A Multimodal Graph Neural Network for Multiclass ADHD and ASD Classification with Leakage-Aware Evaluation
Abstract
Neurodevelopmental disorders such as attention deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) share overlapping clinical symptoms, complicating diagnosis and motivating objective, data-driven approaches using neuroimaging and machine learning. Graph neural networks (GNNs) have shown strong performance in this domain, yet many existing studies rely on single-modality data, transductive learning, and feature selection procedures that may introduce information leakage and inflate reported accuracy. This study proposes a multimodal graph learning framework that integrates resting-state fMRI (rs-fMRI), structural MRI (sMRI), and demographic data for classifying ADHD, ASD, and healthy controls (HC). The framework integrates temporal stability-based functional connectivity, hybrid feature selection, and adaptive multi-graph learning to exploit complementary information across these modalities. Using the ADHD-200 and ABIDE datasets, the framework is evaluated under three protocols that progressively tighten control over information leakage: transductive learning with global feature selection, inductive learning with global feature selection, and inductive learning with fold-wise feature selection. Results show that classification performance is highest under the transductive, globally-selected setting (85.5% accuracy for HC vs ADHD vs ASD, 92.5% for HC vs ASD, and 90.4% for HC vs ADHD), but decreases under the strictest leakage-aware protocol (70.9%, 81.7%, and 79.3%, respectively). This performance gap indicates that conventional evaluation protocols can substantially overestimate real-world generalization. Importantly, the proposed framework still achieves reasonable accuracy under the strictest setting, suggesting genuine discriminative capability beyond evaluation artifacts. These findings emphasize that leakage-aware evaluation, although yielding lower numbers, provides a more realistic and trustworthy estimate of model performance, highlighting its importance for developing reliable neuroimaging-based GNN models
Downloads
References
E. David, B. Eva, and G. Christopher, “Neurodevelopmental disorders and comorbidity in young adults attending a psychiatric outpatient clinic,” Psychiatry Res., vol. 313, p. 114638, Jul. 2022, doi: 10.1016/j.psychres.2022.114638.
F. Panvino et al., “Neurotrophins in Neurodevelopmental Disorders: A Narrative Review of the Literature,” Int. J. Mol. Sci., vol. 26, no. 17, p. 8335, Aug. 2025, doi: 10.3390/ijms26178335.
E. Mark Mahone, S. Warschausky, and T. Andrew Zabel, “Introduction to the JINS Special Issue: Neurodevelopmental Disorders,” Journal of the International Neuropsychological Society, vol. 24, no. 9, pp. 893–895, Oct. 2018, doi: 10.1017/S1355617718000905.
I. Parenti, L. G. Rabaneda, H. Schoen, and G. Novarino, “Neurodevelopmental Disorders: From Genetics to Functional Pathways,” Trends Neurosci., vol. 43, no. 8, pp. 608–621, Aug. 2020, doi: 10.1016/j.tins.2020.05.004.
K. Kaur, V. Chawla, and B. Rana, “Phase Synchronization-based Topological Features for Autism and ADHD Classification,” in Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP 2024), Bengaluru, India, Dec. 13–15, 2024, New York, NY, USA: ACM, 8 pp., doi: 10.1145/3702250.3702295.
S. Martinez, K. Stoyanov, and L. Carcache, “Unraveling the spectrum: overlap, distinctions, and nuances of ADHD and ASD in children,” Front. Psychiatry, vol. 15, p. 1387179, Sep. 2024, doi: 10.3389/ fpsyt.2024.1387179
X. Wang, X. Zhang, Y. Chen, and X. Yang, “IFC-GNN: Combining interactions of functional connectivity with multimodal graph neural networks for ASD brain disorder analysis,” Alexandria Engineering Journal, vol. 98, pp. 44–55, Jul. 2024, doi: 10.1016/j.aej.2024.04.023.
D. C. Lohani and B. Rana, “ADHD diagnosis using structural brain MRI and personal characteristic data with machine learning framework,” Psychiatry Res. Neuroimaging, vol. 334, Art. no. 111689, Sep. 2023, doi: 10.1016/j.pscychresns.2023.111689.
Y. Zhao, L. Li, and B. S. Caffo, “Multimodal Neuroimaging Data Integration and Pathway Analysis,” Biometrics, vol. 77, no. 3, pp. 879–889, Sep. 2021, doi: 10.1111/biom.13351.
