{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:09:29Z","timestamp":1792793369487,"version":"4.5.0"},"reference-count":61,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T00:00:00Z","timestamp":1625097600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"crossref","award":["766276"],"award-info":[{"award-number":["766276"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Purpose<\/jats:title>\n<jats:p>To facilitate the demonstration of the prognostic value of radiomics, multicenter radiomics studies are needed. Pooling radiomic features of such data in a statistical analysis is however challenging, as they are sensitive to the variability in scanner models, acquisition protocols and reconstruction settings, which is often unavoidable in a multicentre retrospective analysis. A statistical harmonization strategy called ComBat was utilized in radiomics studies to deal with the \u201ccenter-effect\u201d. The goal of the present work was to integrate a transfer learning (TL) technique within ComBat\u2014and recently developed alternate versions of ComBat with improved flexibility (M-ComBat) and robustness (B-ComBat)\u2013to allow the use of a previously determined harmonization transform to the radiomic feature values of new patients from an already known center.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Material and methods<\/jats:title>\n<jats:p>The proposed TL approach were incorporated in the four versions of ComBat (standard, B, M, and B-M ComBat). The proposed approach was evaluated using a dataset of 189 locally advanced cervical cancer patients from 3 centers, with magnetic resonance imaging (MRI) and positron emission tomography (PET) images, with the clinical endpoint of predicting local failure. The impact performance of the TL approach was evaluated by comparing the harmonization achieved using only parts of the data to the reference (harmonization achieved using all the available data). It was performed through three different machine learning pipelines.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>The proposed TL technique was successful in harmonizing features of new patients from a known center in all versions of ComBat, leading to predictive models reaching similar performance as the ones developed using the features harmonized with all the data available.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>The proposed TL approach enables applying a previously determined ComBat transform to new, previously unseen data.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0253653","type":"journal-article","created":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T20:07:13Z","timestamp":1625170033000},"page":"e0253653","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":44,"title":["A transfer learning approach to facilitate ComBat-based harmonization of multicentre radiomic features in new datasets"],"prefix":"10.1371","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5730-4211","authenticated-orcid":true,"given":"Ronrick","family":"Da-ano","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Lucia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ingrid","family":"Masson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronan","family":"Abgral","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joanne","family":"Alfieri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Rousseau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Augustin","family":"Mervoyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caroline","family":"Reinhold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Pradier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ulrike","family":"Schick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitris","family":"Visvikis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Hatt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,7,1]]},"reference":[{"issue":"2","key":"pone.0253653.ref001","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images Are More than Pictures, They Are Data","volume":"278","author":"RJ Gillies","year":"2016","journal-title":"Radiology"},{"issue":"4","key":"pone.0253653.ref002","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information frommedical images using advanced feature analysis","volume":"48","author":"P Lambin","year":"2012","journal-title":"Eur J Cancer"},{"issue":"9","key":"pone.0253653.ref003","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: the process and the challenges","volume":"30","author":"V Kumar","year":"2012","journal-title":"Magn Reson Imaging"},{"issue":"2","key":"pone.0253653.ref004","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images Are More than Pictures, They Are Data","volume":"278","author":"RJ Gillies","year":"2016","journal-title":"Radiology"},{"issue":"1070","key":"pone.0253653.ref005","doi-asserted-by":"crossref","first-page":"20160665","DOI":"10.1259\/bjr.20160665","article-title":"Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures","volume":"90","author":"RT Larue","year":"2017","journal-title":"Br J Radiol"},{"issue":"4","key":"pone.0253653.ref006","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/j.ejca.2011.11.036","article-title":"Radiomics: extracting more information from medical images using advanced feature analysis","volume":"48","author":"P Lambin","year":"2012","journal-title":"Eur J Cancer"},{"issue":"1","key":"pone.0253653.ref007","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1007\/s00259-016-3427-0","article-title":"Characterization