoarthritis using a machine learning-guided approach in patients of the Osteoarthritis Initiative (OAI).","description":"<h4>Objective</h4>To develop a pragmatic model to predict total knee replacement (TKR) in knee osteoarthritis using non-imaging clinical, genetic and lifestyle data with machine learning (ML)-guided feature selection.<h4>Methods</h4>We analysed 3790 Osteoarthritis Initiative participants. Nested ML feature selection on the training set identified 15 informative variables. Classifiers were benchmarked, then a multivariable logistic regression was fit on the full cohort. Performance was summarised by discrimination (area under the curve (AUC) with 95% CI) and calibration (Brier score). To assess the incremental value of genetics, we refit an otherwise identical clinical model excluding the Polygenic Risk Score (PRS) and compared specificity at fixed sensitivities using Bonferroni-adjusted Mc","dates":{"release":"2026-01-01T00:00:00Z","publication":"2026 Feb","modification":"2026-07-16T05:07:46.291Z","creation":"2026-07-10T03:08:52.224Z"},"accession":"S-EPMC12911737","cross_references":{"pubmed":["41667218"],"doi":["10.1136/rmdopen-2025-006476"]}}