Ensemble Learning Model for Screening Autism in Children

Abstract

Autistic Spectrum Disorder (ASD) is a neurological condition associated with communication, repetitive, and social challenges. 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 behavioural scientists. Potential technologies that may improve the reliability and accuracy of ASD tests are Artificial Intelligence and Machine Learning. This paper presents a new framework for ASD screening based on Ensembles Learning called Ensemble Classification for Autism Screening (ECAS). ECAS employs a powerful learning method that considers constructing multiple classifiers from historical cases and controls and then utilizes these classifiers to predict autistic traits in test instances. ECAS performance has been measured on a real dataset related to cases and controls of children and using different Machine Learning techniques. The results revealed that ECAS was able to generate better classifiers from the children dataset than the other Machine Learning methods considered in regard to levels of sensitivity, specificity, and accuracy.

Classification of Autistic Spectrum Disorder Using Deep Neural Network With Particle Swarm Optimization

“…The Decision Tree Classifier from scikit-learn, ADTree, CDT, J48, and LADTree classifiers have used, The experimental outcome they obtained the accuracy 90% using the decision tree classifiers (Hassan & Mokhtar, 2019). Diabat et al (2019) worked on the classifiers C4.5, PART, RIPPER and Voted Perceptron and Ensemble Classification for Autism Screening (ECAS). The outcome shows that the Ensemble Classification obtained the highest accuracy 100% compared to other models (Diabat & Al-shanableh, 2019).…”

“…Diabat et al (2019) worked on the classifiers C4.5, PART, RIPPER and Voted Perceptron and Ensemble Classification for Autism Screening (ECAS). The outcome shows that the Ensemble Classification obtained the highest accuracy 100% compared to other models (Diabat & Al-shanableh, 2019). Abdullah, Rijal, & Dash (2019) worked on feature selection technique Chi-square and Least Absolute Shrinkage and Selection Operator (LASSO) and classification algorithm Random Forest, Logistic Regression and K-Nearest Neighbors.…”

A predictive model for paediatric autism screening

“…Combining the output of multiple weak predictors to form a single strong predictor (ensembling) is a common technique in machine learning. 28 A proposed system called ensemble classification for autism screening (ECAS) 29 implements an ensemble approach to predict ASD from data collected via the ASDTests Android application 23,25 – described further in the next subsection – in children. The ensemble system performed better in benchmarks compared with other common machine learning algorithms.…”

Exploratory Data Analysis and Decision Tree Modeling for Autism Spectrum Disorder: Machine Learning Approach

“…[3] Yet, another analysis by Praveena et al predicted autism using machine learning techniques. [4] The present study uses ASD screening data of adults to design the machine learning framework for classifying autism data. [5]…”