Multitarget brain implants enable generalized decoding of Parkinson’s disease symptoms from chronic home recordings

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract Adaptive deep brain stimulation (aDBS) offers unprecedented precision in the treatment of Parkinson’s disease. Current aDBS control algorithms depend on brain signal biomarkers, such as basal ganglia oscillatory activity in the beta (8-30 Hz) range. Even after extensive optimization through a specialized medical team, about one third of patients may remain ineligible for aDBS due to insufficient biomarker fidelity. Moreover, while the marker broadly correlates with disease severity, it does not recognize how specific symptoms independently fluctuate over time. A concept to address these shortcomings is to rely on machine learning based brain signal decoding. Here, we trained decoders on over 500 hours of invasive multisite recordings from cortex and deep brain targets to predict the wearable based estimates of PD symptoms and side-effects without patient individual training. Recordings were streamed from brain implants while patients were at home on their usual antiparkinsonian treatment. The resulting models robustly outperformed individually defined beta activity, while providing three major conceptual advances: they performed even in patients without a basal ganglia beta rhythm, generalized across patients without requiring retraining or adaptation and robustly and differentially and simultaneously decoded the severity of bradykinesia, tremor and dyskinesia. In a proof-of-concept simulation, we demonstrate how these models could be used to steer stimulation fields dynamically to predefined symptom-response brain networks. This fusion between adaptive and connectomic DBS may define when to stimulate which brain circuit for optimal symptom-specific control in real-time and pave the way for a new generation of fully automatized symptom-specific neuromodulation approaches.
Full text 17,846 characters · extracted from preprint-html · click to expand
Multitarget brain implants enable generalized decoding of Parkinson’s disease symptoms from chronic home recordings | 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 Multitarget brain implants enable generalized decoding of Parkinson’s disease symptoms from chronic home recordings Wolf-Julian Neumann, Timon Merk, Maria Olaru, Nanditha Rajamani, and 13 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9125364/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Adaptive deep brain stimulation (aDBS) offers unprecedented precision in the treatment of Parkinson’s disease. Current aDBS control algorithms depend on brain signal biomarkers, such as basal ganglia oscillatory activity in the beta (8-30 Hz) range. Even after extensive optimization through a specialized medical team, about one third of patients may remain ineligible for aDBS due to insufficient biomarker fidelity. Moreover, while the marker broadly correlates with disease severity, it does not recognize how specific symptoms independently fluctuate over time. A concept to address these shortcomings is to rely on machine learning based brain signal decoding. Here, we trained decoders on over 500 hours of invasive multisite recordings from cortex and deep brain targets to predict the wearable based estimates of PD symptoms and side-effects without patient individual training. Recordings were streamed from brain implants while patients were at home on their usual antiparkinsonian treatment. The resulting models robustly outperformed individually defined beta activity, while providing three major conceptual advances: they performed even in patients without a basal ganglia beta rhythm, generalized across patients without requiring retraining or adaptation and robustly and differentially and simultaneously decoded the severity of bradykinesia, tremor and dyskinesia. In a proof-of-concept simulation, we demonstrate how these models could be used to steer stimulation fields dynamically to predefined symptom-response brain networks. This fusion between adaptive and connectomic DBS may define when to stimulate which brain circuit for optimal symptom-specific control in real-time and pave the way for a new generation of fully automatized symptom-specific neuromodulation approaches. Health sciences/Medical research/Translational research Health sciences/Biomarkers/Diagnostic markers Biological sciences/Neuroscience/Diseases of the nervous system/Parkinson's disease Full Text Additional Declarations Yes there is potential Competing Interest. A.H. reports lecture fees for Boston Scientific, is a consultant for Modulight.bio, was a consultant for FxNeuromodulation and Abbott in recent years and serves as a co-inventor on a patent granted to Charité University Medicine Berlin that covers multisymptom DBS fiberfiltering and an automated DBS parameter suggestion algorithm unrelated to this work (patent #LU103178). Supplementary Files SupplementaryVideo1.mp4 Time-resolved symptom tract activation and stimulation profiles Cite Share Download PDF Status: Under Review 