Pirmani, AshkanDe Brouwer, EdwardArany, AdamOldenhof, MartijnPassemiers, AntoineFaes, AxelMoreau, Yves2025-08-252025-08-2520252398-6352https://doi.org/10.1038/s41746-025-01788-8https://hdl.handle.net/20.500.14365/6361Taylor, Bruce/0000-0003-2807-0070Early prediction of disability progression in multiple sclerosis (MS) remains challenging despite its critical importance for therapeutic decision-making. We present the first systematic evaluation of personalized federated learning (PFL) for 2-year MS disability progression prediction, leveraging multi-center real-world data from over 26,000 patients. While conventional federated learning (FL) enables privacy-aware collaborative modeling, it remains vulnerable to institutional data heterogeneity. PFL overcomes this challenge by adapting shared models to local data distributions without compromising privacy. We evaluated two personalization strategies: a novel AdaptiveDualBranchNet architecture with selective parameter sharing, and personalized fine-tuning of global models, benchmarked against centralized and client-specific approaches. Baseline FL underperformed relative to personalized methods, whereas personalization significantly improved performance, with personalized FedProx and FedAVG achieving ROC-AUC scores of 0.8398 +/- 0.0019 and 0.8384 +/- 0.0014, respectively. These findings establish personalization as critical for scalable, privacy-aware clinical prediction models and highlight its potential to inform earlier intervention strategies in MS and beyond.eninfo:eu-repo/semantics/closedAccessArticle10.1038/s41746-025-01788-82-s2.0-105011413182