Hierarchical Personalized Continual Federated Learning for Real Time Risk Prediction of Chronic Diseases

Hierarchical Personalized Continual Federated Learning for Real Time Risk Prediction of Chronic Diseases | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Hierarchical Personalized Continual Federated Learning for Real Time Risk Prediction of Chronic Diseases Abhigyan Ghoshal, Mohammad Armaan Ali, M. Sambath, E. Balraj This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7627809/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The most prevalent global morbidity and mortality is chronic illnesses like cardiovascular diseases, diabetes, and respiratory diseases which require the proper prediction of risks and in a timely manner so as to have preventative measures. Nevertheless, predictive systems in real-time have been found to be severely limited by fragmented healthcare data, patient population heterogeneity, non-independent and identically distributed (non-IID) data distributions, and strict privacy policies that cannot allow direct data sharing. Current centralized systems tend to perform poorly when it comes to generalizing across dissimilar healthcare locations, and traditional federated learning algorithms have a scalability bottleneck, suboptimal communication, inadequate personalization, and susceptibility to data drift with time, rendering them unsuitable to real-world application. To overcome these obstacles, we suggest a Hierarchical Personalized Continual Federated Learning (HiPerC-FL) model of real-time risk prediction of chronic diseases that incorporates multi-modal input of wearable, electronic health records, and imaging data without having to reveal raw patient data. The system uses a hierarchical aggregation topology between edge devices, hospital servers, and global coordinators to reduce the latency and communication and a personalized meta-learning module coupled with client clustering helps to address the impact of data heterogeneity. Moreover, on-device adaptation that happens continuously allows local models to be immune to concept drift, and a causal feature regularizer makes predictions more interpretable and reliable. Secure aggregation, differential privacy, and verifiable audit trails are the means of implementing privacy and governance, and both adhere to clinical standards. Benchmark healthcare simulation Experimental results on benchmark healthcare data show that, compared to baseline federated methods, HiPerC-FL always yields progress of 7–10 percent in predictive accuracy, is 50 percent more cost-effective in communication, and GUI remains stable under extended distribution shifts. This evidence confirms that the given framework proves to be not only effective but also practically deployable to the real-time chronic disease monitoring process, which can serve as a scalable and ethically-acceptable roadmap to the precision of the healthcare provision. Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Mathematics and computing Federated Learning (FL) Federated Averaging (FedAvg) Data privacy Personalized healthcare solutions Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7627809","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":525221111,"identity":"ae90710b-271a-4c14-9500-51bdd96d563b","order_by":0,"name":"Abhigyan Ghoshal","email":"","orcid":"","institution":"Vellore Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Abhigyan","middleName":"","lastName":"Ghoshal","suffix":""},{"id":525221115,"identity":"bdc096f5-b432-48c3-b91a-c0aacc7de638","order_by":1,"name":"Mohammad Armaan Ali","email":"","orcid":"","institution":"Vellore Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"Armaan","lastName":"Ali","suffix":""},{"id":525221117,"identity":"379ccb8a-699e-46f0-82d5-c0c14040805c","order_by":2,"name":"M. Sambath","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYLACxgYGBgP2BoYDYB4zkVokDHgOMBw4QJoWiQQGqDUEgG4D+8NPN3fY1ZlLvjE8/IHBTp6BnRe/TrMDPMbSuWeSJSxn5xgAHZZs2MDMl0BIC4N0bhuzhMHttASgFuYEBmYeAwJa2B//zm2rlzC4eQykpZ4YLQxmQFsOSxjcYD4A1HKYCC2Hecysc88cl9xwJvnAgTMGxw3bCGo53v74du6Oan6D4webP1RUVMvz85/BrwUt4oCK2fCrHwWjYBSMglFADAAA+rZDZcNBOJ4AAAAASUVORK5CYII=","orcid":"","institution":"Vellore Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"M.","middleName":"","lastName":"Sambath","suffix":""},{"id":525221119,"identity":"35525614-9fdd-45d8-9d45-62de7a58f3e7","order_by":3,"name":"E. Balraj","email":"","orcid":"","institution":"Vellore Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"E.","middleName":"","lastName":"Balraj","suffix":""}],"badges":[],"createdAt":"2025-09-16 08:23:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7627809/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7627809/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93086842,"identity":"1c268b1c-b75f-49df-bc9b-506249e7bc51","added_by":"auto","created_at":"2025-10-09 