{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T01:56:22Z","timestamp":1779242182457,"version":"3.51.4"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T00:00:00Z","timestamp":1746230400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T00:00:00Z","timestamp":1746230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Royal Melbourne Institute of Technology"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Graph neural networks (GNNs) have been developed to model the relationship between regions of interest (ROIs) in brains and have shown significant improvement in detecting brain diseases. However, most of these frameworks do not consider the intrinsic relationship of causality factor between brain ROIs, which is arguably more essential to observe cause and effect interaction between signals rather than typical correlation values. We propose a novel framework called Causal Graphs for Brains (CGB) for brain disease classification\/detection, which models refined brain networks based on the causal discovery method, transfer entropy, and geometric curvature strategy. CGB unveils causal relationships between ROIs that bring vital information to enhance brain disease classification performance. Furthermore, CGB also performs a graph rewiring through a geometric curvature strategy to refine the generated causal graph to become more expressive and reduce potential information bottlenecks when GNNs model it. Our extensive experiments show that CGB outperforms state-of-the-art methods in classification tasks on brain disease datasets, as measured by average F1 scores.<\/jats:p>","DOI":"10.1007\/s10462-025-11231-9","type":"journal-article","created":{"date-parts":[[2025,5,3]],"date-time":"2025-05-03T03:38:24Z","timestamp":1746243504000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Refined causal graph structure learning via curvature for brain disease classification"],"prefix":"10.1007","volume":"58","author":[{"given":"Falih Gozi","family":"Febrinanto","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adonia","family":"Simango","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengpei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonika","family":"Tyagi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,3]]},"reference":[{"key":"11231_CR1","unstructured":"Akansha S (2024) Over-squashing in graph neural networks: a comprehensive survey. arXiv Preprint http:\/\/arxiv.org\/abs\/2308.15568v6"},{"issue":"1","key":"11231_CR2","doi-asserted-by":"publisher","first-page":"464","DOI":"10.3390\/make6010024","volume":"6","author":"MG Alsubaie","year":"2024","unstructured":"Alsubaie MG, Luo S, Shaukat K (2024) Alzheimer\u2019s disease detection using deep learning on neuroimaging: a systematic review. Mach Learn Knowl Extr 6(1):464\u2013505","journal-title":"Mach Learn Knowl Extr"},{"key":"11231_CR3","unstructured":"Arnaiz-Rodr\u00edguez A, Begga A, Escolano F et al (2022) DiffWire: inductive graph rewiring via the Lov\u00e1sz bound. In: Learning on graphs conference. PMLR, pp 15:1\u201315:27"},{"key":"11231_CR4","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1613\/jair.1.13428","volume":"73","author":"CK Assaad","year":"2022","unstructured":"Assaad CK, Devijver E, Gaussier E (2022) Survey and evaluation of causal discovery methods for time series. J Artif Intell Res 73:767\u2013819","journal-title":"J Artif Intell Res"},{"key":"11231_CR5","unstructured":"Black M, Wan Z, Nayyeri A et al (2023) Understanding oversquashing in GNNs through the lens of effective resistance. In: International conference on machine learning. PMLR, pp 2528\u20132547"},{"key":"11231_CR6","unstructured":"Chen W, Wang Y, Du C et al (2023) Balanced spatial-temporal graph structure learning for multivariate time series forecasting: a trade-off between efficiency and flexibility. In: Asian conference on machine learning. PMLR, pp 