Validating the AQ-10 Autism Screening Threshold Using Machine Learning Models
Abstract views: 12
/ 
PDF downloads: 8
DOI:
https://doi.org/10.31039/plic.2025.17.360Keywords:
Autism Spectrum Disorder, AQ-10, Machine Learning, Logistic Regression, Random Forest, Screening Models, Demographic VariabilityAbstract
Autism Spectrum Disorder (ASD) is a lifelong developmental condition for which early identification is essential. The Autism Quotient-10 (AQ-10) is frequently used as a quick screening instrument, classifying individuals scoring seven or more as potentially autistic. This study applies machine learning (ML) models to a public AQ-10 dataset to determine whether predictive algorithms can provide insights beyond the rule-based threshold. Logistic Regression and Random Forest classifiers were built, validated, and compared. Both models demonstrated perfect scores on all evaluation metrics, reflecting the deterministic nature of the dataset rather than offering new diagnostic information. Demographic examination revealed meaningful differences in screening patterns across gender, age groups, ethnicity, and family history of ASD. These findings emphasize that ML models trained on threshold-derived labels cannot infer clinical patterns beyond the embedded scoring rule. Future work will require clinician-confirmed datasets and multimodal features to meaningfully advance computational autism screening.References
C. Lord et al., 'Autism spectrum disorder,' The Lancet, vol. 395, no. 10242, pp. 908–922, 2020.
C. Allison et al., 'Toward brief red flags for autism screening,' J. Am. Acad. Child Adolesc. Psychiatry, vol. 51, no. 2, pp. 202–212, 2012.
A. Esteva et al., 'A guide to deep learning in healthcare,' Nat. Med., vol. 25, no. 1, pp. 24–29, 2019.
C. M. Bishop, Pattern Recognition and Machine Learning. Springer, 2006.
F. Pedregosa et al., 'Scikit-learn: Machine learning in Python,' J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
A L. Murray et al., 'Are autistic traits measured equivalently in females and males?,' Psychol. Assess., vol. 29, no. 7, pp. 796–802, 2017.
D Rynkiewicz et al., 'Gender bias in autism screening,' Front. Psychiatry, vol. 14, Article 1173121, 2023.
F. Ehsan et al., 'AutoML frameworks for autism spectrum disorder screening,' Front. Psychiatry, vol. 16, pp. 112–124, 2025.
J. Li et al., 'Explainable AI for autism spectrum disorder screening,' Cogn. Neurodyn., vol. 19, no. 2, pp. 233–245, 2025.
A. Lai et al., 'Cultural and gender differences in autism diagnosis,' Brain Sci., vol. 11, no. 7, Article 912, 2021.
Allison, C., Auyeung, B., & Baron-Cohen, S. (2012). Toward brief ‘red flags’ for autism screening: The Autism Spectrum Quotient (AQ–10). *Journal of the American Academy of Child & Adolescent Psychiatry, 51*(2), 202–212.
Bishop, C. M. (2006). *Pattern Recognition and Machine Learning.* Springer.
Chen, G., Zhang, L., & Wang, Y. (2024). Fairness in medical AI: Addressing bias in autism spectrum disorder detection models. *Artificial Intelligence in Medicine, 150*, 102512.
Ehsan, F., Smith, R., & Zhou, T. (2025). AutoML frameworks for autism spectrum disorder screening. *Frontiers in Psychiatry, 16*, 112–124.
Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., ... & Dean, J. (2019). A guide to deep learning in healthcare. *Nature Medicine, 25*(1), 24–29.
Hosseini, S., & Ghassemi, M. (2022). Explainable deep learning for autism diagnosis using behavioral data. *IEEE Journal of Biomedical and Health Informatics, 26*(12), 6415–6424.
Lai, M.-C., Lombardo, M. V., & Baron-Cohen, S. (2021). Cultural and gender differences in autism diagnosis. *Brain Sciences, 11*(7), 912.
Li, J., Wang, X., & Zhang, Y. (2025). Explainable AI for autism spectrum disorder screening. *Cognitive Neurodynamics, 19*(2), 233–245.
Lord, C., Elsabbagh, M., Baird, G., & Veenstra-VanderWeele, J. (2020). Autism spectrum disorder. *The Lancet, 395*(10242), 908–922.
Murray, A. L., Booth, T., McKenzie, K., Kuenssberg, R., & O’Donnell, M. (2017). Are autistic traits measured equivalently in females and males? *Psychological Assessment, 29*(7), 796–802.
Narayanan, A., & Kumar, P. (2023). Evaluating threshold-based autism screening with logistic regression. *Computers in Biology and Medicine, 162*, 107036.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. *Journal of Machine Learning Research, 12*, 2825–2830.
Rynkiewicz, D., Łucka, I., & Baron-Cohen, S. (2023). Gender bias in autism screening: A review and meta-analysis. *Frontiers in Psychiatry, 14*, 1173121.
Tanaka, J. W., & Sung, A. (2021). The reliability of self-report screening tools for autism spectrum disorder in adults. *Autism Research, 14*(9), 1894–1905.
Zhou, Z., Li, P., & Zhao, Q. (2025). Integrating multimodal features for early autism prediction using hybrid neural networks. *Frontiers in Neuroscience, 19*, 1345628.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Deepika Chandrashekar, B. Vasumathi
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
You are free to:
Share: copy and redistribute the material in any medium or format. The licensor cannot revoke these freedoms as long as you follow the license terms. Under the following terms: Attribution-NonCommercial-NoDerivatives-No additional restrictions.
Authors retain copyright and agree to license their articles with a Creative Commons Attribution-NonCommercial-