of PET\/CT images using texture analysis: the past, the present\u2026 any future?","volume":"44","author":"M Hatt","year":"2017","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"1","key":"pone.0253653.ref008","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1038\/s41598-017-00426-y","article-title":"PET Radiomics in NSCLC: state of the art and a proposal for harmonization of methodology","volume":"7","author":"M Sollini","year":"2017","journal-title":"Sci Rep"},{"issue":"4","key":"pone.0253653.ref009","doi-asserted-by":"crossref","first-page":"041002","DOI":"10.1117\/1.JMI.2.4.041002","article-title":"Quantitative radiomics: impact of stochastic effects on textural feature analysis implies the need for standards","volume":"2","author":"M. J. Nyflot","year":"2015","journal-title":"Journal of medical imaging (Bellingham, Wash.)"},{"issue":"9","key":"pone.0253653.ref010","doi-asserted-by":"crossref","first-page":"3640","DOI":"10.1007\/s00330-017-5302-1","article-title":"Multiregional radiomics features from multiparametric MRI for prediction of MGMT methylation status in glioblastoma multiforme: A multicentre study","volume":"28","author":"ZC Li","year":"2018","journal-title":"Eur Radiol"},{"issue":"3","key":"pone.0253653.ref011","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1016\/j.radonc.2018.03.004","article-title":"Why validation of prognostic models matters?","volume":"127","author":"A Zwanenburg","year":"2018","journal-title":"Radiother Oncol"},{"issue":"12","key":"pone.0253653.ref012","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"P Lambin","year":"2017","journal-title":"Nat Rev Clin Oncol"},{"key":"pone.0253653.ref013","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1016\/j.ebiom.2019.07.049","article-title":"Radiomic analysis for pretreatment prediction of response to neoadjuvant chemotherapy in locally advanced cervical cancer: A multicentre study","volume":"46","author":"C Sun","year":"2019","journal-title":"EBioMedicine"},{"issue":"6","key":"pone.0253653.ref014","doi-asserted-by":"crossref","first-page":"814","DOI":"10.2967\/jnumed.119.228106","article-title":"Pretreatment 18F-FDG PET\/CT Radiomics Predict Local Recurrence in Patients Treated with Stereotactic Body Radiotherapy for Early-Stage Non-Small Cell Lung Cancer: A Multicentric Study","volume":"61","author":"G Dissaux","year":"2020","journal-title":"J Nucl Med"},{"issue":"4","key":"pone.0253653.ref015","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1007\/s00259-018-4231-9","article-title":"External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy","volume":"46","author":"F Lucia","year":"2019","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"pone.0253653.ref016","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1016\/j.ebiom.2019.08.054","article-title":"Multicentric validation of radiomics findings:challenges and opportunities","volume":"47","author":"M Hatt","year":"2019","journal-title":"EBioMedicine"},{"issue":"7","key":"pone.0253653.ref017","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.3109\/0284186X.2010.498437","article-title":"Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters","volume":"49","author":"PE Galavis","year":"2010","journal-title":"Acta Oncol"},{"issue":"11","key":"pone.0253653.ref018","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.2967\/jnumed.115.156927","article-title":"Impact of Image Reconstruction Settings on Texture Features in 18F-FDG PET","volume":"56","author":"J Yan","year":"2015","journal-title":"J Nucl Med"},{"issue":"1","key":"pone.0253653.ref019","doi-asserted-by":"crossref","first-page":"4800","DOI":"10.1038\/s41598-019-41344-5","article-title":"Stability of radiomics features in apparent diffusion coefficient maps from a multi-centre test-retest trial","volume":"9","author":"J Peerlings","year":"2019","journal-title":"Sci Rep"},{"key":"pone.0253653.ref020","doi-asserted-by":"crossref","first-page":"10248","DOI":"10.1038\/s41598-020-66110-w","article-title":"Performance comparison of modified ComBat for harmonization of radiomic features for multicenter studies","volume":"10","author":"R. Da-ano","year":"2020","journal-title":"Sci Rep"},{"issue":"2","key":"pone.0253653.ref021","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1109\/TRPMS.2019.2899538","article-title":"Machine (Deep) Learning Methods for Image Processing and Radiomics","volume":"3","author":"M. Hatt","year":"2019","journal-title":"IEEE Transactions on Radiation and Plasma Medical Sciences"},{"key":"pone.0253653.ref022","article-title":"Harmonization strategies for multicenter radiomics investigations","author":"R Da-Ano","year":"2020","journal-title":"Phys Med Biol"},{"issue":"2","key":"pone.0253653.ref023","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1109\/TRPMS.2019.2893860","article-title":"Creating Robust Predictive Radiomic Models for Data From Independent Institutions Using Normalization","volume":"3","author":"A. Chatterjee","year":"2019","journal-title":"IEEE Transactions on Radiation and Plasma Medical Sciences"},{"issue":"8","key":"pone.0253653.ref024","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.2967\/jnumed.117.199935","article-title":"A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET","volume":"59","author":"F Orlhac","year":"2018","journal-title":"J Nucl Med"},{"key":"pone.0253653.ref025","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1186\/s12859-015-0478-3","article-title":"Removing