Ann Autism Developmental Disord | Volume 1, Issue 1 | Review Article | Open Access

Optimized Machine Learning Classification Approaches for Prediction of Autism Spectrum Disorder

Devika Varshini G and Chinnaiyan R*

Department of Information Science and Engineering, CMR Institute of Technology, India

*Correspondance to: Chinnaiyan R 

Fulltext PDF

Abstract

Autism spectrum disorder is a serious developmental disorder that impairs the ability to communicate and interact. ASD screening is the process of detecting potential autistic traits in individuals using tests conducted by a medical professional, a caregiver, or a parent. These tests often contain large numbers of items to be covered by the user and they generate a score based on scoring functions designed by psychologists and behavioral scientists. In this paper, the effectiveness of various machine learning algorithms and pre- processing techniques for the task of classification for medical datasets that are used for predicting the early autism traits in toddlers and adults is evaluated. Several previous work in this direction use complex pre-processing and machine
learning techniques for effective classification. However, this experiment establish that a simple pre-processing steps combined with appropriate encoding of data and different classifier algorithms like logistic regression, KNN and Random Forest give rise to comparable results with the state-of-the-art.

Keywords:

Autism; Disorder; Classification; Logic regression; KNN; Random forest

Citation:

Devika Varshini G, Chinnaiyan R. Optimized Machine Learning Classification Approaches for Prediction of Autism Spectrum Disorder. Ann Autism Dev Disord. 2020;1(1):1001.
.

Subscribe to Our Newsletter