185\u2013200"},{"issue":"8","key":"11231_CR7","doi-asserted-by":"publisher","first-page":"1914","DOI":"10.1002\/hbm.21333","volume":"33","author":"RC Craddock","year":"2012","unstructured":"Craddock RC, James GA, Holtzheimer PE III et al (2012) A whole brain fMRI atlas generated via spatially constrained spectral clustering. Hum Brain Mapp 33(8):1914\u20131928","journal-title":"Hum Brain Mapp"},{"issue":"27","key":"11231_CR8","first-page":"5","volume":"7","author":"C Craddock","year":"2013","unstructured":"Craddock C, Benhajali Y, Chu C et al (2013) The neuro bureau preprocessing initiative: open sharing of preprocessed neuroimaging data and derivatives. Front Neuroinform 7(27):5","journal-title":"Front Neuroinform"},{"key":"11231_CR9","doi-asserted-by":"crossref","unstructured":"Cui H, Dai W, Zhu Y et al (2022a) BrainGB: a benchmark for brain network analysis with graph neural networks. IEEE Trans Med Imaging 42(2):493\u2013506","DOI":"10.1109\/TMI.2022.3218745"},{"key":"11231_CR10","doi-asserted-by":"crossref","unstructured":"Cui H, Dai W, Zhu Y et al (2022b) Interpretable graph neural networks for connectome-based brain disorder analysis. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 375\u2013385","DOI":"10.1007\/978-3-031-16452-1_36"},{"issue":"6","key":"11231_CR11","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1038\/mp.2013.78","volume":"19","author":"A Di Martino","year":"2014","unstructured":"Di Martino A, Yan CG, Li Q et al (2014) The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol Psychiatry 19(6):659\u2013667","journal-title":"Mol Psychiatry"},{"issue":"1","key":"11231_CR12","doi-asserted-by":"publisher","first-page":"141","DOI":"10.26599\/TST.2021.9010081","volume":"28","author":"Z Duan","year":"2022","unstructured":"Duan Z, Xu H, Huang Y et al (2022) Multivariate time series forecasting with transfer entropy graph. Tsinghua Sci Technol 28(1):141\u2013149","journal-title":"Tsinghua Sci Technol"},{"key":"11231_CR13","unstructured":"ElGazzar A, Thomas R, Van\u00a0Wingen G (2022) Benchmarking graph neural networks for fMRI analysis. arXiv Preprint http:\/\/arxiv.org\/abs\/2211.08927"},{"key":"11231_CR14","doi-asserted-by":"crossref","unstructured":"Fabbri F, Wang Y, Bonchi F et al (2022) Rewiring what-to-watch-next recommendations to reduce radicalization pathways. In: Proceedings of the ACM web conference 2022. pp 2719\u20132728","DOI":"10.1145\/3485447.3512143"},{"key":"11231_CR15","doi-asserted-by":"crossref","unstructured":"Febrinanto FG, Liu M, Xia F (2023a) Balanced graph structure information for brain disease detection. In: Pacific rim knowledge acquisition workshop. Springer, pp 134\u2013143","DOI":"10.1007\/978-981-99-7855-7_11"},{"key":"11231_CR16","unstructured":"Febrinanto FG, Moore K, Thapa C et al (2023b) Entropy causal graphs for multivariate time series anomaly detection. arXiv Preprint http:\/\/arxiv.org\/abs\/2312.09478"},{"key":"11231_CR17","doi-asserted-by":"crossref","unstructured":"Febrinanto FG, Xia F, Moore K et al (2023c) Graph lifelong learning: a survey. IEEE Comput Intell Mag 18(1):32\u201351","DOI":"10.1109\/MCI.2022.3222049"},{"key":"11231_CR18","unstructured":"Gasteiger J, Wei\u00dfenberger S, G\u00fcnnemann S (2019) Diffusion improves graph learning. In: Advances in neural information processing systems, vol 32"},{"key":"11231_CR19","doi-asserted-by":"crossref","unstructured":"Granger CW (1969) Investigating causal relations by econometric models and cross-spectral methods. Econometrica 37(3):424\u2013438","DOI":"10.2307\/1912791"},{"key":"11231_CR20","first-page":"8291","volume":"35","author":"K Han","year":"2022","unstructured":"Han K, Wang Y, Guo J et al (2022) Vision GNN: an image is worth graph of nodes. Adv Neural Inf Process Syst 35:8291\u20138303","journal-title":"Adv Neural Inf Process Syst"},{"key":"11231_CR21","doi-asserted-by":"crossref","unstructured":"Hu