batch effects from purified plasma cell gene expression microarrays with modified ComBat","volume":"16","author":"CK Stein","year":"2015","journal-title":"BMC Bioinformatics"},{"issue":"4","key":"pone.0253653.ref026","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1093\/bib\/bbs037","article-title":"Batch effect removal methods for microarray gene expression data integration: a survey","volume":"14","author":"C Lazar","year":"2013","journal-title":"Brief Bioinform"},{"issue":"2","key":"pone.0253653.ref027","doi-asserted-by":"crossref","first-page":"e17238","DOI":"10.1371\/journal.pone.0017238","article-title":"Removing batch effects in analysis of expression microarray data: an evaluation of six batch adjustment methods","volume":"6","author":"C Chen","year":"2011","journal-title":"PLoS One"},{"issue":"4","key":"pone.0253653.ref028","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1038\/tpj.2010.57","article-title":"A comparison of batch effect removal methods for enhancement of prediction performance using MAQC-II microarray gene expression data","volume":"10","author":"J Luo","year":"2010","journal-title":"Pharmacogenomics J"},{"key":"pone.0253653.ref029","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/1755-8794-5-23","article-title":"Batch correction of microarray data substantially improves the identification of genes differentially expressed in rheumatoid arthritis and osteoarthritis","volume":"5","author":"P Kupfer","year":"2012","journal-title":"BMC Med Genomics"},{"issue":"1","key":"pone.0253653.ref030","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1093\/biostatistics\/kxj037","article-title":"Adjusting batch effects in microarray expression data using empirical Bayes methods","volume":"8","author":"W. Evan Johnson","year":"2007","journal-title":"Biostatistics"},{"issue":"3","key":"pone.0253653.ref031","doi-asserted-by":"crossref","first-page":"e18202","DOI":"10.1371\/journal.pone.0018202","article-title":"Integrated analysis of multiple microarray datasets identifies a reproducible survival predictor in ovarian cancer","volume":"6","author":"P. A. Konstantinopoulos","year":"2011","journal-title":"PloS one"},{"issue":"5","key":"pone.0253653.ref032","doi-asserted-by":"crossref","first-page":"768","DOI":"10.1007\/s00259-017-3898-7","article-title":"Prediction of outcome using pretreatment 18F-FDG PET\/CT and MRI radiomics in locally advanced cervical cancer treated with chemoradiotherapy","volume":"45","author":"F Lucia","year":"2018","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"6","key":"pone.0253653.ref033","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1109\/TMI.2008.2012036","article-title":"A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET","volume":"28","author":"M Hatt","year":"2009","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0253653.ref034","doi-asserted-by":"crossref","first-page":"632","DOI":"10.1109\/ISBI.2004.1398617","volume-title":"\u201c3D Slicer,\u201d 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821)","author":"S. Pieper","year":"2004"},{"key":"pone.0253653.ref035","unstructured":"Zwanenburg A, Leger S, Valli\u00e8res M, et al., \u201cImage biomarker standardisation initiative-feature definitions,\u201d arXiv preprint arXiv:1612.07003, 2016."},{"issue":"1","key":"pone.0253653.ref036","doi-asserted-by":"crossref","first-page":"10117","DOI":"10.1038\/s41598-017-10371-5","article-title":"Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer","volume":"7","author":"M Valli\u00e8res","year":"2017","journal-title":"Sci Rep"},{"key":"pone.0253653.ref037","volume-title":"DataMining: Practical machine learning tools and techniques","author":"IH Witten","year":"2016"},{"key":"pone.0253653.ref038","unstructured":"Fonti V, and Belitser E. Feature Selection using LASSO. Research Paper in Business Analytics March 2017."},{"issue":"1","key":"pone.0253653.ref039","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine learning"},{"key":"pone.0253653.ref040","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"V. N. Vapnik","year":"1995"},{"issue":"1","key":"pone.0253653.ref041","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross- validation for model selection","volume":"7","author":"S Varma","year":"2006","journal-title":"BMC bioinformatics"},{"key":"pone.0253653.ref042","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/978-3-540-35488-8_6","volume-title":"Feature Extraction: Foundations and Applications Studies in Fuzziness and Soft Computing","author":"TN Lal","year":"2006"},{"issue":"2","key":"pone.0253653.ref043","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1007\/s00259-014-2961-x","article-title":"FDG PET\/CT: EANM procedure guidelines for tumour imaging: version 2.0","volume":"42","author":"R Boellaard","year":"2015","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"8","key":"pone.0253653.ref044","doi-asserted-by":"crossref","first-page":"1344","DOI":"10.1007\/s00259-018-3977-4","article-title":"Feasibility of state of the art PET\/CT systems performance harmonisation","volume":"45","author":"A Kaalep","year":"2018","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"3","key":"pone.0253653.ref045","doi-asserted-by":"crossref","first-page":"469","DOI":"10.2967\/jnumed.119.229724","article-title":"Experimental Multicenter and Multivendor Evaluation of the Performance of PET Radiomic Features Using 3-Dimensionally Printed Phantom