A. Porter, S. Fei, K. S. F. Damme, R. Nusslock, C. Gratton, and V. A. Mittal, “A meta-analysis and systematic review of single vs. multimodal neuroimaging techniques in the classification of psychosis,” Molecular Psychiatry 2023 28:8, vol. 28, no. 8, pp. 3278–3292, Aug. 2023, doi: 10.1038/s41380-023-02195-9.
E. C. Peterson, H. R. Smolker, A. D. Moser, and R. H. Kaiser, “Review of Dynamic Resting‐State Methods in Neuroimaging: Applications to Depression and Rumination,” Hum. Brain Mapp., vol. 46, no. 15, p. e70377, Oct. 2025, doi: 10.1002/hbm.70377.
S. Pau, A. Perniciano, B. Pes, and D. Rubattu, “An Evaluation of Feature Selection Robustness on Class Noisy Data,” Information, vol. 14, no. 8, p. 438, Aug. 2023, doi: 10.3390/info14080438.
J. Ding, J. Du, H. Wang, and S. Xiao, “A novel two-stage feature selection method based on random forest and improved genetic algorithm for enhancing classification in machine learning,” Sci. Rep., vol. 15, no. 1, Art. No. 16828, May 2025, doi: 10.1038/s41598-025-01761-1.
L. Shao, C. Fu, and X. Chen, “A heterogeneous graph convolutional attention network method for classification of autism spectrum disorder,” BMC Bioinformatics, vol. 24, no. 1, p. 363, Dec. 2023, doi: 10.1186/S12859-023-05495-7.
L. Wang, X. Li, J. Yuan, and Y. Chen, “DAGMNet: Dual-Branch Attention-Pruned Graph Neural Network for Multimodal sMRI and fMRI Fusion in Autism Prediction,” Biomedicines, vol. 13, no. 9, p. 2168, Sep. 2025, doi: 10.3390/biomedicines13092168.
Q. Liao et al., “A brain-to-population graph learning framework for diagnosing brain disorders,” Neural Networks, vol. 197, p. 108526, May 2026, doi: 10.1016/j.neunet.2025.108526.
M. Rosenblatt, L. Tejavibulya, R. Jiang, S. Noble, and D. Scheinost, “Data leakage inflates prediction performance in connectome-based machine learning models,” Nature Communications 2024 15:1, vol. 15, no. 1, Art. No. 1829, Feb. 2024, doi: 10.1038/s41467-024-46150-w.
H. Mohammadi and W. Karwowski, “Graph Neural Networks in Brain Connectivity Studies: Methods, Challenges, and Future Directions,” Brain Sci., vol. 15, no. 1, Art. no. 17, Jan. 2025, doi: 10.3390/brainsci15010017.
Y. Yang, C. Ye, and T. Ma, “A deep connectome learning network using graph convolution for connectome-disease association study,” Neural Networks, vol. 164, pp. 91–104, Jul. 2023, doi: 10.1016/j.neunet.2023.04.025.
P. Bellec, C. Chu, F. Chouinard-Decorte, Y. Benhajali, D. S. Margulies, and R. C. Craddock, “The Neuro Bureau ADHD-200 Preprocessed repository,” Neuroimage, vol. 144, no. Pt B, pp. 275–286, Jan. 2017, doi: 10.1016/j.neuroimage.2016.06.034.
A. Di Martino et al., “The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism,” Mol. Psychiatry, vol. 19, no. 6, pp. 659–667, Jun. 2014, doi: 10.1038/mp.2013.78.
E. A. Allen, E. Damaraju, S. M. Plis, E. B. Erhardt, T. Eichele, and V. D. Calhoun, “Tracking Whole-Brain Connectivity Dynamics in the Resting State,” Cerebral Cortex (New York, NY), vol. 24, no. 3, pp. 663–676, Mar. 2014, doi: 10.1093/cercor/bhs352.
R. M. Hutchison et al., “Dynamic functional connectivity: Promise, issues, and interpretations,” Neuroimage, vol. 80, pp. 360–378, Oct. 2013, doi: 10.1016/j.neuroimage.2013.05.079.
H. Peng, F. Long, and C. Ding, “Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 8, pp. 1226–1238, Aug. 2005, doi: 10.1109/tpami.2005.159.
M. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering,” in Advances in Neural Information Processing Systems, vol. 29, D. D. Lee, M. Sugiyama, U. von Luxburg, I. Guyon, and R. Garnett, Eds., pp. 3844–3852, 2016. Available: https://proceedings.neurips.cc/paper_files/paper/2016/file/04df4d434d481c5bb723be1b6df1ee65-Paper.pdf
M. Mennes, B. B. Biswal, F. X. Castellanos, and M. P. Milham, “Making data sharing work: The FCP/INDI experience,” Neuroimage, vol. 82, pp. 683–691, Nov. 2013, doi: 10.1016/j.neuroimage.2012.10.064.