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-9125364","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":631221010,"identity":"f0390ada-d483-49b0-9459-e2ab63df2cd5","order_by":0,"name":"Wolf-Julian Neumann","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYBACxgbmhgNIfBsGAyB5ACyDUwsjipY0iJYDeLSgSx0Ga2HAp4V5RmLjgZ87GPL4JbITPxfuOC9vzn724eEPFQyy/bjsmJHYcLD3DEOx5IzczdIzz9w23NmTbnDgwBkG45k4rAFpOcDbxpC44UbuBmnettsJBgfSGA4cBIkcwK3l4F+ggv03cjf/5m07l2Bw/hlQyz+gCB4th8G2SORuA9pyIMHgBsiWBqAILr/0PGw4LNsmkTjjzNtt1rxtyYYbbgBtOXNMwngGDlsM25MPf3zbZpPY3567+TZvm528wfk05g8VNTay/Ti8bwgRl8CQwBSBAXmcMqNgFIyCUTAKYAAAeGpqy1gxwe0AAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-6758-9708","institution":"Movement Disorder and Neuromodulation Unit, Department of Neurology, Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Unive","correspondingAuthor":true,"prefix":"","firstName":"Wolf-Julian","middleName":"","lastName":"Neumann","suffix":""},{"id":631221011,"identity":"a34da0d9-8df1-4822-b117-5952b0200a82","order_by":1,"name":"Timon Merk","email":"","orcid":"","institution":"Charité – Universitätsmedizin Berlin","correspondingAuthor":false,"prefix":"","firstName":"Timon","middleName":"","lastName":"Merk","suffix":""},{"id":631221012,"identity":"806c0d96-13bf-4a77-ad65-52e833cc5dcf","order_by":2,"name":"Maria Olaru","email":"","orcid":"","institution":"University of California San Francisco","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"","lastName":"Olaru","suffix":""},{"id":631221014,"identity":"6e69e8c6-4f41-492d-87c4-e66a5345b51a","order_by":3,"name":"Nanditha Rajamani","email":"","orcid":"https://orcid.org/0000-0002-2511-9839","institution":"Harvard University","correspondingAuthor":false,"prefix":"","firstName":"Nanditha","middleName":"","lastName":"Rajamani","suffix":""},{"id":631221017,"identity":"a649b2a8-89e2-4cd3-8107-cec91d7123b5","order_by":4,"name":"Patricia Zvarova","email":"","orcid":"","institution":"University Hospital Cologne","correspondingAuthor":false,"prefix":"","firstName":"Patricia","middleName":"","lastName":"Zvarova","suffix":""},{"id":631221018,"identity":"17dc8b20-d44f-44a2-9dcc-68dc6ff9d0a8","order_by":5,"name":"Erblina Purelku","email":"","orcid":"","institution":"Charité – Universitätsmedizin Berlin","correspondingAuthor":false,"prefix":"","firstName":"Erblina","middleName":"","lastName":"Purelku","suffix":""},{"id":631221019,"identity":"9cebe73a-e8d0-473c-bee6-cd659b870c18","order_by":6,"name":"Zixiao Yin","email":"","orcid":"","institution":"Beijing Tiantan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Zixiao","middleName":"","lastName":"Yin","suffix":""},{"id":631221020,"identity":"eed45579-1f17-4fc8-99f8-08bf5fe4071b","order_by":7,"name":"Richard Köhler","email":"","orcid":"https://orcid.org/0000-0002-5219-1289","institution":"Movement Disorder and Neuromodulation Unit, Department of Neurology, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Unive","correspondingAuthor":false,"prefix":"","firstName":"Richard","middleName":"","lastName":"Köhler","suffix":""},{"id":631221021,"identity":"22ad0a8b-f721-4dd7-bb3f-e399b0907b75","order_by":8,"name":"Jojo Vanhoecke","email":"","orcid":"https://orcid.org/0000-0002-9857-1519","institution":"Movement Disorder and Neuromodulation Unit, Department of Neurology, Charité – Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt Unive","correspondingAuthor":false,"prefix":"","firstName":"Jojo","middleName":"","lastName":"Vanhoecke","suffix":""},{"id":631221022,"identity":"d27ee5ca-98e9-43c6-8a5f-723f0218cba5","order_by":9,"name":"Ashwini Oswal","email":"","orcid":"","institution":"MRC Brain Networks Dynamics Unit, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK","correspondingAuthor":false,"prefix":"","firstName":"Ashwini","middleName":"","lastName":"Oswal","suffix":""},{"id":631221023,"identity":"fa6406e9-3def-423c-8a4d-7ac6c3eb6067","order_by":10,"name":"Guanyu Zhu","email":"","orcid":"","institution":"Beijing Tiantan Hospital","correspondingAuthor":false,"prefix":"","firstName":"Guanyu","middleName":"","lastName":"Zhu","suffix":""},{"id":631221024,"identity":"b945060c-7af2-4d41-afba-45423b36674f","order_by":11,"name":"Jianguo Zhang","email":"","orcid":"https://orcid.org/0000-0002-0009-0574","institution":"Capital Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jianguo","middleName":"","lastName":"Zhang","suffix":""},{"id":631221025,"identity":"46784ca6-8ce0-4545-879c-d10de12afb65","order_by":12,"name":"Reza Abbasi-Asl","email":"","orcid":"","institution":"University of California San Francisco","correspondingAuthor":false,"prefix":"","firstName":"Reza","middleName":"","lastName":"Abbasi-Asl","suffix":""},{"id":631221026,"identity":"846415d5-9a58-47cf-987c-c304a59c5bb3","order_by":13,"name":"Amelia Hahn","email":"","orcid":"","institution":"University of California, San Francisco","correspondingAuthor":false,"prefix":"","firstName":"Amelia","middleName":"","lastName":"Hahn","suffix":""},{"id":631221027,"identity":"9c1b676a-7238-406a-a868-a3206c6a3c04","order_by":14,"name":"Simon Little","email":"","orcid":"https://orcid.org/0000-0001-6249-6230","institution":"University of California, San