{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:41:18Z","timestamp":1784738478723,"version":"3.55.0"},"reference-count":32,"publisher":"IMR Press","issue":"1","license":[{"start":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T00:00:00Z","timestamp":1769385600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Integr. Neurosci."],"abstract":"<jats:p>Background: Parkinson\u2019s Disease (PD) is a neurological condition characterized by motor symptoms that fluctuate throughout the day depending on medication. Continuous and objective monitoring is essential, but conventional clinical assessments are episodic and subjective, while wearable and video-based solutions may raise privacy concerns. This study aims to develop a real-time, privacy-preserving deep learning framework that utilizes 2D skeleton pose data to simultaneously classify medication states (ON or OFF) and continuously estimate motor symptom severity. Methods: To enable privacy-preserving and real-time monitoring of Parkinson\u2019s motor fluctuations, a Multi-Scale Temporal Attention-Transformer Network (MS-TATNet) was developed based on 2D skeleton pose data collected from the REal-world Mobility Activities in Parkinson\u2019s disease dataset (REMAP) dataset. The MS-TATNet captures complex, variable, and multi-scale temporal dynamics of PD motor symptoms through a multi-scale temporal convolutional network, scaled dot-product attention mechanism, stacked transformer encoder blocks with a multi-head self-attention mechanism, temporal pooling layer, softmax classifier, and regression layer. Results: The experimental results demonstrate that the MS-TATNet achieved 99.63% accuracy, 99.50% recall, 99.33% specificity, and 99.67% F1-score for medication state classification. For continuous severity estimation, the predicted scores showed a Pearson correlation coefficient of 0.97 with clinical assessments. Conclusion: Thus, this work highlights the MS-TATNet\u2019s potential for scalable, privacy-preserving remote monitoring of PD.<\/jats:p>","DOI":"10.31083\/jin47677","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T11:53:12Z","timestamp":1769687592000},"source":"Crossref","is-referenced-by-count":1,"title":["Multi-Scale Adaptive Temporal Network for Parkinson\u2019s Motor Symptom Fluctuation Detection Using Coarsened 2D Skeleton Pose Data"],"prefix":"10.31083","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5674-4493","authenticated-orcid":true,"given":"Balamurugan","family":"Velumani","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Akshaya College of Engineering and Technology, Coimbatore, 642109 Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1810-6562","authenticated-orcid":true,"given":"Sivasankari","family":"Krishnakumar","sequence":"additional","affiliation":[{"name":"Department of Electronics and Communication Engineering, Akshaya College of Engineering and Technology, Coimbatore, 642109 Tamil Nadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"16242","published-online":{"date-parts":[[2026,1,26]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","unstructured":"Minervini G, Franco R, Marrapodi MM, Ronsivalle V, Shapira I, Cicci\u00f9 M. Prevalence of temporomandibular disorders in subjects affected by Parkinson disease: A systematic review and metanalysis. Journal of Oral Rehabilitation. 