New improved model for Autism Detection and Prediction based on AQ-10 test by using Artificial Neural Network

被引：0
作者：
Mahi Sarra [1 ]
Imedjdouben Fayçal [1 ]
Ridouh Abdelhakim [1 ]
机构：
[1] Department of Computational Linguistics, Scientific and Technical Research Center for the Development of the Arabic Language (CRSTDLA), PO Box 225, Algiers, El Rustamia, Bouzareah
来源：
Journal of Ambient Intelligence and Humanized Computing | 2025年 / 16卷 / 1期
关键词：
ANN; AQ-10; model; Autism spectrum disorder; New model;
D O I：
10.1007/s12652-024-04945-1
中图分类号：
学科分类号：
摘要：
Autism spectrum disorder (ASD) is a neurodevelopment disorder characterized by difficulties in social skills, repetitive behaviors, speech, and nonverbal communication. While there are various diagnostic methods used for ASD assesses, this work focuses on the Autism Quotient Trait 10 (AQ-10) which is a non-clinical diagnostic method that assesses autism in children, adolescents, and adults using 10 questions. However, the AQ-10 in its current form can only detects the presence of ASD without providing additional information. To improve the AQ-10’s detection capacity, we propose a new model based on AQ-10 that assigns weights to each question, as opposed to the initial model that assumes all questions have the same influence on the results. Our model, named as Mahi’s model, improves the number of classes from 10 to an interval between − 20 and 60, allowing for precise tracking of autism variations within the same class. We employ an Artificial Neural Network to estimate weight matrices and train our model on an open database containing 509 cases of individuals of different ages and genders of child. The results show a strong correlation between the output of our model and the real data. The results obtained demonstrate the potential of our new model to enhance early identification and support for individuals with autism spectrum disorder. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.
引用
收藏
页码：295 / 302
页数：7
相关论文
共 24 条
  • [1] Agrawal P., Dewangan A., A brief survey on the techniques used for the diagnosis of diabetes-mellitus, Int Res J Eng Tech, 2, pp. 1039-1043, (2015)
  • [2] Allison C., Auyeung B., Baron-Cohen S., Toward brief “red flags” for autism screening: the short autism spectrum quotient and the short quantitative checklist in 1000 cases and 3000 controls, J Am Acad Child Adoles Psychiatry, 51, pp. 202-212, (2012)
  • [3] Almuqhim F., Saeed F., Aasd-saenet: A sparse autoencoder, and deep-neural network model for detecting autism spectrum disorder (asd) using fmri data, Front. Comput. Neurosci, (2021)
  • [4] Asperger H.D., Autistischen psychopathen” im kindesalter, Arch Psychiatr, 117, pp. 76-136, (1944)
  • [5] Autism Spectrum Disorder in Adults: Diagnosis and Management
  • [6] Baron-Cohen S., Wheelwright S., Skinner R., Martin J., Clubley E., The autism-spectrum quotient (aq): evidence from asperger syndrome/high-functioning autism, males and females, scientists and mathematicians, J Autism Dev Disord, 31, pp. 5-1, (2001)
  • [7] Chris J.P., Scott M., Autism spectrum disorders, Developmental-Behavioral Pediatrics, pp. 519-577, (2008)
  • [8] Colgill S., Wang L., Support vector machine model of developmental brain gene expression data for prioritization of autism risk gene candidates, Bioinform Adv Access, 32, pp. 3611-3618, (2016)
  • [9] Dar J.A., Srivastava K.K., Lone S.A., Spectral features and optimal hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals, Biomed Signal Process Control, 78, (2022)
  • [10] Dar J.A., Srivastava K.K., Lone S.A., Design and development of hybrid optimization enabled deep learning model for covid-19 detection with comparative analysis with dcnn, biat-gru, xgboost, Comput Biol Med, 150, (2022)
123