Francisco","correspondingAuthor":false,"prefix":"","firstName":"Simon","middleName":"","lastName":"Little","suffix":""},{"id":631221028,"identity":"29775199-2e1e-4fc7-8054-90463e2303db","order_by":15,"name":"Andreas Horn","email":"","orcid":"","institution":"University Hospital Cologne","correspondingAuthor":false,"prefix":"","firstName":"Andreas","middleName":"","lastName":"Horn","suffix":""},{"id":631221029,"identity":"8c1d4a17-92e1-419f-bc37-7b38c0ffb186","order_by":16,"name":"Philip Starr","email":"","orcid":"https://orcid.org/0000-0003-2733-4003","institution":"University of California","correspondingAuthor":false,"prefix":"","firstName":"Philip","middleName":"","lastName":"Starr","suffix":""}],"badges":[],"createdAt":"2026-03-14 23:25:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9125364/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9125364/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109297864,"identity":"2d5edd30-c091-4c5c-b464-3f631316c974","added_by":"auto","created_at":"2026-05-15 09:07:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1464282,"visible":true,"origin":"","legend":"Article File","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9125364/v1_covered_5ed57202-962f-4a5a-9d82-49fa590aa30c.pdf"},{"id":109287146,"identity":"5139544a-2d09-46bd-ab98-0346c4b95701","added_by":"auto","created_at":"2026-05-15 02:46:05","extension":"mp4","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":24204551,"visible":true,"origin":"","legend":"Time-resolved symptom tract activation and stimulation profiles","description":"","filename":"SupplementaryVideo1.mp4","url":"https://assets-eu.researchsquare.com/files/rs-9125364/v1/f0491fd8b93067b6bb611588.mp4"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nA.H. reports lecture fees for Boston Scientific, is a consultant for Modulight.bio, was a consultant for FxNeuromodulation and Abbott in recent years and serves as a co-inventor on a patent granted to Charité University Medicine Berlin that covers multisymptom DBS fiberfiltering and an automated DBS parameter suggestion algorithm unrelated to this work (patent #LU103178).","formattedTitle":"Multitarget brain implants enable generalized decoding of Parkinson’s disease symptoms from chronic home recordings","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9125364/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9125364/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Adaptive deep brain stimulation (aDBS) offers unprecedented precision in the treatment of Parkinson’s disease. Current aDBS control algorithms depend on brain signal biomarkers, such as basal ganglia oscillatory activity in the beta (8-30 Hz) range. Even after extensive optimization through a specialized medical team, about one third of patients may remain ineligible for aDBS due to insufficient biomarker fidelity. Moreover, while the marker broadly correlates with disease severity, it does not recognize how specific symptoms independently fluctuate over time. A concept to address these shortcomings is to rely on machine learning based brain signal decoding. Here, we trained decoders on over 500 hours of invasive multisite recordings from cortex and deep brain targets to predict the wearable based estimates of PD symptoms and side-effects without patient individual training. Recordings were streamed from brain implants while patients were at home on their usual antiparkinsonian treatment. The resulting models robustly outperformed individually defined beta activity, while providing three major conceptual advances: they performed even in patients without a basal ganglia beta rhythm, generalized across patients without requiring retraining or adaptation and robustly and differentially and simultaneously decoded the severity of bradykinesia, tremor and dyskinesia. In a proof-of-concept simulation, we demonstrate how these models could be used to steer stimulation fields dynamically to predefined symptom-response brain networks. This fusion between adaptive and connectomic DBS may define when to stimulate which brain circuit for optimal symptom-specific control in real-time and pave the way for a new generation of fully automatized symptom-specific neuromodulation approaches.","manuscriptTitle":"Multitarget brain implants enable generalized decoding of Parkinson’s disease symptoms from chronic home recordings","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-15 02:46:01","doi":"10.21203/rs.3.rs-9125364/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"785be06e-e91f-4597-8f3e-6605deb9ce22","owner":[],"postedDate":"May 15th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":67184730,"name":"Health sciences/Medical research/Translational research"},{"id":67184731,"name":"Health sciences/Biomarkers/Diagnostic markers"},{"id":67184732,"name":"Biological sciences/Neuroscience/Diseases of the nervous system/Parkinson's disease"}],"tags":[],"updatedAt":"2026-05-15T02:46:01+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-15 02:46:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9125364","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9125364","identity":"rs-9125364","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-30T02:00:01.510937+00:00
License: CC-BY-4.0