{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:27:58Z","timestamp":1787027278551,"version":"build-2736575974"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"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. Artif. Intell."],"abstract":"<jats:p>Upper Extremity (UE) rehabilitation is crucial for stroke survivors, aiming to improve the use of the paretic UE in everyday activities. However, assessing the effectiveness of these treatments is challenging due to a lack of objective measurement tools. Traditional methods, such as clinician-rated motor ability or patient self-reports, often fail to measure UE performance in real-life settings accurately. Evidence suggests that currently used clinical assessments do not reliably capture actual UE use at home or in the community. This study investigates the application of Convolutional Neural Networks (CNNs) combined with Dense layers using accelerometry data from wrist-worn sensors to classify functional and non-functional UE movements of stroke survivors. Two types of models were developed: one trained on data from individual subjects (intrasubject model) and another trained on data across all subjects (intersubject model). The intrasubject model for the paretic UE achieved an average accuracy of 0.90\u202f\u00b1\u202f0.05, while the intersubject model reached an accuracy of 0.79\u202f\u00b1\u202f0.06. When incorporating signals from the non-paretic arm, the intersubject model\u2019s accuracy improves to 0.88\u202f\u00b1\u202f0.10. Notably, this method utilized raw accelerometry data, eliminating the need for manual feature extraction, which is commonly required in traditional machine learning, and yielded higher accuracy than previously reported methods. This proposed deep learning approach incorporates CNNs with Dense layers, offering a cost-effective and adaptable method for monitoring UE functionality in real-world settings. The results from this study have the potential to inform the development of personalized rehabilitation strategies for stroke survivors, offering valuable insights for clinical practice.<\/jats:p>","DOI":"10.3389\/frai.2025.1547127","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T07:16:01Z","timestamp":1762326961000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing rehabilitation in stroke survivors: a deep learning approach to access upper extremity movement using accelerometry data"],"prefix":"10.3389","volume":"8","author":[{"given":"Tan","family":"Tran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin-Ching","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter S.","family":"Lum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1177\/1545968310370748","article-title":"Kinematic variables quantifying upper-extremity performance after stroke during reaching and drinking from a glass","volume":"25","author":"Alt Murphy","year":"2011","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.3390\/s22041377","article-title":"FL-PMI: federated learning-based person movement identification through wearable devices in smart healthcare systems","volume":"22","author":"Arikumar","year":"2022","journal-title":"Sensors"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1177\/0888439003259415","article-title":"Treatment interventions for the paretic upper limb of stroke survivors: a critical review","volume":"17","author":"Barreca","year":"2003","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1001\/jama.2017.18391","article-title":"Big data and machine learning in health care","volume":"319","author":"Beam","year":"2018","journal-title":"JAMA"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1177\/1747493017711816","article-title":"Agreed definitions and a shared vision for new standards in stroke recovery research: the stroke recovery and rehabilitation roundtable taskforce","volume":"12","author":"Bernhardt","year":"2017","journal-title":"Int. J. Stroke"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4842-4470-8","volume-title":"Building machine learning and deep learning models on Google cloud platform: A comprehensive guide for beginners","author":"Bisong","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1016\/j.jstrokecerebrovasdis.2017.07.004","article-title":"Measuring functional arm movement after stroke using a single wrist-worn sensor and machine learning","volume":"26","author":"Bochniewicz","year":"2017","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"667509","DOI":"10.3389\/fnhum.2021.667509","article-title":"A framework for sensor-based assessment of upper-limb functioning in hemiparesis","volume":"15","author":"David","year":"2021","journal-title":"Front. Hum. Neurosci."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1016\/S1474-4422(21)00252-0","article-title":"Global, regional, and national burden of stroke and its risk factors, 1990\u20132019: a systematic analysis for the global burden of disease study 2019","volume":"20","author":"Feigin","year":"2021","journal-title":"Lancet Neurol."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1472-6947-12-8","article-title":"Predicting sample size required for classification performance","volume":"12","author":"Figueroa","year":"2012","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1116878","DOI":"10.3389\/fphys.2023.1116878","article-title":"Concurrent validity of machine learning-classified functional upper extremity use from accelerometry in chronic stroke","volume":"14","author":"Geed","year":"2023","journal-title":"Front. Physiol."},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1016\/j.csbj.2021.01.028","article-title":"Machine learning applications in microbial ecology, human microbiome studies, and environmental monitoring","volume":"19","author":"Ghannam","year":"2021","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"880","DOI":"10.48550\/arXiv.1604.08880","article-title":"Deep, convolutional, and recurrent models for human activity recognition using wearables","volume":"2016","author":"Hammerla","year":"2016","journal-title":"arXiv"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s12984-023-01140-9","article-title":"The use of machine learning and deep learning techniques to assess proprioceptive impairments of the upper limb after stroke","volume":"20","author":"Hossain","year":"2023","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1016\/j.asoc.2017.09.027","article-title":"Real-time human activity recognition from accelerometer data using convolutional neural networks","volume":"62","author":"Ignatov","year":"2018","journal-title":"Appl. Soft Comput."