{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T04:10:15Z","timestamp":1777349415399,"version":"3.51.4"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T00:00:00Z","timestamp":1666742400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001804","name":"Canada Research Chairs","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001804","id-type":"DOI","asserted-by":"publisher"}]},{"name":"River Fund at Calgary Foundation"},{"DOI":"10.13039\/501100000024","name":"Canadian Institutes of Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009003","name":"Hotchkiss Brain Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009003","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>2025 T1-weighted magnetic resonance imaging scans were used to investigate the effect of sample sizes on FL and TM for brain age prediction. We evaluated models across 18 scenarios varying the number of samples per site (1, 2, 5, 10, and 20) and the number of training rounds (20, 40, and 200).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Our results demonstrate that the TM outperforms FL, for every sample size examined. In the extreme case when each site provided only one sample, FL achieved a mean absolute error (MAE) of 18.9\u2009\u00b1\u20090.13\u00a0years, while the TM achieved a MAE of 6.21\u2009\u00b1\u20090.50\u00a0years, comparable to central learning (MAE\u2009=\u20095.99\u00a0years).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>Although FL is more commonly used, our study demonstrates that TM is the best implementation for small sample sizes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The TM offers new opportunities to apply machine learning models in rare diseases and pediatric research but also allows even small hospitals to contribute small datasets.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocac204","type":"journal-article","created":{"date-parts":[[2022,10,26]],"date-time":"2022-10-26T16:36:46Z","timestamp":1666802206000},"page":"112-119","source":"Crossref","is-referenced-by-count":15,"title":["An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction"],"prefix":"10.1093","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7455-3383","authenticated-orcid":false,"given":"Raissa","family":"Souza","sequence":"first","affiliation":[{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary , Calgary, Alberta, Canada"},{"name":"Hotchkiss Brain Institute, University of Calgary , Calgary, Alberta, Canada"},{"name":"Biomedical Engineering Graduate Program, University of Calgary , Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pauline","family":"Mouches","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary , Calgary, Alberta, Canada"},{"name":"Hotchkiss Brain Institute, University of Calgary , Calgary, Alberta, Canada"},{"name":"Biomedical Engineering Graduate Program, University of Calgary , Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Wilms","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary , Calgary, Alberta, Canada"},{"name":"Hotchkiss Brain Institute, University of Calgary , Calgary, Alberta, Canada"},{"name":"Alberta Children\u2019s Hospital Research Institute, University of Calgary , Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3942-2732","authenticated-orcid":false,"given":"Anup","family":"Tuladhar","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary , Calgary, Alberta, Canada"},{"name":"Hotchkiss Brain Institute, University of Calgary , Calgary, Alberta, Canada"},{"name":"Biomedical Engineering Graduate Program, University of Calgary , Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00f6nke","family":"Langner","sequence":"additional","affiliation":[{"name":"Institute for Diagnostic Radiology and Neuroradiology, Rostock University Medical Center , Rostock, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2556-3224","authenticated-orcid":false,"given":"Nils D","family":"Forkert","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cumming School of Medicine, University of Calgary , Calgary, Alberta, Canada"},{"name":"Hotchkiss Brain Institute, University of Calgary , Calgary, Alberta, Canada"},{"name":"Alberta Children\u2019s Hospital Research Institute, University of Calgary , Calgary, Alberta, Canada"},{"name":"Department of Clinical Neurosciences, Cumming School of Medicine, University of Calgary , Calgary, Alberta, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,10,26]]},"reference":[{"issue":"4","key":"2022121408271793800_ocac204-B1","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1139\/gen-2020-0131","article-title":"Machine learning for precision medicine","volume":"64","author":"Maceachern","year":"2021","journal-title":"Genome"},{"issue":"6","key":"2022121408271793800_ocac204-B2","doi-asserted-by":"crossref","first-page":"062001","DOI":"10.1088\/1741-2552\/abbff2","article-title":"Supervised machine learning tools: a tutorial for clinicians","volume":"17","author":"lo Vercio","year":"2020","journal-title":"J Neural Eng"},{"issue":"3","key":"2022121408271793800_ocac204-B3","doi-asserted-by":"crossref","first-page":"e1001779","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK Biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"},{"issue":"4","key":"2022121408271793800_ocac204-B4","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/jmri.21049","article-title":"The Alzheimer\u2019s disease neuroimaging initiative (ADNI): MRI methods","volume":"27","author":"Jack","year":"2008","journal-title":"J Magn Reson Imaging"},{"key":"2022121408271793800_ocac204-B5","doi-asserted-by":"crossref","first-page":"103424","DOI":"10.1016\/j.jbi.2020.103424","article-title":"Building machine learning models without sharing patient data: a simulation-based analysis of distributed learning by ensembling","volume":"106","author":"Tuladhar","year":"2020","journal-title":"J Biomed Inform"},{"issue":"2","key":"2022121408271793800_ocac204-B6","doi-asserted-by":"crossref","first-page":"852","DOI":"10.21037\/qims-20-595","article-title":"Federated learning: a collaborative effort to achieve better medical imaging models for individual sites that have small labelled datasets","volume":"11","author":"Ng","year":"2021","journal-title":"Quant Imaging Med Surg"},{"issue":"6","key":"2022121408271793800_ocac204-B7","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","article-title":"Secure, privacy-preserving and federated machine learning in medical