Early Detection of Autism Spectrum Disorder Using Deep Learning

  • Unique Paper ID: 176336
  • PageNo: 6383-6389
  • Abstract:
  • The early identification of Autism Spectrum Disorder (ASD) presents a pressing need in the global healthcare community. ASD is a neurodevelopmental disorder that affects social interaction, communication, and behavior, often resulting in long-term challenges when not addressed early. Traditional diagnostic methods, although effective, are often time-consuming, resource-intensive, and inaccessible to underprivileged communities. This research introduces a deep learning-based system designed to assist in the early screening of ASD using structured datasets derived from behavioral questionnaires and demographic data. The system implements a Multi-Layer Perceptron (MLP) model utilizing Keras, aiming for high classification accuracy with minimal false positives. The paper begins by providing a comprehensive background on ASD, including its symptoms, causes, and the importance of early diagnosis. It then explores current diagnostic practices and the challenges faced by healthcare professionals. The focus then shifts to the role of deep learning algorithms in transforming healthcare diagnostics and introduces the specific model architecture developed in this study. A detailed explanation of the dataset, preprocessing techniques, model structure, training methodology, and evaluation metrics is provided.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{176336,
        author = {Swetha C and Hasini Kanchetty and Ajay Boddu and Brahma Reddy},
        title = {Early Detection of Autism Spectrum Disorder Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {6383-6389},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176336},
        abstract = {The early identification of Autism Spectrum Disorder (ASD) presents a pressing need in the global healthcare community. ASD is a neurodevelopmental disorder that affects social interaction, communication, and behavior, often resulting in long-term challenges when not addressed early. Traditional diagnostic methods, although effective, are often time-consuming, resource-intensive, and inaccessible to underprivileged communities. This research introduces a deep learning-based system designed to assist in the early screening of ASD using structured datasets derived from behavioral questionnaires and demographic data. The system implements a Multi-Layer Perceptron (MLP) model utilizing Keras, aiming for high classification accuracy with minimal false positives.
The paper begins by providing a comprehensive background on ASD, including its symptoms, causes, and the importance of early diagnosis. It then explores current diagnostic practices and the challenges faced by healthcare professionals. The focus then shifts to the role of deep learning algorithms in transforming healthcare diagnostics and introduces the specific model architecture developed in this study. A detailed explanation of the dataset, preprocessing techniques, model structure, training methodology, and evaluation metrics is provided.},
        keywords = {Autism Spectrum Disorder, Deep Learning, Neural Networks, Early Diagnosis, Keras, Behavioral Screening, Healthcare AI, Machine Learning in Medicine},
        month = {April},
        }

Cite This Article

C, S., & Kanchetty, H., & Boddu, A., & Reddy, B. (2025). Early Detection of Autism Spectrum Disorder Using Deep Learning. International Journal of Innovative Research in Technology (IJIRT), 11(11), 6383–6389.

Related Articles