2023; 50: 877\u2013885.","DOI":"10.1111\/joor.13496"},{"key":"ref2","doi-asserted-by":"publisher","unstructured":"Burtscher J, Moraud EM, Malatesta D, Millet GP, Bally JF, Patoz A. Exercise and gait\/movement analyses in treatment and diagnosis of Parkinson\u2019s Disease. Ageing Research Reviews. 2024; 93: 102147.","DOI":"10.1016\/j.arr.2023.102147"},{"key":"ref3","doi-asserted-by":"publisher","unstructured":"Stocchi F, Bravi D, Emmi A, Antonini A. Parkinson disease therapy: current strategies and future research priorities. Nature Reviews. Neurology. 2024; 20: 695\u2013707.","DOI":"10.1038\/s41582-024-01034-x"},{"key":"ref4","doi-asserted-by":"publisher","unstructured":"Balamurugan V, Sivasankari K. Segment anything model-based segmentation with inception-ResNet-v2 classifier for Parkinson\u2019s disease diagnosis and metaverse visualization. Computers in Biology and Medicine. 2025; 187: 109732.","DOI":"10.1016\/j.compbiomed.2025.109732"},{"key":"ref5","doi-asserted-by":"publisher","unstructured":"Meng D, Jin Z, Wang Y, Fang B. Longitudinal cognitive changes in patients with early Parkinson\u2019s disease and neuropsychiatric symptoms. CNS Neuroscience & Therapeutics. 2023; 29: 2259\u20132266.","DOI":"10.1111\/cns.14173"},{"key":"ref6","doi-asserted-by":"publisher","unstructured":"Leite Silva ABR, Gon\u00e7alves de Oliveira RW, Di\u00f3genes GP, de Castro Aguiar MF, Sallem CC, Lima MPP, et al. Premotor, nonmotor and motor symptoms of Parkinson\u2019s Disease: A new clinical state of the art. Ageing Research Reviews. 2023; 84: 101834.","DOI":"10.1016\/j.arr.2022.101834"},{"key":"ref7","doi-asserted-by":"publisher","unstructured":"Saini N, Singh N, Kaur N, Garg S, Kaur M, Kumar A, et al. Motor and non-motor symptoms, drugs, and their mode of action in Parkinson\u2019s disease (PD): a review. Medicinal Chemistry Research. 2024; 33: 580\u2013599.","DOI":"10.1007\/s00044-024-03203-5"},{"key":"ref8","doi-asserted-by":"publisher","unstructured":"Alharbi B, Al-Kuraishy HM, Al-Gareeb AI, Elekhnawy E, Alharbi H, Alexiou A, et al. Role of GABA pathway in motor and non-motor symptoms in Parkinson\u2019s disease: a bidirectional circuit. European Journal of Medical Research. 2024; 29: 205.","DOI":"10.1186\/s40001-024-01779-7"},{"key":"ref9","doi-asserted-by":"publisher","unstructured":"Asadpoordezaki Z, Coogan AN, Henley BM. Chronobiology of Parkinson\u2019s disease: Past, present and future. The European Journal of Neuroscience. 2023; 57: 178\u2013200.","DOI":"10.1111\/ejn.15859"},{"key":"ref10","doi-asserted-by":"publisher","unstructured":"Janssen Daalen JM, van den Bergh R, Prins EM, Moghadam MSC, van den Heuvel R, Veen J, et al. Digital biomarkers for non-motor symptoms in Parkinson\u2019s disease: the state of the art. NPJ Digital Medicine. 2024; 7: 186.","DOI":"10.1038\/s41746-024-01144-2"},{"key":"ref11","doi-asserted-by":"publisher","unstructured":"Antonini A, Reichmann H, Gentile G, Garon M, Tedesco C, Frank A, et al. Toward objective monitoring of Parkinson\u2019s disease motor symptoms using a wearable device: wearability and performance evaluation of PDMonitor\u00ae. Frontiers in Neurology. 2023; 14: 1080752.","DOI":"10.3389\/fneur.2023.1080752"},{"key":"ref12","doi-asserted-by":"publisher","unstructured":"Polvorinos-Fern\u00e1ndez C, Sigcha L, Borz\u00ec L, Olmo G, Asensio C, L\u00f3pez JM, et al. Evaluating motor symptoms in Parkinson\u2019s disease through wearable sensors: a systematic review of digital biomarkers. Applied Sciences. 