Early Detection of Autism Spectrum Disorders (ASD) with the Help of Data Mining Tools

Autism is a disorder of neurobiological origin that originates a different course in the development of verbal and nonverbal communication, social interactions, the flexibility of behavior, and interests. The results obtained offer relevant information to reflect on the practices currently used in a...

Full description

Saved in:
Bibliographic Details
Published in:BioMed research international 2022-05, Vol.2022, p.1201129-10
Main Authors: Abdulrazzaq, Ammar Akram, Hamid, Sana Sulaiman, Al-Douri, Asaad T., Mohamad, A. A. Hamad, Ibrahim, Abdelrahman Mohamed
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Autism
Autism Spectrum Disorder - diagnosis
Autistic Disorder - psychology
Child
Children
Classification
Clustering
Data collection
Data Mining
Datasets
Developmental disabilities
Diagnosis
Digitizing
Disorders
Fuzzy logic
Humans
Illnesses
Insomnia
Intellectual disabilities
Linguistics
Medical personnel
Methods
Missing data
Neural networks
Neurodevelopmental disorders
Normalizing
Pervasive developmental disorders
Psychology
Social factors
Social interactions
Success
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Autism is a disorder of neurobiological origin that originates a different course in the development of verbal and nonverbal communication, social interactions, the flexibility of behavior, and interests. The results obtained offer relevant information to reflect on the practices currently used in assessing the development of children and the detection of ASD and suggest the need to strengthen the training of health professionals in aspects such as psychology and developmental disorders. This study, based on genuine and current facts, used data from 292 children with an autism spectrum disorder. The input dataset has 20 characteristics, and the output dataset has one attribute. The output property indicates whether or not a certain person has autism. The research study first and foremost performed data pretreatment activities such as filling in missing data gaps in the data collection, digitizing categorical data, and normalizing. The features were then clustered using k-means and x-means clustering methods, then artificial neural networks and a linguistic strong neurofuzzy classifier were used to classify them. The outcomes of each strategy were examined, and their respective performances were compared.
ISSN:2314-6133
2314-6141
DOI:10.1155/2022/1201129