Paper ID: 2409.01235
MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning
Pedro Mateus (1), Swier Garst (2 and 3), Jing Yu (4 and 5), Davy Cats (2), Alexander G. J. Harms (4), Mahlet Birhanu (4), Marian Beekman (2), P. Eline Slagboom (2), Marcel Reinders (3), Jeroen van der Grond (12), Andre Dekker (1), Jacobus F. A. Jansen (6, 7 and 8), Magdalena Beran (9), Miranda T. Schram (5 and 9), Pieter Jelle Visser (10), Justine Moonen (10 and 11), Mohsen Ghanbari (5), Gennady Roshchupkin (4 and 5), Dina Vojinovic (5), Inigo Bermejo (1), Hailiang Mei (2), Esther E. Bron (4) ((1) Department of Radiation Oncology (Maastro), GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands., (2) Section of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands., (3) Delft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands., (4) Biomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands., (5) Department of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands., (6) Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the Netherlands., (7) Mental Health & Neuroscience Research Institute, Maastricht University, Maastricht, the Netherlands., (8) Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands., (9) Department of Internal Medicine, School for Cardiovascular Diseases (CARIM), Maastricht University, Maastricht, the Netherlands., (10) Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the Netherlands., (11) Amsterdam Neuroscience, Neurodegeneration, Amsterdam, The Netherlands., (12) Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands.)
Biological age scores are an emerging tool to characterize aging by estimating chronological age based on physiological biomarkers. Various scores have shown associations with aging-related outcomes. This study assessed the relation between an age score based on brain MRI images (BrainAge) and an age score based on metabolomic biomarkers (MetaboAge). We trained a federated deep learning model to estimate BrainAge in three cohorts. The federated BrainAge model yielded significantly lower error for age prediction across the cohorts than locally trained models. Harmonizing the age interval between cohorts further improved BrainAge accuracy. Subsequently, we compared BrainAge with MetaboAge using federated association and survival analyses. The results showed a small association between BrainAge and MetaboAge as well as a higher predictive value for the time to mortality of both scores combined than for the individual scores. Hence, our study suggests that both aging scores capture different aspects of the aging process.
Submitted: Sep 2, 2024