Inserts","volume":"61","author":"E Pfaehler","year":"2020","journal-title":"J Nucl Med"},{"issue":"2","key":"pone.0253653.ref046","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1148\/radiol.2019181960","article-title":"Deep Learning-based Image Conversion of CT Reconstruction Kernels Improves Radiomics Reproducibility for Pulmonary Nodules or Masses","volume":"292","author":"J Choe","year":"2019","journal-title":"Radiology"},{"issue":"5","key":"pone.0253653.ref047","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.3390\/cancers13051082","article-title":"Dosimetric Validation of a GAN-Based Pseudo-CT Generation for MRI-Only Stereotactic Brain Radiotherapy","volume":"13","author":"V Bourbonne","year":"2021","journal-title":"Cancers (Basel)"},{"issue":"21","key":"pone.0253653.ref048","doi-asserted-by":"crossref","first-page":"215025","DOI":"10.1088\/1361-6560\/abb31f","article-title":"Intensity non uniformity correction in MR imaging using residual cycle generative adversarial network","volume":"65","author":"X Dai","year":"2020","journal-title":"Phys Med Biol"},{"key":"pone.0253653.ref049","unstructured":"Cackowski S, Barbier E, Dojat M, and Christen T. comBat versus cycleGAN formulti-center MR images harmonization. Proceedings of Machine Learning Research\u2014Under Review:1\u201315, 2021. Paper Submission."},{"key":"pone.0253653.ref050","volume-title":"Standardization of Multicentric Image Datasets with Generative Adversarial Networks","author":"C Hognon","year":"2019"},{"issue":"21","key":"pone.0253653.ref051","doi-asserted-by":"crossref","first-page":"215025","DOI":"10.1088\/1361-6560\/abb31f","article-title":"Intensity non uniformity correction in MR imaging using residual cycle generative adversarial network","volume":"65","author":"X Dai","year":"2020","journal-title":"Phys Med Biol"},{"key":"pone.0253653.ref052","article-title":"Application of a Machine Learning Approach for the Analysis of Clinical and Radiomic Features of Pretreatment [18F]-FDG PET\/CT to Predict Prognosis of Patients with Endometrial Cancer","author":"M Nakajo","year":"2021","journal-title":"Mol Imaging Biol"},{"key":"pone.0253653.ref053","article-title":"Harmonization of radiomic feature distributions: impact on classification of hepatic tissue in CT imaging","author":"H Beaumont","year":"2021","journal-title":"Eur Radiol"},{"key":"pone.0253653.ref054","article-title":"Radiomics of high-resolution computed tomography for the differentiation between cholesteatoma and middle ear inflammation: effects of post-reconstruction methods in a dual-center study","author":"CT Arendt","year":"2020","journal-title":"Eur Radiol"},{"issue":"3","key":"pone.0253653.ref055","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1007\/s00330-020-07174-0","article-title":"Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis","volume":"31","author":"M Ligero","year":"2021","journal-title":"Eur Radiol"},{"issue":"16","key":"pone.0253653.ref056","doi-asserted-by":"crossref","first-page":"7231","DOI":"10.7150\/thno.46428","article-title":"Radiomics Analysis of Computed Tomography helps predict poor prognostic outcome in COVID-19","volume":"10","author":"Q Wu","year":"2020","journal-title":"Theranostics"},{"issue":"7","key":"pone.0253653.ref057","doi-asserted-by":"crossref","first-page":"3449","DOI":"10.1002\/mp.12967","article-title":"Machine learning algorithms for outcome prediction in (chemo)radiotherapy: An empirical comparison of classifiers","volume":"45","author":"TM Deist","year":"2018","journal-title":"Med Phys"},{"key":"pone.0253653.ref058","doi-asserted-by":"crossref","first-page":"675","DOI":"10.3390\/diagnostics11040675","article-title":"Comparison and Fusion of Machine Learning Algorithms for Prospective Validation of PET\/CT Radiomic Features Prognostic Value in Stage II-III Non-Small Cell Lung Cancer","volume":"11","author":"S. Sepehri","year":"2021","journal-title":"Diagnostics"},{"issue":"4","key":"pone.0253653.ref059","doi-asserted-by":"crossref","first-page":"864","DOI":"10.1007\/s00259-018-4231-9","article-title":"External validation of a combined PET and MRI radiomics model for prediction of recurrence in cervical cancer patients treated with chemoradiotherapy","volume":"46","author":"F Lucia","year":"2019","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"3","key":"pone.0253653.ref060","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.radonc.2016.10.002","article-title":"Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital\u2014A real life proof of concept","volume":"121","author":"A Jochems","year":"2016","journal-title":"Radiother Oncol"},{"key":"pone.0253653.ref061","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1200\/CCI.19.00047","article-title":"Systematic Review of Privacy-Preserving Distributed Machine Learning From Federated Databases in Health Care","volume":"4","author":"F Zerka","year":"2020","journal-title":"JCO Clin Cancer Inform"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0253653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,1]],"date-time":"2021-07-01T20:08:10Z","timestamp":1625170090000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0253653"}},"subtitle":[],"editor":[{"given":"Francesco","family":"Bianconi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,7,1]]},"references-count":61,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7,1]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0253653","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,1]]}}}