Autism Spectrum Disorder Classification in Children Using Eye-tracking Technology and Convolutional Neural Networks
DOI:
https://doi.org/10.22399/ijcesen.3900Keywords:
Autism Spectrum Disorder (ASD), Deep Learning, Medical Images Diagnosis, Convolutional Neural Networks, VGG16Abstract
Autism Spectrum Disorder (ASD) is a highly complex and difficult to treat neural developmental disorder that often manifests with distinct challenges in social abilities such as human interaction and communication, as well as causing children to exhibit behaviors repeatedly. A definitive one-size-fits-all treatment has yet to be developed for ASD, but early diagnosis and detection is critical for implementing effective interventions at an early age which allows children suffering from ASD to achieve greatly better outcomes in their development, pulling them closer to typically developing children. Traditional diagnostic methods are, most of the time, hard to access in undeveloped countries, consume a lot of time and are highly subjective. The most recent breakthroughs and developments in machine learning, particularly deep learning, have allowed for the creation of automated systems for ASD classification. This paper focuses on using a Convolutional Neural Network (CNN) utilizing transfer learning along with the pre-trained VGG16 augmented with further convolutional layers to classify ASD from eye-tracking scanpaths. The proposed method demonstrates high classification accuracy that reaches 98.4%, with precision and recall reaching 96.6% and 100% respectively, supported by robust preprocessing, augmentation and transfer learning techniques, the results emphasize the potential of CNNs as a reliable diagnostic tool, paving the way for integrating AI in clinical settings.
References
[1] Centers for Disease Control and Prevention. (2025, April 15). Data and statistics on autism spectrum disorder. Centers for Disease Control and Prevention. https://www.cdc.gov/autism/data-research/?CDC_AAref_Val=https%3A%2F%2Fwww.cdc.gov%2Fncbddd%2Fautism%2Fdata.html
[2] Church, C., Alisanski, S., & Amanullah, S. (2000). The social, behavioral, and academic experiences of children with asperger syndrome. Focus on Autism and Other Developmental Disabilities, 15(1), 12–20. https://doi.org/10.1177/108835760001500102
[3] Vanaken, G.-J., Noens, I., Steyaert, J., van Esch, L., Warreyn, P., & Hens, K. (2024, November). The earlier, the better? an in-depth interview study on the ethics of early detection with parents of children at an elevated likelihood for autism. Journal of autism and developmental disorders. https://pmc.ncbi.nlm.nih.gov/articles/PMC11461763/
[4] Hus, Y., & Segal, O. (2021, December 3). Challenges surrounding the diagnosis of autism in children. Neuropsychiatric disease and treatment. https://pmc.ncbi.nlm.nih.gov/articles/PMC8654688/
[5] Antezana, L., Scarpa, A., Valdespino, A., Albright, J., & Richey, J. A. (2017, April 20). Rural trends in diagnosis and services for autism spectrum disorder. Frontiers in psychology. https://pmc.ncbi.nlm.nih.gov/articles/PMC5397491/
[6] Autism spectrum disorder diagnosis across cultures. (n.d.). https://journals.sagepub.com/doi/full/10.1177/27546330241226811
[7] Development of the methodology for studying the social attention of children with autism spectrum disorders by the eye tracking method (preliminary results). Acta Medica Eurasica. (n.d.). https://acta-medica-eurasica.ru/en/single/2021/2/3/
[8] Pierce, K., Conant, D., & Hazen, R. (2011, January 3). Preference for geometric patterns early in life as a risk factor for autism | autism spectrum disorders | JAMA psychiatry | jama network. https://jamanetwork.com/journals/jamapsychiatry/fullarticle/210964
[9] Patil, D., Rane, N. L., Desai, P., & Rane, J. (2024, October 17). Machine learning and deep learning: Methods, techniques, applications, challenges, and future research opportunities. Deep Science Publishing. https://deepscienceresearch.com/index.php/dsr/catalog/book/10/chapter/75
[10] Ahmed, S. F., Alam, Md. S. B., Hassan, M., Rozbu, M. R., Ishtiak, T., Rafa, N., Mofijur, M., Ali, A. B. M. S., & Gandomi, A. H. (2023, April 17). Deep Learning Modelling Techniques: Current Progress, applications, advantages, and Challenges - Artificial Intelligence Review. SpringerLink. https://link.springer.com/article/10.1007/s10462-023-10466-8
[11] Li, M., Jiang, Y., Zhang, Y., & Zhu, H. (2023, November 7). Medical image analysis using deep learning algorithms. Frontiers in public health. https://pmc.ncbi.nlm.nih.gov/articles/PMC10662291/
[12] Ahmed, R., Zhang, Y., Liu, Y., & Liao, H. (n.d.). Single Volume Image Generator and deep learning-based ASD classification | IEEE Journals & Magazine | IEEE Xplore. https://ieeexplore.ieee.org/document/9104007/
[13] Wang, Z., Yang, R., Wang, M., Zeng, N., & Liu, X. (2020, September 29). A review on transfer learning in EEG signal analysis. Neurocomputing. https://www.sciencedirect.com/science/article/abs/pii/S0925231220314223?via%3Dihub
