{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T03:25:27Z","timestamp":1769829927334,"version":"3.49.0"},"reference-count":25,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T00:00:00Z","timestamp":1679270400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61976110"],"award-info":[{"award-number":["61976110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176112"],"award-info":[{"award-number":["62176112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["11931008"],"award-info":[{"award-number":["11931008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"crossref","award":["ZR202102270451"],"award-info":[{"award-number":["ZR202102270451"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Brain functional network (BFN) analysis has become a popular technique for identifying neurological\/mental diseases. Due to the fact that BFN is a graph, a graph convolutional network (GCN) can be naturally used in the classification of BFN. Different from traditional methods that directly use the adjacency matrices of BFNs to train a classifier, GCN requires an additional input-node features. To our best knowledge, however, there is no systematic study to analyze their influence on the performance of GCN-based brain disorder classification. Therefore, in this study, we conduct an empirical study on various node feature measures, including (1) original fMRI signals, (2) one-hot encoding, (3) node statistics, (4) node correlation, and (5) their combination. Experimental results on two benchmark databases show that different node feature inputs to GCN significantly affect the brain disease classification performance, and node correlation usually contributes higher accuracy compared to original signals and manually extracted statistical features.<\/jats:p>","DOI":"10.7717\/peerj.14835","type":"journal-article","created":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T09:53:38Z","timestamp":1679306018000},"page":"e14835","source":"Crossref","is-referenced-by-count":4,"title":["The effect of node features on GCN-based brain network classification: an empirical study"],"prefix":"10.7717","volume":"11","author":[{"given":"Guangyu","family":"Wang","sequence":"first","affiliation":[{"name":"Liaocheng University, Liaocheng, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Limei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Liaocheng University, Liaocheng, China"},{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lishan","family":"Qiao","sequence":"additional","affiliation":[{"name":"Liaocheng University, Liaocheng, China"},{"name":"Shandong Jianzhu University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2023,3,20]]},"reference":[{"key":"10.7717\/peerj.14835\/ref-1","article-title":"N-GCN: multi-scale graph convolution for semi-supervised node classification","author":"Abu-El-Haija","year":"2020"},{"key":"10.7717\/peerj.14835\/ref-2","first-page":"44","article-title":"Fusing structural and functional MRIs using graph convolutional networks for autism classification","author":"Arya","year":"2020"},{"key":"10.7717\/peerj.14835\/ref-3","doi-asserted-by":"publisher","first-page":"103015","DOI":"10.1016\/j.bspc.2021.103015","article-title":"Using deep GCN to identify the autism spectrum disorder from multi-site resting-state data","volume":"70","author":"Cao","year":"2021","journal-title":"Biomedical Signal Processing and Control"},{"key":"10.7717\/peerj.14835\/ref-4","doi-asserted-by":"publisher","first-page":"802305","DOI":"10.3389\/fninf.2021.802305","article-title":"Multi-scale graph representation learning for autism identification with functional MRI","volume":"15","author":"Chu","year":"2022","journal-title":"Frontiers in NeuroInformatics"},{"key":"10.7717\/peerj.14835\/ref-5","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.neuroimage.2019.02.062","article-title":"Benchmarking functional connectome-based predictive models for resting-state fMRI","volume":"192","author":"Dadi","year":"2019","journal-title":"NeuroImage"},{"key":"10.7717\/peerj.14835\/ref-6","first-page":"1157","article-title":"An introduction to variable and feature selection","volume":"3","author":"Guyon","year":"2003","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"10.7717\/peerj.14835\/ref-7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-031-01588-5","article-title":"Graph representation learning","volume":"14","author":"Hamilton","year":"2020","journal-title":"Synthesis Lectures on Artifical Intelligence and Machine Learning"},{"key":"10.7717\/peerj.14835\/ref-8","doi-asserted-by":"publisher","first-page":"107082","DOI":"10.1016\/j.cmpb.2022.107082","article-title":"Joint selection of brain network nodes and edges for mci identification","volume":"225","author":"Jiang","year":"2022","journal-title":"Computer Methods and Programs in Biomedicine"},{"key":"10.7717\/peerj.14835\/ref-9","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.7717\/peerj.14835\/ref-10","first-page":"3734","article-title":"Self-attention