{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T06:47:51Z","timestamp":1790318871365,"version":"4.1.0"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T00:00:00Z","timestamp":1773014400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Cloud-based artificial intelligence (AI) combined with smart-health technology presents a powerful tool to passively monitor disease severity. However, current methods raise privacy concerns as they require transmitting patient data to the cloud. A potential solution is Federated Learning (FL), which only shares the weights of locally trained neural networks (NNs) instead of user data. Here, we simulated an FL system to demonstrate its application for evaluating Parkinson\u2019s disease (PD) severity in a smart-home scenario.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Retrospective data including 89 people with PD wore an accelerometer on the lower-back at home for 7\u202fdays at 18-month intervals over 6\u202fyears. Patient characteristics (age, sex, and body mass index) and clinical measures of PD were additionally collected, including the Movement Disorder Society Unified Parkinson\u2019s Disease Rating Scale (MDS-UPDRS)-Part III. Real-world daily gait measures along with these patient characteristics were used to predict the MDS-UPDRS-III score. For FL, a local model was trained for each participant, and a global model (an aggregation of these local models) was tested on unseen participants.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The performance of a simulated FL system was compared with that of a traditional Machine Learning (ML) approach in which patient data were shared. The traditional ML approach had a mean absolute error (MAE) of 10.43. The global FL model had a similar MAE of 10.22 but was underfitted, and the mean MAE of the local, personalised models was 4.83. Shapley Additive exPlanations (SHAP) analysis showed that while the participants\u2019 age and sex were very important in traditional ML, this was not the case for the local FL models, leading to a decrease in global model performance. Here, we show that reserving a small number of participants from the system and including them in training data for all local models restored the importance of these features and improved global FL performance (MAE\u202f=\u202f9.26) but reduced local performance (MAE\u202f=\u202f6.83).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This exploratory study shows that our proposed approach enables FL to achieve similar accuracy to traditional Machine Learning without sharing any patient data but with costs to the local performance, leading towards a smart-home system that prioritises personalisation and patient privacy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2026.1766599","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:48:16Z","timestamp":1773038896000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Privacy and personalisation: predicting Parkinson\u2019s disease severity from real-world gait with federated learning"],"prefix":"10.3389","volume":"18","author":[{"given":"Chloe","family":"Hinchliffe","sequence":"first","affiliation":[{"name":"Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Hiden","sequence":"additional","affiliation":[{"name":"School of Computing, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Alcock","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"National Institute for Health and Care Research (NIHR) Newcastle Biomedical Research Centre (BRC), Newcastle University and The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachael A.","family":"Lawson","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"National Institute for Health and Care Research (NIHR) Newcastle Biomedical Research Centre (BRC), Newcastle University and The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alison J.","family":"Yarnall","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"National Institute for Health and Care Research (NIHR) Newcastle Biomedical Research Centre (BRC), Newcastle University and The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lynn","family":"Rochester","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"National Institute for Health and Care Research (NIHR) Newcastle Biomedical Research Centre (BRC), Newcastle University and The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Silvia","family":"Del Din","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"National Institute for Health and Care Research (NIHR) Newcastle Biomedical Research Centre (BRC), Newcastle University and The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Watson","sequence":"additional","affiliation":[{"name":"School of Computing, Newcastle University","place":["Newcastle upon Tyne, United Kingdom"]},{"name":"National Institute for Health and Care Research (NIHR) Newcastle Biomedical Research Centre (BRC), Newcastle University and The Newcastle upon Tyne Hospitals NHS Foundation Trust","place":["Newcastle upon Tyne, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,9]]},"reference":[{"key":"ref1","author":"Abadi","year":"2015"},{"key":"ref2","first-page":"5003","article-title":"Federated learning for secure development of AI models for Parkinson\u2019s disease detection using speech from different languages","author":"Arasteh","year":"2023"},{"key":"ref3","year":"2025"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.1016\/S0140-6736(21)00218-X","article-title":"Parkinson\u2019s disease","volume":"397","author":"Bloem","year":"2021","journal-title":"Lancet"},{"key":"ref5","author":"Brendan McMahan","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/MIS.2020.2988604","article-title":"FedHealth: a federated transfer learning framework for wearable healthcare","volume":"35","author":"Chen","year":"2020","journal-title":"IEEE Intell. Syst."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1109\/ICME55011.2023.00122","article-title":"FedDBM: federated digital biomarker for detecting Parkinson\u2019s disease Progress","volume":"2023","author":"Chen","year":"2023","journal-title":"Proc. IEEE Int. Conf. Multimed. Expo."