[14] Chen, Y.-H., Chen, Q., Kong, L., & Liu, G. (2022, September 8). Early detection of autism spectrum disorder in young children with machine learning using medical claims data. BMJ Health & Care Informatics. https://informatics.bmj.com/content/29/1/e100544
[15] Zhang, M., Lu, J., Ma, N., Cheng, T. C. E., & Hua, G. (n.d.). A feature engineering and ensemble learning based approach for repeated buyers prediction. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL. https://univagora.ro/jour/index.php/ijccc/article/view/4988
[16] Saleh, A. Y., & Chern, L. H. (n.d.). Autism spectrum disorder classification using deep learning. International Journal of Online and Biomedical Engineering (iJOE). https://online-journals.org/index.php/i-joe/article/view/24603
[17] Wang, Zhengning, Peng, D., Shang, Y., & Gao, J. (2021, October 8). Autistic spectrum disorder detection and structural biomarker identification using self-attention model and individual-level morphological covariance brain networks. Frontiers in neuroscience. https://pmc.ncbi.nlm.nih.gov/articles/PMC8547518/
[18] Radhakrishnan, M., Ramamurthy, K., Shanmugam, S., Prasanna, G., S, V., Y, S., & Won, D. (2024). A hybrid model for the classification of autism spectrum disorder using MU rhythm in EEG. Technology and health care : official journal of the European Society for Engineering and Medicine. https://pmc.ncbi.nlm.nih.gov/articles/PMC11613045/#abstract1
[19] Tenenbaum, E. J., Major, S., Carpenter, K. L. H., Howard, J., Murias, M., & Dawson, G. (2021, October). Distance from typical scan path when viewing complex stimuli in children with autism spectrum disorder and its association with behavior. Journal of autism and developmental disorders. https://pmc.ncbi.nlm.nih.gov/articles/PMC9903808/
[20] McParland, A., Gallagher, S., & Keenan, M. (2021, December). Investigating gaze behaviour of children diagnosed with autism spectrum disorders in a classroom setting. Journal of autism and developmental disorders. https://pmc.ncbi.nlm.nih.gov/articles/PMC8531110/
[21] He, Q., Wang, Q., Wu, Y., Yi, L., & Wei, K. (2021, April 12). Automatic classification of children with autism spectrum disorder by using a computerized visual-orienting task. PsyCh journal. https://pubmed.ncbi.nlm.nih.gov/33847077/
[22] Cilia, F., Carette, R., Elbattah, M., Dequen, G., Guérin, J.-L., Bosche, J., Vandromme, L., & Driant, B. L. (n.d.). Computer-aided screening of autism spectrum disorder: EYE-tracking study using data visualization and deep learning. JMIR Human Factors. https://humanfactors.jmir.org/2021/4/e27706
[23] Fernández, D. N., Porras, F. B., Gilman, R. H., Mondonedo, M. V., Sheen, P., & Zimic, M. (2020, July 28). A convolutional neural network for Gaze Preference Detection: A potential tool for diagnostics of autism spectrum disorder in children. arXiv.org. https://arxiv.org/abs/2007.14432
[24] Jaradat, A. S., Wedyan, M., Alomari, S., & Barhoush, M. M. (2024a, December 30). Using machine learning to diagnose autism based on eye tracking technology. Diagnostics (Basel, Switzerland). https://pmc.ncbi.nlm.nih.gov/articles/PMC11719697/#sec5-diagnostics-15-00066
[25] Sun, B., Wang, B., Wei, Z., Feng, Z., Wu, Z.-L., Yassin, W., Stone, W., Lin, Y., & Kong, X.-J. (n.d.). Identification of diagnostic markers for ASD: A restrictive interest analysis based on EEG combined with Eye Tracking. Frontiers in neuroscience. https://pubmed.ncbi.nlm.nih.gov/37886678/
[26] Bohnsack, C. (2025, May 16). Autism through the years: How understanding has evolved over two decades. Southwest Autism Research & Resource Center (SARRC). https://autismcenter.org/autism-through-the-years
[27] Elbattah, M. (2023, May 30). Visualization of eye-tracking scanpaths in autism spectrum disorder: Image dataset. figshare. https://figshare.com/articles/dataset/Visualization_of_EyeTracking_Scanpaths_in_Autism_Spectrum_Disorder_Image_Dataset/7073087/1
[28] SMI. (2015, June). User Manual RED250mobile. Gaze Intelligence. https://drive.google.com/file/d/0B0hDAb1qZQkRMXVsTU5EeENVMjg/view?resourcekey=0-K1CxOFP0p1vcxgotfO5pQg
[29] Carette, R., Elbattah, M., Dequen, G., Guerin, J.-L., & Cilia, F. (2018). Visualization of eye-tracking patterns in autism spectrum disorder: Method and dataset | IEEE conference publication | IEEE xplore. IEEE. https://ieeexplore.ieee.org/document/8846967/
[30] Yan, F., Zhao, S., & Venegas-Andraca, S. E. (2020, October 20). Implementing bilinear interpolation on quantum images. arXiv.org. https://arxiv.org/abs/2010.10254
[31] Liu, M., Chen, L., Du, X., Jin, L., & Shang, M. (2021, September 1). Activated gradients for Deep Neural Networks | IEEE Journals & Magazine | IEEE Xplore. IEEE. https://ieeexplore.ieee.org/document/9526915/
[32] Simonyan, K., & Zisserman, A. (2015, April 10). Very deep convolutional networks for large-scale image recognition. arXiv.org. https://arxiv.org/abs/1409.1556
[33] O’Shea, K., & Nash, R. (2015, December 2). An introduction to Convolutional Neural Networks. arXiv.org. https://arxiv.org/abs/1511.08458
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
