[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83403-en":3,"doc-seo-83403-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83403,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction","Cardiovascular disease risk prediction often depends on single-institution data or centrally pooled datasets, which conflicts with privacy regulations that limit sharing patient-level records. Federated learning enables collaborative training while keeping sensitive data at the source, yet faces challenges from heterogeneous datasets. This study presents a federated deep survival approach integrating the Lifelines cohort (148,230 participants) and the Rotterdam Study (10,155 participants). Federated training improved C-statistics versus local training, increasing model performance on both cohorts while preserving privacy.","arXiv :2607 .08595v 1 [ cs .LG] 9 Jul 2026  \nFederated Deep Learning for Privacy-Preserving Cardiovascular  \nDisease Risk Prediction  \nHyunho Mo 1 ,∗ , Djura Smits2 , Mahlet A. Birhanu 1 , Maarten J.G. Leening 1 ,3 ,4 , Daniel Bos 1 ,3 , Pim van der Harst5 , Esther E. Bron 1  \n1 Department of Radiology & Nuclear Medicine, Erasmus MC University Medical Center Rotterdam, Dr. Molewaterplein 40, Rotterdam, 3015 GD, The Netherlands  \n2 Netherlands eScience Center, Matrix THREE, Science Park 402, Amsterdam, 1098 XH, The  \nNetherlands  \n3 Department of Epidemiology, Erasmus MC University Medical Center Rotterdam, Dr. Molewaterplein  \n40, Rotterdam, 3015 GD, The Netherlands  \n4 Department of Cardiology, Erasmus MC University Medical Center Rotterdam, Dr. Molewaterplein 40, Rotterdam, 3015 GD, The Netherlands  \n5 Department of Cardiology, University Medical Center Utrecht, Heidelberglaan 100, Utrecht, 3584 CX, The Netherlands  \n∗ Correspondence: Hyunho Mo, [h.mo@erasmusmc.nl](h.mo@erasmusmc.nl)  \nAbstract  \nCardiovascular disease risk prediction models often rely on data from a single institution or centrally pooled datasets. Extending these models across institutions could be limited by privacy regulations and constraints on sharing patient-level data. Federated learning enables collaborative model development without transferring sensitive patient data, but its application in healthcare remains challenging because datasets often differ in size, population characteristics, and outcome definitions. In this study, we present a federated deep learning approach for privacy-preserving cardiovascular disease risk prediction that integrates two population-based cohorts with different characteristics: Lifelines, including 148,230 participants meeting the study inclusion criteria with self-reported outcomes, and the Rotterdam Study, including a smaller cohort of 10,155 participants with digitally linked clinical outcomes. Model performance was primarily evaluated on the Rotterdam Study because of its complete follow-up. Deep survival models trained using federated learning achieved higher predictive performance than models trained locally without federation. For the Rotterdam Study, the C-statistic increased from 0.728 (95% CI: 0.717–0.739) to 0.739 (95% CI: 0.728–0.749) . For Lifelines, the C-statistic increased from 0.783 (95% CI: 0.775–0.791) to 0.787 (95% CI: 0.780–0.792) . These findings suggest that federated deep learning across heterogeneous cohorts can improve cardiovascular disease risk prediction while preserving the privacy of individual-level patient data  \nKeywords: Federated learning, Cardiovascular disease, Healthcare AI, Deep survival neural networks, Lifelines, Rotterdam Study  \n1 Introduction  \nIn healthcare, patient records contain sensitive health information that is classified as specialcategory personal data under regulatory frameworks such as the General Data Protection Regulation (GDPR), which restricts the sharing of personal data across organizational boundaries (Kaissiset al. , 2021) . Building predictive models that draw on data from multiple institutions is therefore challenging, as pooling individual-level records across sites is often not permitted. Federated learning addresses this challenge by distributing the training process across several nodes, each holding a separate part of the data (McMahan et al. , 2017 ; Kaissis et al. , 2021) . Rather than sharing raw records, each node trains a model on its local data and sends only the resulting model parameter updates, such as learned network weights, to a central server, which aggregates them into a global model (McMahan et al. , 2017) . Since raw data never leave their source, federated learning has gained attention as a practical means to build predictive models across multiple institutions while protecting data privacy (Kaissis et al. , 2021 ; Li et al. , 2025) .  \nOne domain where this capability is particularly valuable is cardiovascular disease (CVD) risk p","cbCaibjcQpe2B7ia","https://ap.wps.com/l/cbCaibjcQpe2B7ia","pdf",423595,5,1,15,"English","en",105,"# Introduction\n## Privacy constraints and federated learning\n## Cardiovascular risk prediction context\n## Deep survival models for time-to-event outcomes","[{\"question\":\"Why is federated learning important for cardiovascular disease risk prediction?\",\"answer\":\"Federated learning allows training across institutions without pooling patient-level records, which is restricted by privacy regulations such as GDPR. It keeps raw data at each site while sharing model updates to build a global model.\"},{\"question\":\"Which cohorts are integrated in the federated deep learning study?\",\"answer\":\"The study integrates two population-based cohorts: Lifelines with 148,230 eligible participants and the Rotterdam Study with 10,155 participants with digitally linked clinical outcomes.\"},{\"question\":\"How does federated learning affect predictive performance compared with local training?\",\"answer\":\"Deep survival models trained with federated learning achieved higher predictive performance than models trained locally without federation. The C-statistic increased for both the Rotterdam Study and Lifelines cohorts.\"}]",1784187277,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"federated-deep-learning-for-privacy-preserving-cardiovascular-disease-risk-prediction","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/federated-deep-learning-for-privacy-preserving-cardiovascular-disease-risk-prediction/83403/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is federated learning important for cardiovascular disease risk prediction?","Question",{"text":76,"@type":77},"Federated learning allows training across institutions without pooling patient-level records, which is restricted by privacy regulations such as GDPR. It keeps raw data at each site while sharing model updates to build a global model.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which cohorts are integrated in the federated deep learning study?",{"text":81,"@type":77},"The study integrates two population-based cohorts: Lifelines with 148,230 eligible participants and the Rotterdam Study with 10,155 participants with digitally linked clinical outcomes.",{"name":83,"@type":74,"acceptedAnswer":84},"How does federated learning affect predictive performance compared with local training?",{"text":85,"@type":77},"Deep survival models trained with federated learning achieved higher predictive performance than models trained locally without federation. The C-statistic increased for both the Rotterdam Study and Lifelines cohorts.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":20,"slug":138},19,"General","general"]