J, Huang Y, Dong S (2023) Transformer and snowball graph convolution learning for brain functional network analysis. In: 2023 IEEE international conference on bioinformatics and biomedicine (BIBM). IEEE, pp 2809\u20132816","DOI":"10.1109\/BIBM58861.2023.10385857"},{"key":"11231_CR22","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.neuroimage.2013.05.079","volume":"80","author":"RM Hutchison","year":"2013","unstructured":"Hutchison RM, Womelsdorf T, Allen EA et al (2013) Dynamic functional connectivity: promise, issues, and interpretations. NeuroImage 80:360\u2013378","journal-title":"NeuroImage"},{"issue":"9","key":"11231_CR23","doi-asserted-by":"publisher","first-page":"6347","DOI":"10.1109\/TII.2020.2989810","volume":"17","author":"J Jiao","year":"2020","unstructured":"Jiao J, Zhen W, Zhu W et al (2020) Quality-related root cause diagnosis based on orthogonal kernel principal component regression and transfer entropy. IEEE Trans Ind Inf 17(9):6347\u20136356","journal-title":"IEEE Trans Ind Inf"},{"key":"11231_CR24","unstructured":"Kan X, Cui H, Lukemire J et al (2022a) FBNETGEN: task-aware GNN-based fMRI analysis via functional brain network generation. In: International conference on medical imaging with deep learning. PMLR, pp 618\u2013637"},{"key":"11231_CR25","unstructured":"Kan X, Dai W, Cui H et al (2022b) Brain network transformer. Adv Neural Inf Process Syst 35:25586\u201325599"},{"key":"11231_CR26","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1016\/j.neuroimage.2016.09.046","volume":"146","author":"J Kawahara","year":"2017","unstructured":"Kawahara J, Brown CJ, Miller SP et al (2017) BrainNetCNN: convolutional neural networks for brain networks; towards predicting neurodevelopment. NeuroImage 146:1038\u20131049","journal-title":"NeuroImage"},{"issue":"2","key":"11231_CR27","doi-asserted-by":"publisher","first-page":"1606","DOI":"10.1109\/TPAMI.2022.3170249","volume":"45","author":"A Kazi","year":"2022","unstructured":"Kazi A, Cosmo L, Ahmadi SA et al (2022) Differentiable graph module (DGM) for graph convolutional networks. IEEE Trans Pattern Anal Mach Intell 45(2):1606\u20131617","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"15","key":"11231_CR28","doi-asserted-by":"publisher","first-page":"5167","DOI":"10.1002\/hbm.26456","volume":"44","author":"KI Khalilullah","year":"2023","unstructured":"Khalilullah KI, Agcaoglu O, Sui J et al (2023) Multimodal fusion of multiple rest fMRI networks and MRI gray matter via parallel multilink joint ICA reveals highly significant function\/structure coupling in Alzheimer\u2019s disease. Hum Brain Mapp 44(15):5167\u20135179","journal-title":"Hum Brain Mapp"},{"issue":"7","key":"11231_CR29","doi-asserted-by":"publisher","first-page":"5251","DOI":"10.1007\/s00330-021-07975-x","volume":"31","author":"B Kocak","year":"2021","unstructured":"Kocak B (2021) Artificial intelligence to predict task activation from resting state fMRI. Eur Radiol 31(7):5251\u20135252","journal-title":"Eur Radiol"},{"key":"11231_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102233","volume":"74","author":"X Li","year":"2021","unstructured":"Li X, Zhou Y, Dvornek N et al (2021) BrainGNN: interpretable brain graph neural network for fMRI analysis. Med Image Anal 74:102233","journal-title":"Med Image Anal"},{"key":"11231_CR31","unstructured":"Li C, Yu S, Cui Y (2024a) Individual brain parcellation: Review of methods, validations and applications. arXiv Preprint http:\/\/arxiv.org\/abs\/2407.00984"},{"key":"11231_CR32","doi-asserted-by":"crossref","unstructured":"Li H, Li C, Zhang J et al (2024b) Addressing over-squashing in GNNs with graph rewiring and ordered neurons. In: 2024 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN60899.2024.10650713"},{"key":"11231_CR33","doi-asserted-by":"crossref","unstructured":"Liu M, Dong Q, Wang C et al (2024) Motif-induced