imaging","volume":"2","author":"Kaissis","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2022121408271793800_ocac204-B8","doi-asserted-by":"publisher","first-page":"3854","DOI":"10.1109\/EMBC46164.2021.9629865","author":"Basodi","year":"2021"},{"issue":"1","key":"2022121408271793800_ocac204-B9","doi-asserted-by":"crossref","first-page":"1953","DOI":"10.1038\/s41598-022-05539-7","article-title":"Federated learning and differential privacy for medical image analysis","volume":"12","author":"Adnan","year":"2022","journal-title":"Sci Rep"},{"key":"2022121408271793800_ocac204-B10","doi-asserted-by":"crossref","first-page":"101765","DOI":"10.1016\/j.media.2020.101765","article-title":"Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results","volume":"65","author":"Li","year":"2020","journal-title":"Med Image Anal"},{"key":"2022121408271793800_ocac204-B11","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1109\/ISBI.2019.8759317","author":"Silva","year":"2019"},{"issue":"8","key":"2022121408271793800_ocac204-B12","doi-asserted-by":"crossref","first-page":"945","DOI":"10.1093\/jamia\/ocy017","article-title":"Distributed deep learning networks among institutions for medical imaging","volume":"25","author":"Chang","year":"2018","journal-title":"J Am Med Inform Assoc"},{"key":"2022121408271793800_ocac204-B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/12.2612728","volume-title":"Medical Imaging 2022: Imaging Informatics for Healthcare, Research, and Applications","author":"Souza","year":"2022"},{"issue":"1","key":"2022121408271793800_ocac204-B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-69250-1","article-title":"Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data","volume":"10","author":"Sheller","year":"2020","journal-title":"Sci Rep"},{"issue":"9","key":"2022121408271793800_ocac204-B15","doi-asserted-by":"crossref","first-page":"2331","DOI":"10.1109\/TMI.2022.3161947","article-title":"Invertible modeling of bidirectional relationships in neuroimaging with normalizing flows: application to brain aging","volume":"41","author":"Wilms","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"issue":"8","key":"2022121408271793800_ocac204-B16","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1002\/hbm.25805","article-title":"Multimodal biological brain age prediction using magnetic resonance imaging and angiography with the identification of predictive regions","volume":"43","author":"Mouches","year":"2022","journal-title":"Hum Brain Mapp"},{"key":"2022121408271793800_ocac204-B17","doi-asserted-by":"crossref","first-page":"103600","DOI":"10.1016\/j.ebiom.2021.103600","article-title":"Machine learning for brain age prediction: introduction to methods and clinical applications","volume":"72","author":"Baecker","year":"2021","journal-title":"eBioMedicine"},{"issue":"2","key":"2022121408271793800_ocac204-B18","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1093\/ije\/dyp394","article-title":"Cohort profile: the study of health in pomerania","volume":"40","author":"Volzke","year":"2011","journal-title":"Int J Epidemiol"},{"key":"2022121408271793800_ocac204-B19","doi-asserted-by":"crossref","first-page":"117012","DOI":"10.1016\/j.neuroimage.2020.117012","article-title":"FastSurfer \u2013 a fast and accurate deep learning based neuroimaging pipeline","volume":"219","author":"Henschel","year":"2020","journal-title":"Neuroimage"},{"issue":"10","key":"2022121408271793800_ocac204-B20","doi-asserted-by":"crossref","first-page":"3113","DOI":"10.1002\/hbm.25837","article-title":"Mind the gap: performance metric evaluation in brain-age prediction","volume":"43","author":"de Lange","year":"2022","journal-title":"Hum Brain Mapp"},{"key":"2022121408271793800_ocac204-B21","volume-title":"Federated Learning on Non-IID Data Silos: An Experimental Study","author":"Li","year":"2021"},{"key":"2022121408271793800_ocac204-B22","first-page":"420","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2021. Lecture Notes in Computer Science.","author":"Souza","year":"2022"},{"key":"2022121408271793800_ocac204-B23","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.neurobiolaging.2019.12.008","article-title":"Estimating age-related changes in in vivo cerebral magnetic resonance angiography using convolutional neural network","volume":"87","author":"Nam","year":"2020","journal-title":"Neurobiol Aging"},{"issue":"11","key":"2022121408271793800_ocac204-B24","doi-asserted-by":"crossref","first-page":"3143","DOI":"10.1002\/hbm.24588","article-title":"Investigating systematic bias in brain age estimation with application to post-traumatic stress disorders","volume":"40","author":"Liang","year":"2019","journal-title":"Hum Brain Mapp"},{"issue":"7","key":"2022121408271793800_ocac204-B25","doi-asserted-by":"crossref","first-page":"1470","DOI":"10.3390\/ijerph15071470","article-title":"The occurrence of 275 rare diseases and 47 rare disease groups in Italy. Results from the National Registry of Rare Diseases","volume":"15","author":"Taruscio","year":"2018","journal-title":"Int J Environ Res Public Health"},{"issue":"5","key":"2022121408271793800_ocac204-B26","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1001\/jamapediatrics.2017.5500","article-title":"Key implications of data sharing in pediatric genomics","volume":"172","author":"Rahimzadeh","year":"2018","journal-title":"JAMA Pediatr"},{"key":"2022121408271793800_ocac204-B27","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/978-3-030-11723-8_9","article-title":"Multi-institutional deep learning modeling without sharing patient data: a feasibility study on brain tumor segmentation","volume":"11383","author":"Sheller","year":"2018","journal-title":"Lect Notes Comput Sci"},{"key":"2022121408271793800_ocac204-B28","doi-asserted-by":"crossref","first-page":"104716","DOI":"10.1016\/j.compbiomed.2021.104716","article-title":"Privacy preserving distributed learning classifiers \u2013 sequential learning with small sets of data","volume":"136","author":"Zerka","year":"2021","journal-title":"Comput Biol Med"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/1\/112\/47829373\/ocac204.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/30\/1\/112\/47829373\/ocac204.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T11:49:36Z","timestamp":1671018576000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/30\/1\/112\/6775041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,26]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,10,26]]},"published-print":{"date-parts":[[2022,12,13]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocac204","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,10,26]]}}}