2024; 14: 10189.","DOI":"10.3390\/app142210189"},{"key":"ref13","doi-asserted-by":"publisher","unstructured":"Shcherbak A, Kovalenko E, Somov A. Detection and classification of early stages of Parkinson\u2019s disease through wearable sensors and machine learning. IEEE Transactions on Instrumentation and Measurement. 2023; 72: 1\u20139.","DOI":"10.1109\/TIM.2023.3284944"},{"key":"ref14","doi-asserted-by":"publisher","unstructured":"Wu X, Ma L, Wei P, Shan Y, Chan P, Wang K, et al. Wearable sensor devices can automatically identify the ON-OFF status of patients with Parkinson\u2019s disease through an interpretable machine learning model. Frontiers in Neurology. 2024; 15: 1387477.","DOI":"10.3389\/fneur.2024.1387477"},{"key":"ref15","doi-asserted-by":"publisher","unstructured":"Battista L, Romaniello A. A New Wrist-Worn Tool Supporting the Diagnosis of Parkinsonian Motor Syndromes. Sensors (Basel, Switzerland). 2024; 24: 1965.","DOI":"10.3390\/s24061965"},{"key":"ref16","doi-asserted-by":"publisher","unstructured":"Lin S, Gao C, Li H, Huang P, Ling Y, Chen Z, et al. Wearable sensor-based gait analysis to discriminate early Parkinson\u2019s disease from essential tremor. Journal of Neurology. 2023; 270: 2283\u20132301.","DOI":"10.1007\/s00415-023-11577-6"},{"key":"ref17","doi-asserted-by":"publisher","unstructured":"Davidashvilly S, Cardei M, Hssayeni M, Chi C, Ghoraani B. Deep neural networks for wearable sensor-based activity recognition in Parkinson\u2019s disease: investigating generalizability and model complexity. Biomedical Engineering Online. 2024; 23: 17.","DOI":"10.1186\/s12938-024-01214-2"},{"key":"ref18","doi-asserted-by":"publisher","unstructured":"Johnson S, Kantartjis M, Severson J, Dorsey R, Adams JL, Kangarloo T, et al. Wearable Sensor-Based Assessments for Remotely Screening Early-Stage Parkinson\u2019s Disease. Sensors (Basel, Switzerland). 2024; 24: 5637.","DOI":"10.3390\/s24175637"},{"key":"ref19","doi-asserted-by":"publisher","unstructured":"Rodriguez F, Krauss P, Kluckert J, Ryser F, Stieglitz L, Baumann C, et al. Continuous and Unconstrained Tremor Monitoring in Parkinson\u2019s Disease Using Supervised Machine Learning and Wearable Sensors. Parkinson\u2019s Disease. 2024; 2024: 5787563.","DOI":"10.1155\/2024\/5787563"},{"key":"ref20","doi-asserted-by":"publisher","unstructured":"Hammoud M, Shcherbak A, Istrakova O, Shindryaeva N, Bril E, Passerone R, et al. Wrist-Worn Sensors and Machine Learning for Parkinson\u2019s Disease Detection: Investigation of Binary and Multi-classification Problem. IEEE Transactions on Instrumentation and Measurement. 2025; 74: 1\u201311.","DOI":"10.1109\/TIM.2025.3544381"},{"key":"ref21","doi-asserted-by":"publisher","unstructured":"Brien DC, Riek HC, Yep R, Huang J, Coe B, Areshenkoff C, et al. Classification and staging of Parkinson\u2019s disease using video-based eye tracking. Parkinsonism & Related Disorders. 2023; 110: 105316.","DOI":"10.1016\/j.parkreldis.2023.105316"},{"key":"ref22","doi-asserted-by":"publisher","unstructured":"Sarapata G, Dushin Y, Morinan G, Ong J, Budhdeo S, Kainz B, et al. Video-Based Activity Recognition for Automated Motor Assessment of Parkinson\u2019s Disease. IEEE Journal of Biomedical and Health Informatics. 2023; 27: 5032\u20135041.","DOI":"10.1109\/JBHI.2023.3298530"},{"key":"ref23","doi-asserted-by":"publisher","unstructured":"Zeng Q, Liu P, Yu N, Wu J, Huo W, Han J. Video-Based Quantification of Gait Impairments in Parkinson\u2019s Disease Using Skeleton-Silhouette Fusion Convolution Network. IEEE Transactions on Neural Systems and Rehabilitation Engineering: a Publication of the IEEE Engineering in Medicine and Biology Society. 