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1177\/23969873231191304","article-title":"Motor rehabilitation after stroke: European stroke organisation (ESO) consensus-based definition and guiding framework","volume":"8","author":"Kwakkel","year":"2023","journal-title":"Eur. Stroke J."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.jht.2012.06.005","article-title":"Assessment of upper extremity impairment, function, and activity following stroke: foundations for clinical decision making","volume":"26","author":"Lang","year":"2013","journal-title":"J. Hand Ther."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"6110","DOI":"10.3390\/s23136110","article-title":"Application of deep learning algorithm to monitor upper extremity task practice","volume":"23","author":"Li","year":"2023","journal-title":"Sensors"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1177\/1545968320962483","article-title":"Improving accelerometry-based measurement of functional use of the upper extremity after stroke: machine learning versus counts threshold method","volume":"34","author":"Lum","year":"2020","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"106590","DOI":"10.1016\/j.jstrokecerebrovasdis.2022.106590","article-title":"Changes in upper limb capacity and performance in the early and late subacute phase after stroke","volume":"31","author":"Lundquist","year":"2022","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1295132","DOI":"10.3389\/fneur.2023.1295132","article-title":"A deep learning wearable-based solution for continuous at-home monitoring of upper limb goal-directed movements","volume":"14","author":"Nunes","year":"2024","journal-title":"Front. Neurol."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3390\/s16010115","article-title":"Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition","volume":"16","author":"Ordonez","year":"2016","journal-title":"Sensors (Basel)"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/j.medengphy.2015.03.017","article-title":"Use of wearable technology for performance assessment: a validation study","volume":"37","author":"Papi","year":"2015","journal-title":"Med. Eng. Phys."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1109\/titb.2005.856863","article-title":"Activity classification using realistic data from wearable sensors","volume":"10","author":"Parkka","year":"2006","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"952757","DOI":"10.3389\/fphys.2022.952757","article-title":"Classification of functional and non-functional arm use by inertial measurement units in individuals with upper limb impairment after stroke","volume":"13","author":"Pohl","year":"2022","journal-title":"Front. Physiol."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"3624","DOI":"10.48550\/arXiv.2004.03624","article-title":"The relationship between fully connected layers and number of classes for the analysis of retinal images","volume":"2020","author":"Ram","year":"2020","journal-title":"arXiv"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1016\/j.jstrokecerebrovasdis.2014.07.039","article-title":"Predicting daily use of the affected upper extremity 1 year after stroke","volume":"24","author":"Rand","year":"2015","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/JBHI.2016.2636665","article-title":"Deep learning for health informatics","volume":"21","author":"Ravi","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"36026","DOI":"10.1109\/ACCESS.2024.3373910","article-title":"A survey of wearable sensors and machine learning algorithms for automated stroke rehabilitation","volume":"12","author":"Sengupta","year":"2024","journal-title":"IEEE Access"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis","volume":"19","author":"Shen","year":"2017","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1023589","DOI":"10.3389\/fphys.2022.1023589","article-title":"Comparing algorithms for assessing upper limb use with inertial measurement units","volume":"13","author":"Subash","year":"2022","journal-title":"Front. Physiol."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1038\/jcbfm.2011.199","article-title":"Protective effect of delayed remote limb ischemic postconditioning: role of mitochondrial KATP channels in a rat model of focal cerebral ischemic reperfusion injury","volume":"32","author":"Sun","year":"2012","journal-title":"J. Cereb. Blood Flow Metab."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"e10124","DOI":"10.7717\/peerj.10124","article-title":"Convolutional neural network in upper limb functional motion analysis after stroke","volume":"8","author":"Szczesna","year":"2020","journal-title":"PeerJ"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1177\/1545968320909796","article-title":"Machine learning methods predict individual upper-limb motor impairment following therapy in chronic stroke","volume":"34","author":"Tozlu","year":"2020","journal-title":"Neurorehabil. Neural Repair"},{"key":"ref44","author":"Tran","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1359776","DOI":"10.3389\/fdgth.2024.1359776","article-title":"Upper limb movement quality measures: comparing IMUs and optical motion capture in stroke patients performing a drinking task","volume":"6","author":"Unger","year":"2024","journal-title":"Front. Digit. Health"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1016\/j.apmr.2005.01.010","article-title":"Ambulatory monitoring of arm movement using accelerometry: an objective measure of upper-extremity rehabilitation in persons with chronic stroke","volume":"86","author":"Uswatte","year":"2005","journal-title":"Arch. Phys. Med. Rehabil."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1161\/01.str.31.3.662","article-title":"Objective measurement of functional upper-extremity movement using accelerometer recordings transformed with a threshold filter","volume":"31","author":"Uswatte","year":"2000","journal-title":"Stroke"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"3762","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"2017","author":"Vaswani","year":"2017","journal-title":"arXiv"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"877563","DOI":"10.3389\/fphys.2022.877563","article-title":"Using wearable inertial sensors to estimate clinical scores of upper limb movement quality in stroke","volume":"13","author":"Werner","year":"2022","journal-title":"Front. Physiol."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1547127\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T07:16:02Z","timestamp":1762326962000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1547127\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":43,"alternative-id":["10.3389\/frai.2025.1547127"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1547127","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"article-number":"1547127"}}