Blanco García, Francisco JOreiro Villar, NatividadVázquez-García, JorgeMorano Torres, AntonioBalboa-Barreiro, VanesaRodríguez-Valle, IsabelRelaño, SaraVeronese, Nicolade Andrés, María C.Rego-Pérez, I.2026-02-232026-02-232026-02-10Blanco FJ, Oreiro N, Vázquez-García J, et al. Predicting total knee replacement in knee osteoarthritis using a machine learning-guided approach in patients of the Osteoarthritis Initiative (OAI). RMD Open 2026;12:e006476.2056-5933https://hdl.handle.net/2183/47471[Abstract] Objective 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. Methods 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 McNemar tests. A prespecified analysis examined performance by baseline Kellgren-Lawrence (KL) grade (KL 0–1 vs KL ≥2). Results On the test set, classifier AUCs ranged 0.716–0.748, with Elastic Net and XGBoost performing best. The final logistic model fit on the full cohort achieved AUC 0.765 (95% CI 0.736 to 0.793) with acceptable calibration (Brier 0.097). Performance remained robust by disease stage, with higher discrimination in pre-radiographic knees (KL 0–1: AUC 0.827) and moderate discrimination in KL ≥2 (AUC 0.720); decile plots indicated broadly aligned observed versus predicted risks. PRS added modest, statistically significant gains in specificity at several fixed sensitivities without materially changing AUC. Conclusions We present a pragmatic, non-imaging, ML-informed model that predicts TKR with clinically acceptable discrimination and calibration using routinely collected data. This framework provides a practical basis for individualised risk stratification and decision support without reliance on imaging.engAttribution-NonCommercial 4.0 Internationalhttp://creativecommons.org/licenses/by-nc/4.0/journal articleopen access10.1136/rmdopen-2025-006476