02:40:21","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2621574,"visible":true,"origin":"","legend":"","description":"","filename":"AbigyanSambath.docx","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/c4a8c23712910231009688bb.docx"},{"id":93087072,"identity":"222561f7-f9d3-4dbd-bca6-b70ac773bd70","added_by":"auto","created_at":"2025-10-09 02:40:49","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7244,"visible":true,"origin":"","legend":"","description":"","filename":"b3951600de1843f288b24e3ae1b53b84.json","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/4bd2f2b6f2514dbb9dc6223f.json"},{"id":93086708,"identity":"a88d54e0-56e0-4748-a733-63062d3e577b","added_by":"auto","created_at":"2025-10-09 02:40:05","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":110838,"visible":true,"origin":"","legend":"","description":"","filename":"b3951600de1843f288b24e3ae1b53b841enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/1fd9cf69417d19e9ea071caf.xml"},{"id":93086904,"identity":"33aeca38-5220-4030-bd47-ff976b037219","added_by":"auto","created_at":"2025-10-09 02:40:30","extension":"eps","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":416,"visible":true,"origin":"","legend":"","description":"","filename":"drawingimage1.eps","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/67f4e33e17c76ea65a74fcbc.eps"},{"id":93086703,"identity":"83ab70b6-1797-4674-a9e3-92dedbae127d","added_by":"auto","created_at":"2025-10-09 02:40:05","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1375142,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/71d3fff1d240669c2264f796.jpeg"},{"id":93086795,"identity":"1e268727-0d25-4afd-94ae-ee975545bb2c","added_by":"auto","created_at":"2025-10-09 02:40:13","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":528097,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/2c4ceaac59b7fb60b0bf9952.jpeg"},{"id":93087001,"identity":"87dce0b8-1092-4302-8f85-d02f49cb8393","added_by":"auto","created_at":"2025-10-09 02:40:47","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30551,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/795dd68d825811f35f95e160.png"},{"id":93086689,"identity":"2ebf2993-7169-43fe-9b08-7bf2b865d2f0","added_by":"auto","created_at":"2025-10-09 02:40:03","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22362,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/c228153c385c710de8886472.png"},{"id":93086981,"identity":"32204c5f-1423-4433-b075-bdf16b9d3041","added_by":"auto","created_at":"2025-10-09 02:40:43","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25074,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/dd71fa25a587fb905b7e89c8.png"},{"id":93086979,"identity":"c007a6e8-a75e-4b66-973b-9de0e2395d73","added_by":"auto","created_at":"2025-10-09 02:40:43","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24133,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/53de788b7eff31b0b8812536.png"},{"id":93086880,"identity":"871fd625-f216-49ba-bd5a-ffae0a9ae149","added_by":"auto","created_at":"2025-10-09 02:40:27","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":245717,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/6a94d2c5209282c707156362.jpeg"},{"id":93086824,"identity":"1bcd8477-492c-41eb-92e1-38ef18173e21","added_by":"auto","created_at":"2025-10-09 02:40:19","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":214376,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/eec424138a477fc37222f028.png"},{"id":93086906,"identity":"6995d9a7-66a0-48c4-aa27-a0ebbc8609da","added_by":"auto","created_at":"2025-10-09 02:40:32","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":72927,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/bface5c9270548cc839d1a63.png"},{"id":93086874,"identity":"40a4cc01-dbb3-45ad-8509-47664694c2f3","added_by":"auto","created_at":"2025-10-09 02:40:27","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11026,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/42286e2ae9a3126630f49fb8.png"},{"id":93086686,"identity":"ea047f67-6d5e-47bc-a2b5-40b60a780e42","added_by":"auto","created_at":"2025-10-09 02:40:02","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7423,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/83e25357832601bd78e501f3.png"},{"id":93086896,"identity":"b8c037b9-e84d-4ab7-ad7a-351a6ef5ec5a","added_by":"auto","created_at":"2025-10-09 02:40:30","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8004,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/79cca0e71551a458524db062.png"},{"id":93086934,"identity":"6ccba80f-9fad-4eac-9b85-c6ec146e8ff5","added_by":"auto","created_at":"2025-10-09 02:40:34","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8331,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/7d2b6ead301cef8d014aa6d2.png"},{"id":93086609,"identity":"27056d79-3d47-4f8c-88ee-cbc79f274616","added_by":"auto","created_at":"2025-10-09 