O. Esteban et al., “fMRIPrep: a robust preprocessing pipeline for functional MRI,” Nat. Methods, vol. 16, no. 1, pp. 111–116, Jan. 2019, doi: 10.1038/S41592-018-0235-4.
B. Fischl, “FreeSurfer,” Neuroimage, vol. 62, no. 2, pp. 774–781, Aug. 2012, doi: 10.1016/j.neuroimage.2012.01.021.
N. Tzourio-Mazoyer et al., “Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain,” Neuroimage, vol. 15, no. 1, pp. 273–289, 2002, doi: 10.1006/nimg.2001.0978.
B. Qiu, Q. Wang, X. Li, W. Li, W. Shao, and M. Wang, “Adaptive spatial-temporal neural network for ADHD identification using functional fMRI,” Front. Neurosci., vol. 18, Art. no. 1394234, May 2024, doi: 10.3389/fnins.2024.1394234
A. D. Savva, G. D. Mitsis, and G. K. Matsopoulos, “Assessment of dynamic functional connectivity in resting‐state fMRI using the sliding window technique,” Brain Behav., vol. 9, no. 4, p. e01255, Apr. 2019, doi: 10.1002/BRB3.1255.
S. Parisot et al., “Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer’s disease,” Med. Image Anal., vol. 48, pp. 117–130, Aug. 2018, doi: 10.1016/j.media.2018.06.001.
S. I. Ktena et al., “Metric learning with spectral graph convolutions on brain connectivity networks,” Neuroimage, vol. 169, pp. 431–442, Apr. 2018, doi: 10.1016/j.neuroimage.2017.12.052.
Y. D. Zhang et al., “Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation,” Information Fusion, vol. 64, pp. 149–187, Dec. 2020, doi: 10.1016/j.inffus.2020.07.006.
M. Vaida and Z. Huang, “Multimodal graph neural networks in healthcare: a review of fusion strategies across biomedical domains,” Front. Artif. Intell., vol. 8, p. 1716706, Jan. 2026, doi: 10.3389/frai.2025.1716706.
J. Wen et al., “Convolutional neural networks for classification of Alzheimer’s disease: Overview and reproducible evaluation,” Med. Image Anal., vol. 63, Art. no. 101694, Jul. 2020, doi: 10.1016/j.media.2020.101694.
S. Saeb, L. Lonini, A. Jayaraman, D. C. Mohr, and K. P. Kording, “The need to approximate the use-case in clinical machine learning,” Gigascience, vol. 6, no. 5, pp. 1–9, May 2017, doi: 10.1093/gigascience/gix019.
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
M. Sokolova and G. Lapalme, “A systematic analysis of performance measures for classification tasks,” Inf. Process. Manag., vol. 45, no. 4, pp. 427–437, Jul. 2009, doi: 10.1016/j.ipm.2009.03.002.
D. C. Montgomery and G. C. Runger, Applied Statistics and Probability for Engineers, 7th ed. Hoboken, NJ, USA: John Wiley & Sons, 2018.
T. Song, Z. Ren, J. Zhang, and M. Wang, “Multi-View and Multimodal Graph Convolutional Neural Network for Autism Spectrum Disorder Diagnosis,” Mathematics, vol. 12, no. 11, p. 1648, May 2024, doi: 10.3390/math12111648.
Z. Zolghadr, S. A. H. Batouli, H. A. Majd, L. Shafaghi, and Y. Mehrabi, “fMRI-Based Multi-class DMDC Model Efficiently Decodes the Overlaps between ASD and ADHD,” Basic Clin. Neurosci., vol. 15, no. 3, pp. 367–382, May 2024, doi: 10.32598/bcn.2023.4302.1.
L. Chen et al., “An explainable spatio-temporal graph convolutional network for the biomarkers identification of ADHD,” Biomed. Signal Process. Control, vol. 99, p. 106913, Jan. 2025, doi: 10.1016/j.bspc.2024.106913.
K. Zhao, B. Duka, H. Xie, D. J. Oathes, V. Calhoun, and Y. Zhang, “A dynamic graph convolutional neural network framework reveals new insights into connectome dysfunctions in ADHD,” Neuroimage, vol. 246, p. 118774, Feb. 2022, doi: 10.1016/j.neuroimage.2021.118774.
Copyright (c) 2026 Chofifatul Hidayah, Wiharto Wiharto, Esti Suryani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
