Personalized federated learning for predicting disability progression in multiple sclerosis using real-world routine clinical data.
Early 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.
Authors
Pirmani Pirmani, De Brouwer De Brouwer, Arany Arany, Oldenhof Oldenhof, Passemiers Passemiers, Faes Faes, Kalincik Kalincik, Ozakbas Ozakbas, Gouider Gouider, Willekens Willekens, Horakova Horakova, Havrdova Havrdova, Patti Patti, Prat Prat, Lugaresi Lugaresi, Tomassini Tomassini, Grammond Grammond, Cartechini Cartechini, Roos Roos, Boz Boz, Alroughani Alroughani, Amato Amato, Buzzard Buzzard, Lechner-Scott Lechner-Scott, Guimarães Guimarães, Solaro Solaro, Gerlach Gerlach, Soysal Soysal, Kuhle Kuhle, Sanchez-Menoyo Sanchez-Menoyo, Spitaleri Spitaleri, Csepany Csepany, Van Wijmeersch Van Wijmeersch, Ampapa Ampapa, Prevost Prevost, Khoury Khoury, Van Pesch Van Pesch, John John, Maimone Maimone, Weinstock-Guttman Weinstock-Guttman, Laureys Laureys, McCombe McCombe, Blanco Blanco, Altintas Altintas, Al-Asmi Al-Asmi, Garber Garber, Van der Walt Van der Walt, Butzkueven Butzkueven, de Gans de Gans, Rozsa Rozsa, Taylor Taylor, Al-Harbi Al-Harbi, Sas Sas, Rajda Rajda, Gray Gray, Decoo Decoo, Carroll Carroll, Kermode Kermode, Fabis-Pedrini Fabis-Pedrini, Mason Mason, Perez-Sempere Perez-Sempere, Simu Simu, Shuey Shuey, Singhal Singhal, Cauchi Cauchi, Hardy Hardy, Ramanathan Ramanathan, Lalive Lalive, Sirbu Sirbu, Hughes Hughes, Castillo Trivino Castillo Trivino, Peeters Peeters, Moreau Moreau
View on Pubmed