{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T07:03:24Z","timestamp":1782975804135,"version":"3.54.5"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"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:p>Parkinson\u2019s disease (PD) is a common neurodegenerative disorder, and accurate diagnosis is crucial for timely intervention. Dynamic functional connectivity (DFC) analysis of resting-state functional magnetic resonance imaging (rs-fMRI) can capture the time-varying characteristics of brain networks, offering a new perspective for PD identification. However, traditional clustering-based DFC methods suffer from issues such as the loss of continuous temporal information. Existing machine learning approaches struggle to effectively integrate the temporal dynamics of DFC with inter-subject differences in functional connectivity patterns and are further limited by the poor generalizability and opaque decision-making processes inherent to the small sample sizes typical of neuroimaging data. Here, we propose a DFC analysis framework based on a multi-view graph convolutional network (GCN). This method independently constructs inter-subject similarity networks for each sliding time window, forming multi-view graph-structured inputs. It employs a shared-weight GCN to extract node embeddings from each window, which are then fused for classification. Furthermore, the gradient-weighted class activation mapping (Grad-CAM) algorithm is incorporated to provide visual interpretability of the model\u2019s decisions. Our method outperforms traditional static functional connectivity and clustering-based approaches in classification accuracy. Concurrently, it achieves superior classification performance compared to other benchmark models. Grad-CAM-based interpretability analysis further reveals that the frontal and parietal lobes contribute most significantly to the classification decisions, providing computational evidence for understanding the brain network mechanisms underlying PD.<\/jats:p>","DOI":"10.3389\/fnagi.2026.1856371","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:35:46Z","timestamp":1782970546000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A multi-view graph neural network framework for Parkinson\u2019s disease identification based on dynamic functional connectivity"],"prefix":"10.3389","volume":"18","author":[{"given":"Meili","family":"Lu","sequence":"first","affiliation":[{"name":"School of Information Technology Engineering, Tianjin University of Technology and Education","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Technology Engineering, Tianjin University of Technology and Education","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xile","family":"Wei","sequence":"additional","affiliation":[{"name":"Tianjin Key Laboratory of 5 Process Measurement and Control, School of Electrical and Information Engineering, Tianjin University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/s41572-021-00280-3","article-title":"Parkinson disease-associated cognitive impairment.","volume":"7","author":"Arsland","year":"2021","journal-title":"Nat. Rev. Dis. Primers"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e0197121","DOI":"10.1371\/journal.pone.0197121","article-title":"Correction: Exploring the reproducibility of functional connectivity alterations in Parkinson\u2019s disease.","volume":"13","author":"Badea","year":"2018","journal-title":"PLoS One"},{"key":"B3","first-page":"458","article-title":"Quantitative imaging for Parkinson\u2019s disease research progress of magnetic susceptibility.","volume":"33","author":"Bu","year":"2023","journal-title":"Chin. J. Med. Imaging Technol."},{"key":"B4","first-page":"649","article-title":"Trend analysis and prediction of the changing burden of disease in Parkinson\u2019s disease in China.","volume":"30","author":"Chen","year":"2022","journal-title":"Chin. J. Prevent. Control Chronic Dis."},{"key":"B5","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1186\/s41983-024-00839-3","article-title":"Dynamic channelwise functional-connectivity states extracted from resting-state EEG signals of patients with Parkinson\u2019s disease.","volume":"60","author":"Ding","year":"2024","journal-title":"Egypt. J. Neurol. Psychiatry Neurosurg."