International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 10 | Oct 2024
p-ISSN: 2395-0072
www.irjet.net
Predicting Autism Spectrum Disorder Using the K-Nearest Neighbours Algorithm in Machine Learning Sakshi Gupta1, Dr. dayashankar Pandey2 1M Tech Scholar Dept. of Information Technology, RKDF IST SRK UNIVERSITY, BHOPAL 2HOD, Dept. of Information Technology, RKDF IST SRK UNIVERSITY, BHOPAL
----------------------------------------------------------------------***----------------------------------------------------------------------Abstract This research paper investigates the prediction of Autism Spectrum Disorder (ASD) using the K-Nearest Neighbours (KNN) algorithm in machine learning. Autism is a neurodevelopmental disorder characterized by challenges in social interaction, communication, and repetitive behaviours. Early diagnosis is critical to enable timely intervention, yet diagnosing ASD can be a complex process due to the variation in symptoms. In this study, we explore the use of KNN as a predictive tool to identify potential cases of ASD based on behavioural and demographic data. The performance of the KNN algorithm is evaluated using a publicly available dataset, and we assess its accuracy, precision, recall, and F1 score. The results demonstrate that the KNN algorithm is a viable method for predicting ASD, although there are limitations in terms of sensitivity and specificity that require further refinement.
Keywords: Autism Disorder, KNN Algorithm, Machine learning, ASD, K Nearest Neighbours etc I.
Introduction
Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition that affects an individual’s ability to communicate and interact with others. The global prevalence of ASD is estimated to be around 1 in 160 children, according to the World Health Organization. ASD is typically diagnosed based on behavioural assessments conducted by clinicians, which can be subjective and time-consuming. As a result, there is a growing interest in developing automated tools to assist in the early diagnosis of ASD, which can lead to timely interventions and improved outcomes for individuals affected by the disorder. Machine learning (ML) offers a promising avenue for the early detection and diagnosis of ASD. By leveraging large datasets and powerful computational algorithms, machine learning models can identify patterns and relationships in data that may be difficult for humans to discern. Among the various machine learning algorithms, the K-Nearest Neighbours (KNN) algorithm stands out due to its simplicity, interpretability, and effectiveness in classification tasks. KNN is a non-parametric algorithm that classifies data points based on the majority class of their nearest neighbours in the feature space. It is widely used in medical research due to its ability to handle non-linear relationships and multi-dimensional data. This paper aims to explore the application of the KNN algorithm in predicting ASD, using publicly available datasets that contain demographic and behavioural information of individuals. We hypothesize that KNN can serve as an effective tool for predicting ASD, particularly when used in conjunction with feature selection and optimization techniques.
II. Literature Survey Autism Spectrum Disorder (ASD) is marked by heterogeneity in symptoms and severity, which poses a significant challenge to clinicians when diagnosing the disorder. Traditional diagnostic methods, such as the Autism Diagnostic Observation Schedule (ADOS) and the Autism Diagnostic Interview-Revised (ADI-R), rely heavily on human judgment, which can lead to variability in diagnosis. Furthermore, the time-intensive nature of these assessments may delay the initiation of intervention, which is critical for improving long-term outcomes. Numerous studies have explored the potential of automated diagnostic tools for ASD. For instance, the use of machine learning techniques has gained traction due to their ability to process large datasets and detect subtle patterns in data. Researchers have employed various machine learning algorithms, including decision trees, support vector machines, neural networks, and KNN, to predict ASD based on behavioural, genetic, and imaging data.
© 2024, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 403