subgraph generative learning for explainable neurological disorder detection. In: Australasian joint conference on artificial intelligence. Springer, pp 376\u2013389","DOI":"10.1007\/978-981-96-0351-0_28"},{"issue":"2\u20133","key":"11231_CR34","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.schres.2005.11.020","volume":"83","author":"N Makris","year":"2006","unstructured":"Makris N, Goldstein JM, Kennedy D et al (2006) Decreased volume of left and total anterior insular lobule in schizophrenia. Schizophr Res 83(2\u20133):155\u2013171","journal-title":"Schizophr Res"},{"key":"11231_CR35","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1146\/annurev-neuro-100220-093239","volume":"44","author":"MG Philiastides","year":"2021","unstructured":"Philiastides MG, Tu T, Sajda P (2021) Inferring macroscale brain dynamics via fusion of simultaneous EEG-fMRI. Annu Rev Neurosci 44:315\u2013334","journal-title":"Annu Rev Neurosci"},{"key":"11231_CR36","unstructured":"Ren J, Xia F (2024) Brain-inspired artificial intelligence: a comprehensive review. arXiv Preprint http:\/\/arxiv.org\/abs\/2408.14811"},{"issue":"2","key":"11231_CR37","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1103\/PhysRevLett.85.461","volume":"85","author":"T Schreiber","year":"2000","unstructured":"Schreiber T (2000) Measuring information transfer. Phys Rev Lett 85(2):461","journal-title":"Phys Rev Lett"},{"key":"11231_CR38","first-page":"94568","volume":"37","author":"K Tieu","year":"2025","unstructured":"Tieu K, Fu D, Zhu Y et al (2025) Temporal graph neural tangent kernel with graphon-guaranteed. Adv Neural Inf Process Syst 37:94568\u201394606","journal-title":"Adv Neural Inf Process Syst"},{"key":"11231_CR39","unstructured":"Topping J, Di\u00a0Giovanni F, Chamberlain BP et al (2022) Understanding over-squashing and bottlenecks on graphs via curvature. In: International conference on learning representations"},{"key":"11231_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.nbd.2023.106095","volume":"181","author":"T Vasilkovska","year":"2023","unstructured":"Vasilkovska T, Adhikari MH, Van Audekerke J et al (2023) Resting-state fMRI reveals longitudinal alterations in brain network connectivity in the ZQ175DN mouse model of Huntington\u2019s disease. Neurobiol Dis 181:106095","journal-title":"Neurobiol Dis"},{"key":"11231_CR41","unstructured":"Welling M, Kipf TN (2017) Semi-supervised classification with graph convolutional networks. In: ICLR"},{"issue":"2","key":"11231_CR42","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/TAI.2021.3076021","volume":"2","author":"F Xia","year":"2021","unstructured":"Xia F, Sun K, Yu S et al (2021) Graph learning: a survey. IEEE Trans Artif Intell 2(2):109\u2013127","journal-title":"IEEE Trans Artif Intell"},{"issue":"1","key":"11231_CR43","first-page":"1","volume":"13","author":"Y Zhou","year":"2022","unstructured":"Zhou Y, Zheng H, Huang X et al (2022) Graph neural networks: taxonomy, advances, and trends. ACM Trans Intell Syst Technol 13(1):1\u201354","journal-title":"ACM Trans Intell Syst Technol"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11231-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-025-11231-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-025-11231-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T10:34:59Z","timestamp":1750674899000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-025-11231-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,3]]},"references-count":43,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["11231"],"URL":"https:\/\/doi.org\/10.1007\/s10462-025-11231-9","relation":{},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,3]]},"assertion":[{"value":"10 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Feng Xia is Associate Editor of Artificial Intelligence Review.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"222"}}