},{"key":"B6","year":"2018","journal-title":"Parkinson\u2019s Progression Markers Initiative, rs-fMRI Data Availability and Usage, En-rolled Subject Schedule of Activities, in Protocol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41592-018-0235-4","article-title":"fMRIPrep: A robust preprocessing pipeline for functional MRI.","volume":"16","author":"Esteban","year":"2019","journal-title":"Nat. Methods"},{"key":"B8","article-title":"Analysis of simultaneous recording of SEEG and high-density EEG ESI localization in preoperative lesion evaluation in epilepsy\/\/Chinese Medical Doctors\u2019 Association, Chinese Medical Doctors\u2019 Association Neurosurgeons\u2019 Branch","volume-title":"Proceedings of the 18th Annual Meeting of the Chinese Physicians Association of Neurosurgeons-Neurophysiology","author":"Hao","year":"2024"},{"key":"B9","volume-title":"Prediction of Cyclic RNA-disease Association Based on Deep Learning Method.","author":"He","year":"2023"},{"key":"B10","first-page":"392","article-title":"A study of brain dynamic functional connectivity in children and adolescents with refractory temporal lobe epilepsy by resting-state functional MRI.","volume":"47","author":"He","year":"2024","journal-title":"J. Zunyi Med. Univ."},{"key":"B11","doi-asserted-by":"publisher","first-page":"3209","DOI":"10.12307\/2024.345","article-title":"Correlations between brain function and olfactory function in patients with cerebral small vessel disease and Parkinson\u2019s disease based on resting-state functional magnetic resonance imaging.","volume":"28","author":"Huang","year":"2024","journal-title":"Chin. J. Tissue Eng. Res."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: A method for stochastic optimization.","author":"Kingma","year":"2014","journal-title":"arXiv [Preprint]"},{"key":"B13","volume-title":"Research and Application of Spectral Clustering Algorithm Based on Similarity Improvement.","author":"Lei","year":"2023"},{"key":"B14","first-page":"598","article-title":"Static and dynamic functional connectivity changes in the default network of patients with major depressive disorder.","volume":"40","author":"Li","year":"2024","journal-title":"Chin. J. Med. Imaging Technol."},{"key":"B15","volume-title":"Dynamic Load Inversion for Linear Structures Under Frobenius Paradigm Regularization Constraints.","author":"Li","year":"2023"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.12677\/acm.2025.152456","article-title":"Brain magnetic resonance (NMR) in adolescent research progress of major depressive disorder reward networks.","volume":"15","author":"Liangbo","year":"2025","journal-title":"J. Clin. Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"2198","DOI":"10.3778\/j.issn.1673-9418.2206102","article-title":"Social network nodes classification method based on multi-information fusion.","volume":"17","author":"Liu","year":"2023","journal-title":"J. Front. Comp. Sci. Technol."},{"key":"B18","volume-title":"Study on Dynamic Functional Connectivity and Classification of Default Network in Epilepsy Patients.","author":"Liu","year":"2023"},{"key":"B19","doi-asserted-by":"publisher","first-page":"106521","DOI":"10.1016\/j.compbiomed.2022.106521","article-title":"BrainTGL: A dynamic graph representation learning model for brain network analysis.","volume":"153","author":"Liu","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"149576","DOI":"10.1016\/j.brainres.2025.149576","article-title":"Basal ganglia connectivity and network asymmetry in Parkinson\u2019s disease: A resting-state fMRI study.","volume":"1856","author":"Liu","year":"2025","journal-title":"Brain Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"e3392","DOI":"10.7717\/peerj-cs.3392","article-title":"Multi-level functional network-based PD identification via graph deep learning.","volume":"12","author":"Lu","year":"2026","journal-title":"PeerJ Comp. Sci."},{"key":"B22","doi-asserted-by":"publisher","first-page":"204","DOI":"10.3969\/j.issn.1674-8425(z).2024.04.027","article-title":"State judgment and classification of dynamic functional connectivity patterns.","volume":"38","author":"Ma","year":"2024","journal-title":"J. Chongqing Univ. Technol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"2997","DOI":"10.12677\/acm.2024.1441383","article-title":"Brain function research progress of magnetic resonance (NMR) in adolescent suicide self-injury.","volume":"14","author":"Ma","year":"2024","journal-title":"J. Clin. Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"259","DOI":"10.3390\/bios14050259","article-title":"Parkinson\u2019s disease recognition using decorrelated convolutional neural networks: Addressing imbalance and scanner bias in rs-fMRI data.","volume":"14","author":"Patil","year":"2024","journal-title":"Biosensors"},{"key":"B25","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.neuroimage.2016.12.061","article-title":"The dynamic functional connectome: State-of-the-art and perspectives.","volume":"160","author":"Preti","year":"2017","journal-title":"Neuroimage"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1109\/TBME.2021.3127173","article-title":"Brain functional connectivity analysis via graphical deep learning.","volume":"69","author":"Qu","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B27","first-page":"61","article-title":"The central mechanism of cognitive impairment after stroke: Advances based on electroencephalography and magnetic resonance imaging.","volume":"46","author":"Ren","year":"2025","journal-title":"J. Sun Yat-sen Univ."},{"key":"B28","volume-title":"Resting-state fMRI Mechanism Study of the Efficacy of Repetitive Transcranial Magnetic Stimulation on Depression in Parkinson\u2019s Disease.","author":"Shen","year":"2023"},{"key":"B29","first-page":"22","article-title":"Sickle cell image classification model based on CNN and KNN.","volume":"2024","author":"Song","year":"2024","journal-title":"J. Mudanjiang Normal College"},{"key":"B30","doi-asserted-by":"publisher","first-page":"3306","DOI":"10.12677\/mos.2024.133301","article-title":"Based on the depth study of Parkinson\u2019s disease progression in the diagnosis of network model.","volume":"13","author":"Tao","year":"2024","journal-title":"J. Model. Simulat."},{"key":"B31","doi-asserted-by":"publisher","first-page":"103252","DOI":"10.1016\/j.nicl.2022.103252","article-title":"BMAT: An open-source BIDS managing and analysis tool.","volume":"36","author":"Vanden Bulcke","year":"2022","journal-title":"Neuroimage Clin."},{"key":"B32","first-page":"5","article-title":"Research on regional brain function changes and functional connectivity status in patients with sensory-motor dysfunction of Parkinson\u2019s disease.","volume":"40","author":"Wang","year":"2021","journal-title":"J. Clin. Radiol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"51","DOI":"10.3969\/j.issn.1671-7104.230141","article-title":"[Application progress of resting-state functional magnetic resonance imaging in study of default mode network in patients with vascular cognitive impairment].","volume":"48","author":"Wang","year":"","journal-title":"Zhongguo Yi Liao Qi Xie Za Zhi"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.19734\/j.issn.1001-3695.2023.09.0367","article-title":"Graph theoretic network construction method and classification of high-order dynamic functional connectivity for MCI patients.","volume":"41","author":"Wang","year":"","journal-title":"Appl. Res. Comp."},{"key":"B35","first-page":"718","article-title":"How to analyze fMRI data with open source tools: An introduction to supervised machine learning algorithm for multi-voxel patterns analysis.","volume":"45","author":"Wang","year":"2022","journal-title":"Psychol. Sci."},{"key":"B36","first-page":"449","article-title":"Resting-state functional MRI of dynamic functional connectivity of supplementary motor areas in patients with Parkinson\u2019s disease.","volume":"37","author":"Yang","year":"2022","journal-title":"Radiol. Pract."},{"key":"B37","volume-title":"Research on Topological Properties of AD Brain Network Based on Dynamic Functional Connectivity Analysis.","author":"Zhang","year":"2020"},{"key":"B38","doi-asserted-by":"publisher","first-page":"139","DOI":"10.19791\/j.cnki.1006-6411.2024.13.035","article-title":"Research on the status and influencing factors of social alienation in Parkinson\u2019s disease patients.","volume":"31","author":"Zhang","year":"2024","journal-title":"Contemp. Nurses"},{"key":"B39","doi-asserted-by":"publisher","first-page":"107478","DOI":"10.1016\/j.compbiomed.2023.107478","article-title":"Multi-view graph network learning framework for identification of major depressive disorder.","volume":"166","author":"Zhang","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B40","first-page":"130","article-title":"Exploring the differences in brain effects of acupuncture on selected points of yin and yang meridians for stroke based on fMRI technique.","volume":"40","author":"Zhang","year":"2022","journal-title":"Chin. Arch. Trad. Chin. Med."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1856371\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:35:56Z","timestamp":1782970556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2026.1856371\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":40,"alternative-id":["10.3389\/fnagi.2026.1856371"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2026.1856371","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"article-number":"1856371"}}