MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning

arXiv - QuanBio - Quantitative Methods Pub Date : 2024-09-02 DOI:arxiv-2409.01235

Pedro MateusDepartment of Radiation Oncology, Swier GarstSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the NetherlandsDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jing YuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Davy CatsSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Alexander G. J. HarmsBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Mahlet BirhanuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Marian BeekmanSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, P. Eline SlagboomSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Marcel ReindersDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jeroen van der GrondDepartment of Radiology, Leiden University Medical Center, Leiden, the Netherlands, Andre DekkerDepartment of Radiation Oncology, Jacobus F. A. JansenDepartment of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the NetherlandsMental Health & Neuroscience Research Institute, Maastricht University, Maastricht, the NetherlandsDepartment of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands, Magdalena BeranDepartment of Internal Medicine, School for Cardiovascular Diseases, Miranda T. SchramDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Internal Medicine, School for Cardiovascular Diseases, Pieter Jelle VisserAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the Netherlands, Justine MoonenAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the NetherlandsAmsterdam Neuroscience, Neurodegeneration, Amsterdam, The Netherlands, Mohsen GhanbariDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Gennady RoshchupkinBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Dina VojinovicDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Inigo BermejoDepartment of Radiation Oncology, Hailiang MeiSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Esther E. BronBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands

{"title":"MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning","authors":"Pedro MateusDepartment of Radiation Oncology, Swier GarstSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the NetherlandsDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jing YuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Davy CatsSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Alexander G. J. HarmsBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Mahlet BirhanuBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Marian BeekmanSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, P. Eline SlagboomSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Marcel ReindersDelft Bioinformatics Lab, Delft University of Technology, Delft, the Netherlands, Jeroen van der GrondDepartment of Radiology, Leiden University Medical Center, Leiden, the Netherlands, Andre DekkerDepartment of Radiation Oncology, Jacobus F. A. JansenDepartment of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the NetherlandsMental Health & Neuroscience Research Institute, Maastricht University, Maastricht, the NetherlandsDepartment of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands, Magdalena BeranDepartment of Internal Medicine, School for Cardiovascular Diseases, Miranda T. SchramDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Internal Medicine, School for Cardiovascular Diseases, Pieter Jelle VisserAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the Netherlands, Justine MoonenAlzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, the NetherlandsAmsterdam Neuroscience, Neurodegeneration, Amsterdam, The Netherlands, Mohsen GhanbariDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Gennady RoshchupkinBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the NetherlandsDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Dina VojinovicDepartment of Epidemiology, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands, Inigo BermejoDepartment of Radiation Oncology, Hailiang MeiSection of Molecular Epidemiology, Department of Biomedical Data Sciences, Leiden University Medical Center, the Netherlands, Esther E. BronBiomedical Imaging Group Rotterdam, Department of Radiology & Nuclear Medicine, Erasmus MC - University Medical Center Rotterdam, Rotterdam, the Netherlands","doi":"arxiv-2409.01235","DOIUrl":null,"url":null,"abstract":"Biological age scores are an emerging tool to characterize aging by\nestimating chronological age based on physiological biomarkers. Various scores\nhave shown associations with aging-related outcomes. This study assessed the\nrelation between an age score based on brain MRI images (BrainAge) and an age\nscore based on metabolomic biomarkers (MetaboAge). We trained a federated deep\nlearning model to estimate BrainAge in three cohorts. The federated BrainAge\nmodel yielded significantly lower error for age prediction across the cohorts\nthan locally trained models. Harmonizing the age interval between cohorts\nfurther improved BrainAge accuracy. Subsequently, we compared BrainAge with\nMetaboAge using federated association and survival analyses. The results showed\na small association between BrainAge and MetaboAge as well as a higher\npredictive value for the time to mortality of both scores combined than for the\nindividual scores. Hence, our study suggests that both aging scores capture\ndifferent aspects of the aging process.","PeriodicalId":501266,"journal":{"name":"arXiv - QuanBio - Quantitative Methods","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Quantitative Methods","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.01235","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

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.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

多队列联合学习显示，基于核磁共振成像和代谢组学的年龄评分可协同预测死亡率

生物年龄分值是一种新兴的工具，它根据生理生物标志物估算计时年龄，从而描述衰老的特征。各种评分都显示与衰老相关的结果有关联。本研究评估了基于脑磁共振成像图像的年龄评分（BrainAge）与基于代谢组生物标记物的年龄评分（MetaboAge）之间的关系。我们训练了一个联合深度学习模型来估计三个队列中的脑年龄。与本地训练的模型相比，联合的 BrainAgemodel 在各队列中的年龄预测误差明显更小。统一队列间的年龄间隔进一步提高了 BrainAge 的准确性。随后，我们使用联合关联分析和生存分析比较了 BrainAge 和 MetaboAge。结果表明，BrainAge 和 MetaboAge 之间的关联很小，而且两个评分相加对死亡时间的预测价值高于单个评分。因此，我们的研究表明，这两个衰老评分反映了衰老过程的不同方面。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

arXiv - QuanBio - Quantitative Methods

自引率

0.00%

发文量