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1016\/j.patter.2024.100945","article-title":"Federated learning for multi-omics: a performance evaluation in Parkinson\u2019s disease","volume":"5","author":"Danek","year":"2024","journal-title":"Patterns"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1186\/S12984-016-0154-5","article-title":"Free-living gait characteristics in ageing and Parkinson\u2019s disease: impact of environment and ambulatory bout length","volume":"13","author":"Del Din","year":"2016","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref10","first-page":"139","article-title":"A federated learning based privacy preserving approach for detecting Parkinson\u2019s disease using deep learning","author":"Dipro","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s12559-024-10332-x","article-title":"Federated learning of XAI models in healthcare: a case study on Parkinson\u2019s disease","volume":"16","author":"Ducange","year":"2024","journal-title":"Cogn. Comput."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1002\/mds.27790","article-title":"Measuring Parkinson\u2019s disease over time: the real-world within-subject reliability of the MDS-UPDRS","volume":"34","author":"Evers","year":"2019","journal-title":"Mov. Disord."},{"key":"ref13","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1002\/MDS.22340","article-title":"Movement disorder society-sponsored revision of the unified Parkinson\u2019s disease rating scale (MDS-UPDRS): scale presentation and clinimetric testing results","volume":"23","author":"Goetz","year":"2008","journal-title":"Mov. Disord."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1621","DOI":"10.1007\/s13042-023-01986-4","article-title":"Assessment of patients with Parkinson\u2019s disease based on federated learning","volume":"15","author":"Guan","year":"2024","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1765220","DOI":"10.1155\/2021\/1765220","article-title":"An investigation into the use and meaning of Parkinson\u2019s disease clinical scale scores","volume":"2021","author":"Hendricks","year":"2021","journal-title":"Parkinsons Dis."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12984-024-01390-1","article-title":"Evaluation of walking activity and gait to identify physical and mental fatigue in neurodegenerative and immune disorders: preliminary insights from the IDEA-FAST feasibility study","volume":"21","author":"Hinchliffe","year":"2024","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref18","first-page":"195","article-title":"Applying federated learning in the detection of freezing of gait in Parkinson\u2019s disease","author":"Jorge","year":"2022"},{"key":"ref19","first-page":"724","author":"Jorge","year":"2024"},{"key":"ref20","author":"Joshi","year":"2023"},{"key":"ref21","author":"Karami","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.3233\/JPD-212581","article-title":"Which neuropsychological tests? Predicting cognitive decline and dementia in Parkinson\u2019s disease in the ICICLE-PD cohort","volume":"11","author":"Lawson","year":"2021","journal-title":"J. Parkinsons Dis."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"2964","DOI":"10.1007\/S00415-013-7037-5","article-title":"Ambulatory activity in incident Parkinson\u2019s: more than meets the eye?","volume":"260","author":"Lord","year":"2013","journal-title":"J. Neurol."},{"key":"ref24","author":"Lundberg","year":"2017"},{"key":"ref25","first-page":"340","author":"Marcilio","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.gaitpost.2012.02.019","article-title":"An enhanced estimate of initial contact and final contact instants of time using lower trunk inertial sensor data","volume":"36","author":"McCamley","year":"2012","journal-title":"Gait Posture"},{"key":"ref27","author":"McMahan","year":"2017"},{"key":"ref28","author":"Ozdayi","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"14352","DOI":"10.1609\/AAAI.V39I13.33572","article-title":"Breaking data silos in Parkinson\u2019s disease diagnosis: an adaptive federated learning approach for privacy-preserving facial expression analysis","volume":"39","author":"Pang","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intellig."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.48550\/arXiv.1201.0490","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","first-page":"163","author":"Reyes","year":"2021"},{"key":"ref32","author":"Sarlas","year":"2023"},{"key":"ref33","author":"Seabold","year":"2010"},{"key":"ref9001","volume-title":"Arch. Neurol","author":"Shulman","year":"2010"},{"key":"ref34","author":"Soumma","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"1301997","DOI":"10.3389\/frai.2024.1301997","article-title":"A multi-center distributed learning approach for Parkinson\u2019s disease classification using the traveling model paradigm","volume":"7","author":"Souza","year":"2024","journal-title":"Front Artif Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3454690","article-title":"Secure federated learning for Parkinson\u2019s disease: non-IID data partitioning and homomorphic encryption strategies","author":"Tanim","year":"2024","journal-title":"IEEE Access."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.21105\/JOSS.01026","article-title":"Pingouin: statistics in Python","volume":"3","author":"Vallat","year":"2018","journal-title":"J. Open Source Softw."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/JOSS.03021","article-title":"Seaborn: statistical data visualization","volume":"6","author":"Waskom","year":"2021","journal-title":"J. Open Source Softw."},{"key":"ref40","year":"2025"},{"key":"ref41","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1212\/WNL.0000000000000066","article-title":"Characterizing mild cognitive impairment in incident Parkinson disease: the ICICLE-PD study","volume":"82","author":"Yarnall","year":"2014","journal-title":"Neurology"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"101006","DOI":"10.1016\/J.PATTER.2024.101006","article-title":"Recent methodological advances in federated learning for healthcare","volume":"5","author":"Zhang","year":"2024","journal-title":"Patterns"}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1766599\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:48:17Z","timestamp":1773038897000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1766599\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,9]]},"references-count":44,"alternative-id":["10.3389\/fnagi.2026.1766599"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2026.1766599","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,9]]},"article-number":"1766599"}}