A Systematic Approach to Autism Spectrum Disorder Diagnosis Using Optimized Machine Learning Models
Main Article Content
Abstract
Autism Spectrum Disorder (ASD) is a developmental neurodisorder that is marked by impaired socialization and behavioural problems. Things should be detected and treated at an early stage. This project involves the development of a solid predictive model to be applied in ASD by using two datasets- the Autism Spectrum Disorder Screening Data, which is a dataset of a toddler screening program in Saudi Arabia, and the Autism Prediction Dataset. Data preparation, feature engineering, and selection of the algorithm are extensive parts of this process as they would improve the overall classification accuracy of the model. Several machine learning algorithms (Random Forest, Support Vector Machine (SVM), Gradient Boosting, and Neural Networks) are trained using accuracy, precision, recall, and F1-score= measures, and compared. Also, an Explainable Artificial Intelligence (XAI) framework is included to provide greater insight into the model forecasts thereby providing a more transparent decision-making process. According to the results, it is possible to state that the proposed algorithm performs better than the existing methods in ASD detection. Results indicate the possible opportunities of medical tools driven by AI to support decision-making by a caregiver, and one can expect the integration of such models into preventative healthcare systems in the future. Future activities might include expanding the data and make these models applicable.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
IJCERT Policy:
The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.
By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.
References
A. Genovese and M. G. Butler, “Clinical assessment, genetics, and treatment approaches in autism spectrum disorder (ASD),” International Journal of Molecular Sciences, vol. 21, no. 13, p. 4726, 2020.
V. Milner, H. McIntosh, E. Colvert, and F. Happé, “A qualitative exploration of the female experience of autism spectrum disorder (ASD),” Journal of Autism and Developmental Disorders, vol. 49, no. 6, pp. 2389–2402, 2019.
J. N. Constantino and T. Charman, “Diagnosis of autism spectrum disorder: reconciling the syndrome, its diverse origins, and variation in expression,” The Lancet Neurology, vol. 15, no. 3, pp. 279–291, 2016.
S. S. Rajagopalan, Y. Zhang, A. Yahia, and K. Tammimies, “Using minimal medical data for ASD prediction via machine learning models,” JAMA Network Open, vol. 7, no. 8, p. e2429229, 2024, doi: 10.1001/jamanetworkopen.2024.29229.
U. J. Ganai, A. Ratne, B. Bhushan, and K. S. Venkatesh, “Early detection of autism spectrum disorder: gait deviations and machine learning,” Sci. Rep., vol. 15, no. 1, p. 873, 2025.
Y. Ding, H. Zhang, and T. Qiu, “RETRACTED ARTICLE: Deep learning approach to predict autism spectrum disorder: a systematic review and meta-analysis,” BMC Psychiatry, vol. 24, no. 1, 2024.
J. Song et al., “Combining radiomics and machine learning approaches for objective ASD diagnosis: Verifying white matter associations with ASD,” arXiv [eess.IV], 2024.
S. Rubio-Martín, M. T. García-Ordás, M. Bayón-Gutiérrez, N. Prieto-Fernández, and J. A. Benítez-Andrades, “Enhancing ASD detection accuracy: a combined approach of machine learning and deep learning models with natural language processing,” Health Inf. Sci. Syst., vol. 12, no. 1, 2024
R. A. Bahathiq, H. Banjar, A. K. Bamaga, and S. K. Jarraya, “Machine learning for autism spectrum disorder diagnosis using structural magnetic resonance imaging: Promising but challenging,” Front. Neuroinform., vol. 16, no. 949926, 2022.
V. Ramesh and R. Assaf, “Detecting autism spectrum disorders with machine learning models using speech transcripts,” arXiv [cs.LG], 2021.
S. S. Rajagopalan, Y. Zhang, A. Yahia, and K. Tammimies, “Machine learning for autism spectrum disorder prediction with limited medical and background data,” JAMA Network Open, vol. 7, no. 8, p. e2429229, 2024.
Z. Yin et al., “Early autism diagnosis based on path signature and Siamese unsupervised feature compressor,” Cereb. Cortex, vol. 34, no. 13, pp. 72–83, 2024.
S. S. Rajagopalan, Y. Zhang, A. Yahia, and K. Tammimies, “Minimal data for autism spectrum disorder prediction using machine learning,” JAMA Network Open, vol. 7, no. 8, p. e2429229, 2024.
https://www.kaggle.com/datasets/jayaprakashpondy/autism-spectrum-disorder
https://www.kaggle.com/datasets/asdpredictioninsaudi/asd-screening-data-for-toddlers-in-saudi-arabia