02:39:57","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41986,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/f8f2c89f6c9406083a1fbcd1.png"},{"id":93086683,"identity":"11efd4e6-33bc-4537-9af1-698aff0730ad","added_by":"auto","created_at":"2025-10-09 02:40:02","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108039,"visible":true,"origin":"","legend":"","description":"","filename":"b3951600de1843f288b24e3ae1b53b841structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/03d539807afc98328c1d51ae.xml"},{"id":93086789,"identity":"eafafa7c-56be-46e6-93a9-805cd1ad04e2","added_by":"auto","created_at":"2025-10-09 02:40:12","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":122290,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1/737e2d51e5f1e4fbc4e526c6.html"},{"id":98586576,"identity":"74310dc8-23a8-4d24-8a5a-e608a83052c7","added_by":"auto","created_at":"2025-12-19 09:39:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":870840,"visible":true,"origin":"","legend":"","description":"","filename":"AbigyanSambath.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7627809/v1_covered_41ef61e5-4c6a-4374-99f3-764484dbfbbf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Hierarchical Personalized Continual Federated Learning for Real Time Risk Prediction of Chronic Diseases","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Federated Learning (FL), Federated Averaging (FedAvg), Data privacy, Personalized healthcare solutions","lastPublishedDoi":"10.21203/rs.3.rs-7627809/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7627809/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe most prevalent global morbidity and mortality is chronic illnesses like cardiovascular diseases, diabetes, and respiratory diseases which require the proper prediction of risks and in a timely manner so as to have preventative measures. Nevertheless, predictive systems in real-time have been found to be severely limited by fragmented healthcare data, patient population heterogeneity, non-independent and identically distributed (non-IID) data distributions, and strict privacy policies that cannot allow direct data sharing. Current centralized systems tend to perform poorly when it comes to generalizing across dissimilar healthcare locations, and traditional federated learning algorithms have a scalability bottleneck, suboptimal communication, inadequate personalization, and susceptibility to data drift with time, rendering them unsuitable to real-world application. To overcome these obstacles, we suggest a Hierarchical Personalized Continual Federated Learning (HiPerC-FL) model of real-time risk prediction of chronic diseases that incorporates multi-modal input of wearable, electronic health records, and imaging data without having to reveal raw patient data. The system uses a hierarchical aggregation topology between edge devices, hospital servers, and global coordinators to reduce the latency and communication and a personalized meta-learning module coupled with client clustering helps to address the impact of data heterogeneity. Moreover, on-device adaptation that happens continuously allows local models to be immune to concept drift, and a causal feature regularizer makes predictions more interpretable and reliable. Secure aggregation, differential privacy, and verifiable audit trails are the means of implementing privacy and governance, and both adhere to clinical standards. Benchmark healthcare simulation Experimental results on benchmark healthcare data show that, compared to baseline federated methods, HiPerC-FL always yields progress of 7\u0026ndash;10 percent in predictive accuracy, is 50 percent more cost-effective in communication, and GUI remains stable under extended distribution shifts. This evidence confirms that the given framework proves to be not only effective but also practically deployable to the real-time chronic disease monitoring process, which can serve as a scalable and ethically-acceptable roadmap to the precision of the healthcare provision.\u003c/p\u003e","manuscriptTitle":"Hierarchical Personalized Continual Federated Learning for Real Time Risk Prediction of Chronic Diseases","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-08 23:46:22","doi":"10.21203/rs.3.rs-7627809/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cb17cf80-1194-4526-94b9-9befa53d9545","owner":[],"postedDate":"October 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":55812278,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":55812279,"name":"Health sciences/Health care"},{"id":55812280,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-12-19T09:38:24+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-08 23:46:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7627809","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7627809","identity":"rs-7627809","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}