BACKGROUND AND OBJECTIVES: Research in Multiple Sclerosis (MS) has recently focused on extracting knowledge from real-world clinical data sources. This type of data is more abundant than data produced during clinical trials and potentially more informative about real-world clinical practice. However, this comes at the cost of less curated and controlled data sets. In this work we aim to predict disability progression by optimally extracting information from longitudinal patient data in the real-world setting, with a special focus on the sporadic sampling problem. METHODS: We use machine learning methods suited for patient trajectories modeling, such as recurrent neural networks and tensor factorization. A subset of 6682 patients from the MSBase registry is used. RESULTS: We can predict disability progression of patients in a two-year horizon with an ROC-AUC of 0.85, which represents a 32% decrease in the ranking pair error (1-AUC) compared to reference methods using static clinical features. CONCLUSIONS: Compared to the models available in the literature, this work uses the most complete patient history for MS disease progression prediction and represents a step forward towards AI-assisted precision medicine in MS.

1 Biostat Data Science Institute Hasselt University Diepenbeek Belgium

1 Biostat Data Science Institute Hasselt University Diepenbeek Belgium; Department of Immunology Biomedical Research Institute Hasselt University Diepenbeek 3590 Belgium; Department of Immunology Biomedical Research Institute Hasselt University Diepenbeek 3590 Belgium; I Biostat Data Science Institute Hasselt University Diepenbeek Belgium

Amiri Hospital Sharq Kuwait

Azienda Ospedaliera di Rilievo Nazionale San Giuseppe Moscati Avellino Avellino Italy

Azienda Ospedaliera Universitaria Modena Italy

Azienda Sanitaria Unica Regionale Marche AV3 Macerata Italy

Bakirkoy Education and Research Hospital for Psychiatric and Neurological Diseases Istanbul Turkey

Box Hill Hospital Melbourne Australia

Charles University Prague General University Hospital Prague Czech

CISSS Chaudire Appalache Levis Canada

Cliniques Universitaires Saint Luc Brussels Belgium

Department of Basic Medical Sciences Neuroscience and Sense Organs University of Bari Bari Italy

Department of Neurology Centro Hospitalar Universitario de So Joo and University Fernando Pessoa Porto Portugal

Dept of Rehabilitation mons L Novarese Hospital Moncrivello Italy

Dokuz Eylul University Konak Izmir Turkey

ESAT STADIUS KU Leuven Leuven 3001 Belgium

Garibaldi Hospital Catania Italy

Hospital Clinico San Carlos Madrid Spain

Hospital de Galdakao Usansolo Galdakao Spain

Hospital Germans Trias i Pujol Badalona Spain

Hospital Universitario Donostia San Sebastain Spain

Hospital Universitario Virgen Macarena Sevilla Spain

IRCCS Mondino Foundation Pavia Italy

Isfahan Neurosciences Research Center Isfahan University of Medical Sciences Isfahan Iran

Jewish General Hospital Montreal Canada

KTU Medical Faculty Farabi Hospital Trabzon Turkey

Mayis University Samsun Turkey

Melbourne MS Centre Department of Neurology Royal Melbourne Hospital Melbourne Australia; CORe Department of Medicine University of Melbourne Melbourne Australia

Neuro Rive Sud Quebec Canada

Neurologic Clinic and Policlinic MS Center and Research Center for Clinical Neuroimmunology and Neuroscience Basel University Hospital Basel University of Basel Basel Switzerland

previously at Ospedali Riuniti di Salerno Salerno Italy

Razi Hospital Manouba Tunisia

Rehabilitation and MS Centre Overpelt Hasselt University Hasselt Belgium

University G d'Annunzio Chieti Italy

University Hospital Reina Sofia Cordoba Spain

University Newcastle Newcastle Australia

University of Debrecen Debrecen Hungary

University of Parma Parma Italy

Zuyderland Ziekenhuis Sittard the Netherlands

Comput Methods Programs Biomed. 2022 Jan;213:106479. doi: 10.1016/j.cmpb.2021.106479. PubMed

References provided by Crossref.org

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

Machine-learning-based prediction of disability progression in multiple sclerosis: An observational, international, multi-center study