2023; 31: 2912\u20132922.","DOI":"10.1109\/TNSRE.2023.3291359"},{"key":"ref24","doi-asserted-by":"publisher","unstructured":"Liu W, Lin X, Chen X, Wang Q, Wang X, Yang B, et al. Vision-based estimation of MDS-UPDRS scores for quantifying Parkinson\u2019s disease tremor severity. Medical Image Analysis. 2023; 85: 102754.","DOI":"10.1016\/j.media.2023.102754"},{"key":"ref25","doi-asserted-by":"publisher","unstructured":"Gao J, Bidulka L, Mckeown MJ, Wang ZJ. Regular RGB-Video Based Eye Movement Assessment for Parkinson\u2019s Disease. IEEE Transactions on Instrumentation and Measurement. 2025; 74: 1\u201312.","DOI":"10.1109\/TIM.2025.3606068"},{"key":"ref26","unstructured":"Ian Craddock, Majid Mirmehdi, Emma Tonkin, Gregory Tourte, Alessandro Masullo, Ryan McConville, Alan Whone, Catherine Morgan, Ferdian Jovan, Arindam Sikdar, Pushpajit Khaire. REMAP Dataset. 2023. Available at: https:\/\/data.bris.ac.uk\/data\/dataset\/21h9f9e30v9cl2fapjggz4q1x7 (Accessed: 16 September 2025)."},{"key":"ref27","doi-asserted-by":"publisher","unstructured":"Xu Z, Zhang Y, Miao Q. An attention-based multi-scale temporal convolutional network for remaining useful life prediction. Reliability Engineering & System Safety. 2024; 250: 110288.","DOI":"10.1016\/j.ress.2024.110288"},{"key":"ref28","doi-asserted-by":"publisher","unstructured":"Saheed YK, Chukwuere JE. CPS-IIoT-P2Attention: Explainable privacy-preserving with scaled dot-product attention in cyber physical system-industrial IoT network. IEEE Access. 2025; 13: 81118-81142.","DOI":"10.1109\/ACCESS.2025.3566980"},{"key":"ref29","doi-asserted-by":"publisher","unstructured":"Yu Z, Shi X, Zhang Z. A multi-head self-attention transformer-based model for traffic situation prediction in terminal areas. IEEE Access. 2023; 11: 16156\u201316165.","DOI":"10.1109\/ACCESS.2023.3245085"},{"key":"ref30","doi-asserted-by":"publisher","unstructured":"Irani Azad M, Rajabi R, Estebsari A. Nonintrusive load monitoring (NILM) using a deep learning model with a transformer-based attention mechanism and temporal pooling. Electronics. 2024; 13: 407.","DOI":"10.3390\/electronics13020407"},{"key":"ref31","doi-asserted-by":"publisher","unstructured":"Boyanapalli A, Shanthini A. Ovarian cancer detection in computed tomography images using ensembled deep optimized learning classifier. Concurrency and Computation: Practice and Experience. 2023; 35: e7716.","DOI":"10.1002\/cpe.7716"},{"key":"ref32","doi-asserted-by":"publisher","unstructured":"Vijayan M, S V. A Regression-Based Approach to Diabetic Retinopathy Diagnosis Using Efficientnet. Diagnostics (Basel, Switzerland). 2023; 13: 774.","DOI":"10.3390\/diagnostics13040774"}],"container-title":["Journal of Integrative Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.imrpress.com\/journal\/JIN\/25\/1\/10.31083\/JIN47677","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T11:53:18Z","timestamp":1769687598000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.imrpress.com\/journal\/JIN\/25\/1\/10.31083\/JIN47677"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,26]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026]]}},"alternative-id":["S0219-6352(25)01066-6"],"URL":"https:\/\/doi.org\/10.31083\/jin47677","relation":{},"ISSN":["0219-6352","1757-448X"],"issn-type":[{"value":"0219-6352","type":"print"},{"value":"1757-448X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,26]]},"article-number":"47677"}}