Abstract
Research in machine learning for autism spectrum disorder (ASD) classification bears the promise to improve clinical diagnoses. However, recent studies in clinical imaging have shown the limited generalization of biomarkers across and beyond benchmark datasets. Despite increasing model complexity and sample size in neuroimaging, the classification performance of ASD remains far away from clinical application. This raises the question of how we can overcome these barriers to develop early biomarkers for ASD. One approach might be to rethink how we operationalize the theoretical basis of this disease in machine learning models. Here we introduced unsupervised graph representations that explicitly map the neural mechanisms of a core aspect of ASD, deficits in dyadic social interaction, as assessed by dual brain recordings, termed hyperscanning, and evaluated their predictive performance. The proposed method differs from existing approaches in that it is more suitable to capture social interaction deficits on a neural level and is applicable to young children and infants. First results from functional near-infrared spectroscopy data indicate potential predictive capacities of a task-agnostic, interpretable graph representation. This first effort to leverage interaction-related deficits on neural level to classify ASD may stimulate new approaches and methods to enhance existing models to achieve developmental ASD biomarkers in the future.
M. Schulte-Rüther and V. Reindl—Shared last authorship.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Babiloni, F., Astolfi, L.: Social neuroscience and hyperscanning techniques: past, present and future. Neurosci. Biobehav. Rev. 44, 76–93 (2014)
Baxter, A.J., Brugha, T., Erskine, H.E., Scheurer, R.W., Vos, T., Scott, J.G.: The epidemiology and global burden of autism spectrum disorders. Psychol. Med. 45(3), 601–613 (2015)
Benavoli, A., Corani, G., Demšar, J., Zaffalon, M.: Time for a change: a tutorial for comparing multiple classifiers through Bayesian analysis. J. Mach. Learn. Res. 18(77), 1–36 (2017)
Bolis, D., Schilbach, L.: Observing and participating in social interactions: action perception and action control across the autistic spectrum. Developm. Cognit. Neurosci. 29, 168–175 (2018)
Bouthillier, X., et al.: Accounting for variance in machine learning benchmarks. In: Smola, A., Dimakis, A., Stoica, I. (eds.) Proceedings of Machine Learning and Systems, vol. 3, pp. 747–769 (2021)
Brodersen, K.H., et al.: Dissecting psychiatric spectrum disorders by generative embedding. NeuroImage 4, 98–111 (2014)
Cai, C., Wang, Y.: A simple yet effective baseline for non-attributed graph classification. arXiv preprint arXiv:1811.03508 (2018)
Chanel, G., Pichon, S., Conty, L., Berthoz, S., Chevallier, C., Grèzes, J.: Classification of autistic individuals and controls using cross-task characterization of fMRI activity. NeuroImage 10, 78–88 (2016)
Chen, H., Koga, H.: GL2vec: graph embedding enriched by line graphs with edge features. Neural Inf. Process. 11955, 3–14 (2019)
Dawson, G., et al.: Randomized, controlled trial of an intervention for toddlers with autism: the Early Start Denver Model. Pediatrics 125(1), e17–e23 (2010)
Ecker, C., Bookheimer, S.Y., Murphy, D.G.: Neuroimaging in autism spectrum disorder: brain structure and function across the lifespan. Lancet Neurol. 14(11), 1121–1134 (2015)
Gao, F., Wolf, G., Hirn, M.: Geometric scattering for graph data analysis. In: Proceedings of the 36th International Conference on Machine Learning, pp. 2122–2131. PMLR (2019). ISSN: 2640–3498
Gerloff, C., Konrad, K., Bzdok, D., Büsing, C., Reindl, V.: Interacting brains revisited: a cross-brain network neuroscience perspective. Hum. Brain Mapp. 43(14), 4458–4474 (2022)
Hosseini, M., et al.: I tried a bunch of things: the dangers of unexpected overfitting in classification of brain data. Neurosci. Biobehav. Rev. 119, 456–467 (2020)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Kruppa, J.A., et al.: Brain and motor synchrony in children and adolescents with ASD-a fNIRS hyperscanning study. Soc. Cognit. Affect. Neurosci. 16(1–2), 103–116 (2021)
Narayanan, A., Chandramohan, M., Venkatesan, R., Chen, L., Liu, Y., Jaiswal, S.: graph2vec: Learning Distributed Representations of Graphs. arXiv preprint arXiv:1707.05005 (2017)
Pooch, E.H.P., Ballester, P., Barros, R.C.: Can we trust deep learning based diagnosis? The impact of domain shift in chest radiograph classification. In: Petersen, J., et al. (eds.) TIA 2020. LNCS, vol. 12502, pp. 74–83. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-62469-9_7
Quiñones-Camacho, L.E., Fishburn, F.A., Belardi, K., Williams, D.L., Huppert, T.J., Perlman, S.B.: Dysfunction in interpersonal neural synchronization as a mechanism for social impairment in autism spectrum disorder. Autism Res. 14(8), 1585–1596 (2021)
American Psychiatric Association: Diagnostic and Statistical Manual of Mental Disorders, 5th edn. American Psychiatric Association, Washington DC (2013)
Reindl, V., et al.: Multimodal hyperscanning reveals that synchrony of body and mind are distinct in mother-child dyads. NeuroImage 251, 118982 (2022)
Rozemberczki, B., Sarkar, R.: Characteristic functions on graphs: birds of a feather, from statistical descriptors to parametric models. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp. 1325–1334. ACM, Virtual Event Ireland (2020)
Schulte-Rüther, M., et al.: Using machine learning to improve diagnostic assessment of ASD in the light of specific differential and co-occurring diagnoses. J. Child Psychol. Psychiat. (2022)
Scott-Van Zeeland, A.A., Dapretto, M., Ghahremani, D.G., Poldrack, R.A., Bookheimer, S.Y.: Reward processing in autism. Autism Res. 3(2), 53–67 (2010)
Tanabe, H.C., et al.: Hard to “tune in”: neural mechanisms of live face-to-face interaction with high-functioning autistic spectrum disorder. Front. Human Neurosci. 6, 268 (2012)
Traut, N., et al.: Insights from an autism imaging biomarker challenge: promises and threats to biomarker discovery. NeuroImage 255, 119171 (2022)
Varoquaux, G., Cheplygina, V.: Machine learning for medical imaging: methodological failures and recommendations for the future. NPJ Digit. Med. 5(1), 1–8 (2022)
Wang, L., Huang, C., Ma, W., Cao, X., Vosoughi, S.: Graph embedding via diffusion-wavelets-based node feature distribution characterization. In: Proceedings of the 30th ACM International Conference on Information & Knowledge Management, pp. 3478–3482. ACM, Queensland (2021)
Wang, Q., et al.: Autism symptoms modulate interpersonal neural synchronization in children with autism spectrum disorder in cooperative interactions. Brain Topography 33(1), 112–122 (2020)
Zeidan, J., et al.: Global prevalence of autism: a systematic review update. Autism Res. 15(5), 778–790 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gerloff, C., Konrad, K., Kruppa, J., Schulte-Rüther, M., Reindl, V. (2022). Autism Spectrum Disorder Classification Based on Interpersonal Neural Synchrony: Can Classification be Improved by Dyadic Neural Biomarkers Using Unsupervised Graph Representation Learning?. In: Abdulkadir, A., et al. Machine Learning in Clinical Neuroimaging. MLCN 2022. Lecture Notes in Computer Science, vol 13596. Springer, Cham. https://doi.org/10.1007/978-3-031-17899-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-17899-3_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-17898-6
Online ISBN: 978-3-031-17899-3
eBook Packages: Computer ScienceComputer Science (R0)
