MétaCan
Menu
Back to cohort
Record W4412631047 · doi:10.1038/s41746-025-01788-8

Personalized federated learning for predicting disability progression in multiple sclerosis using real-world routine clinical data

2025· article· en· W4412631047 on OpenAlexaff
Ashkan Pirmani, Edward De Brouwer, Ádám Arany, Martijn Oldenhof, Antoine Passemiers, Axel Faes, Tomáš Kalinčík, Serkan Özakbaş, Riadh Gouider, Barbara Willekens, Dana Horáková, Eva Havrdová, Francesco Patti, Alexandre Prat, Alessandra Lugaresi, Valentina Tomassini, Pierre Grammond, Elisabetta Cartechini, Izanne Roos, Cavit Boz, Raed Alroughani, Maria Pia Amato, Katherine Buzzard, Jeannette Lechner‐Scott, Joana Guimarães, Claudio Solaro, Oliver Gerlach, Aysun Soysal, Jens Kühle, José Luis Sánchez-Menoyo, Daniele Spitaleri, Tünde Csépány, Bart Van Wijmeersch, Radek Ampapa, Julie Prévost, Samia J. Khoury, Vincent Van Pesch, Nevin John, Davide Maimone, Bianca Weinstock‐Guttman, Guy Laureys, Pamela McCombe, Yolanda Blanco, Ayşe Altıntaş, Abdullah Al‐Asmi, Justin Garber, Anneke van der Walt, Helmut Butzkueven, Koen de Gans, Csilla Rózsa, Bruce Taylor, Talal Al‐Harbi, Attila Sas, Cecília Rajda, Orla Gray, D. Decoo, Allan G. Kermode, Marzena J. Fabis‐Pedrini, Deborah Mason, Ángel Pérez Sempere, Mihaela Simu, Neil Shuey, Bhim Singhal, Marija Cauchi, Todd A. Hardy, Sudarshini Ramanathan, Patrice H. Lalive, Carmen Adella Sîrbu, Stella Hughes, Tamara Castillo‐Triviño, Liesbet M. Peeters, Yves Moreau

Bibliographic record

Venuenpj Digital Medicine · 2025
Typearticle
Languageen
FieldComputer Science
TopicAI in cancer detection
Canadian institutionsCegep de Saint JeromeCentre intégré de santé et de services sociaux de Chaudière-AppalachesUniversité de Montréal
FundersCliniques Universitaires Saint-LucFaculty of Medicine and Health, University of SydneyAllerganEMD SeronoKoç Üniversitesi Translasyonel Tıp Araştırma MerkeziSzegedi TudományegyetemVlaamse regeringUniversiteit HasseltDebreceni EgyetemUniversiteit AntwerpenKoning Boudewijnstichtinglékařská fakulta Univerzity KarlovyTeva Pharmaceutical IndustriesUniversità di BolognaRazi UniversityHunter Medical Research InstituteUniverzita Karlova v PrazeKaradeniz Teknik ÜniversitesiSanofi GenzymeUniversität BaselAgentschap Innoveren en OndernemenKU LeuvenUniversità degli Studi di FirenzeEisaiUniversidade do PortoFonds Wetenschappelijk OnderzoekVšeobecná Fakultní Nemocnice v PrazeBiogenCelgeneKoç ÜniversitesiH. Lundbeck A/SMonash UniversityAlexion PharmaceuticalsEuropean CommissionMultiple Sclerosis International FederationSultan Qaboos UniversitySanofiAmerican University of BeirutBristol-Myers SquibbUniversità di CataniaAmgen
KeywordsMultiple sclerosisReal world dataComputer scienceMedicineData sciencePsychiatry

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.005
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.884
Threshold uncertainty score0.631

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.206
GPT teacher head0.419
Teacher spread0.212 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations7
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuenpj Digital MedicineSame topicAI in cancer detectionFrench-language works237,207