Autism Detection System Using Machine Learning
Keywords:
SVM, Logistic regression, Random Fores, Decision tree, Stream litAbstract
Autism spectrum disorder (ASD) is a complicated neurological illness that significantly affects a person's interests, behaviour, interaction with others, and communication abilities. Early intervention and encouragement can dramatically improve outcomes for those affected; hence, early recognition of ASD is critical. This study proposes а novel method for diagnosing autism spectrum disorder (ASD) In children aged 0 to 6, utilizing machine learning techniques such as Support Vector Machines (SVM), Logistic Regression, Random Forest, and Decision Trees. The proposed concept is intended to be a simple-to-use web application for ASD diagnosis, which takes advantage of the open-source application framework Stream lit and the programming language Python. Because of the tool's easy-to-use design, healthcare practitioners and caregivers may rapidly enter relevant data and obtain a reliable estimate of the possibility of an ASD. The model has received high accuracy rates for all three algorithms after extensive testing and validation, demonstrating its potential as a helpful and trustworthy tool to perform early detection of autism spectrum disorders in children. This work highlights the importance of technological advancements in improving healthcare outcomes for persons with ASD and contributes to the growing body of research on the application of machine learning methods to the early identification of ASD.
Downloads
References
[1] Elsabbagh, M., Bolton, P., Dawson, G., Guicciardi, M. E., Johnson, M. H., Karimi, L. H., ... & Charman, T. (2012). Autism spectrum disorders: early identification and intervention. The Lancet, 379(9813), 230-231.
[2] Rodriguez, A., Gutierrez-Barrera, A., Bravo, D., & Quiroz, J. (2016). Machine learning algorithms for autism. Detection and classification based on eye-tracking data. Journal of Neural Engineering, 13(2), 026004.
[3] Yahata, N., Mori, Y., Nakai, K., More, K., & Kubokawa, Y. (2016). Autism spectrum disorder classification using auditory event-related potentials with high temporal resolution. Journal of Biomedical Engineering, 19(1), 103-113.
[4] Duda, R. O., Hart, P. E., & Stork, D. G. (2016). Pattern Classification, 2nd ed. Wiley, New York.
[5] Bottaci, L. (2017). The need for external validation in medical prediction models. BMC Medical Research Methodology, 17(1), 49.
[6] Chicco, D., & Jürgen Jost, J. (2020). The accuracy paradox in predictive classification tasks. Communications in Statistics-Theory and Methods, 49(4), 1665-1678.
[7] Moons, K. G. M., Altman, D. G., Reitsma, J. B., & Ioannidis, J. P. A. (2020). Transparentreporting of assessments in machine learning: the TRAIML statement. Statistics in Medicine, 39(11), 2327-2341.
[8] Alaa, A. M., & van der Schaar, M. (2019). Validating deep learning models for predicting patient outcomes. arXiv preprint arXiv:1907.05017.
[9] Rao, C. R., & Chen, L. (2020). Causal inference in health sciences. Annual Review of Statistics and Its Application, 7,435-459.
[10] Rajkomar, A., Hardt, M., & Doshi-Velez, F. (2019). Ensuring fairness in machine learning for healthcare: pre-processing-based approaches. Journal of Healthcare Engineering, 2019, 1-21.
[11] Holmström, J., & Li, S. (2019). Fairness in machine learning for health care: concept and preliminary results. Journal of the American Medical Informatics Association, 26(3), 287-295.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal for Research Publication and Seminar
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