graph pooling","author":"Lee","year":"2019"},{"key":"10.7717\/peerj.14835\/ref-11","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.ins.2016.12.027","article-title":"Clustering coefficients of large networks","volume":"382","author":"Li","year":"2017","journal-title":"Information Sciences"},{"issue":"1","key":"10.7717\/peerj.14835\/ref-12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41572-019-0135-7","article-title":"Autism spectrum disorder","volume":"6","author":"Lord","year":"2020","journal-title":"Nature Reviews Disease Primers"},{"key":"10.7717\/peerj.14835\/ref-13","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198805090.001.0001","volume-title":"Networks","author":"Newman","year":"2018"},{"key":"10.7717\/peerj.14835\/ref-14","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.media.2018.06.001","article-title":"Disease prediction using graph convolutional networks: application to autism spectrum disorder and Alzheimer\u2019s disease","volume":"48","author":"Parisot","year":"2018","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj.14835\/ref-15","doi-asserted-by":"publisher","first-page":"116604","DOI":"10.1016\/j.neuroimage.2020.116604","article-title":"Optimising network modelling methods for fMRI","volume":"211","author":"Pervaiz","year":"2020","journal-title":"NeuroImage"},{"issue":"1","key":"10.7717\/peerj.14835\/ref-16","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/j.patcog.2009.05.005","article-title":"Sparsity preserving projections with applications to face recognition","volume":"43","author":"Qiao","year":"2010","journal-title":"Pattern Recognition"},{"key":"10.7717\/peerj.14835\/ref-17","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.neucom.2018.05.084","article-title":"Data-driven graph construction and graph learning: a review","volume":"312","author":"Qiao","year":"2018","journal-title":"NeuroComputing"},{"key":"10.7717\/peerj.14835\/ref-18","article-title":"Multi-center and multi-channel pooling GCN for early ad diagnosis based on dual-modality fused brain network","author":"Song","year":"2022"},{"key":"10.7717\/peerj.14835\/ref-19","doi-asserted-by":"publisher","first-page":"102004","DOI":"10.1016\/j.artmed.2020.102004","article-title":"Estimating sparse functional connectivity networks via hyperparameter-free learning model","volume":"111","author":"Sun","year":"2021","journal-title":"Artificial Intelligence in Medicine"},{"issue":"8","key":"10.7717\/peerj.14835\/ref-20","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1016\/j.euroneuro.2010.03.008","article-title":"Exploring the brain network: a review on resting-state fMRI functional connectivity","volume":"20","author":"Van Den Heuvel","year":"2010","journal-title":"European Neuropsychopharmacology"},{"key":"10.7717\/peerj.14835\/ref-21","doi-asserted-by":"publisher","first-page":"105239","DOI":"10.1016\/j.compbiomed.2022.105239","article-title":"Mvs-GCN: a prior brain structure learning-guided multi-view graph convolution network for autism spectrum disorder diagnosis","volume":"142","author":"Wen","year":"2022","journal-title":"Computers in Biology and Medicine"},{"issue":"3","key":"10.7717\/peerj.14835\/ref-22","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1007\/s12021-016-9299-4","article-title":"DPABI: data processing & analysis for (resting-state) brain imaging","volume":"14","author":"Yan","year":"2016","journal-title":"NeuroInformatics"},{"key":"10.7717\/peerj.14835\/ref-23","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"Ying","year":"2018"},{"key":"10.7717\/peerj.14835\/ref-24","first-page":"228","article-title":"Multi-scale enhanced graph convolutional network for early mild cognitive impairment detection","author":"Yu","year":"2020"},{"issue":"5","key":"10.7717\/peerj.14835\/ref-25","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1007\/s10548-022-00914-z","article-title":"Selecting multiple node statistics jointly from functional connectivity networks for brain disorders identification","volume":"35","author":"Zhang","year":"2022","journal-title":"Brain Topography"}],"container-title":["PeerJ"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/14835.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/14835.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/14835.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/14835.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,20]],"date-time":"2023-03-20T09:53:48Z","timestamp":1679306028000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/14835"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,20]]},"references-count":25,"alternative-id":["10.7717\/peerj.14835"],"URL":"https:\/\/doi.org\/10.7717\/peerj.14835","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2167-8359"],"issn-type":[{"value":"2167-8359","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,20]]},"article-number":"e14835"}}