A machine learning autism classification based on logistic regression analysis

Fadi Thabtah, Neda Abdelhamid, David Peebles

Research output: Contribution to journalArticle

Abstract

Autistic Spectrum Disorder (ASD) is a neurodevelopmental condition associated with significant healthcare costs; early diagnosis could substantially reduce these. The economic impact of autism reveals an urgent need for the development of easily implemented and effective screening methods. Therefore, time-efficient ASD screening is imperative to help health professionals and to inform individuals whether they should pursue formal clinical diagnosis. Presently, very limited autism datasets associated with screening are available and most of them are genetic in nature. We propose new machine learning framework related to autism screening of adults and adolescents that contain vital features and perform predictive analysis using Logistic Regression to reveal important information related to autism screening. We also perform an in-depth feature analysis on the two datasets using information gain (IG) and chi square testing (CHI) to determine the influential features that can be utilized in screening for autism. Results obtained reveal that machine learning technology was able to generate classification systems that have acceptable performance in terms of sensitivity, specificity and accuracy among others.
Original languageEnglish
Number of pages11
JournalHealth Information Science and Systems
Volume7
Issue number12
Early online date1 Jun 2019
DOIs
Publication statusPublished - 1 Dec 2019

Fingerprint

Autistic Disorder
Logistic Models
Regression Analysis
Machine Learning
Health Care Costs
Early Diagnosis
Economics
Technology
Sensitivity and Specificity
Health

Cite this

@article{224473dfdf4642ac8193b90e1a198dcc,
title = "A machine learning autism classification based on logistic regression analysis",
abstract = "Autistic Spectrum Disorder (ASD) is a neurodevelopmental condition associated with significant healthcare costs; early diagnosis could substantially reduce these. The economic impact of autism reveals an urgent need for the development of easily implemented and effective screening methods. Therefore, time-efficient ASD screening is imperative to help health professionals and to inform individuals whether they should pursue formal clinical diagnosis. Presently, very limited autism datasets associated with screening are available and most of them are genetic in nature. We propose new machine learning framework related to autism screening of adults and adolescents that contain vital features and perform predictive analysis using Logistic Regression to reveal important information related to autism screening. We also perform an in-depth feature analysis on the two datasets using information gain (IG) and chi square testing (CHI) to determine the influential features that can be utilized in screening for autism. Results obtained reveal that machine learning technology was able to generate classification systems that have acceptable performance in terms of sensitivity, specificity and accuracy among others.",
keywords = "Autism Spectrum Disorder, Classification, Clinical decision making, Data mining, Feature analysis, Machine learning, Sensitivity, Specificity",
author = "Fadi Thabtah and Neda Abdelhamid and David Peebles",
year = "2019",
month = "12",
day = "1",
doi = "10.1007/s13755-019-0073-5",
language = "English",
volume = "7",
journal = "Health Information Science and Systems",
issn = "2047-2501",
publisher = "Springer London",
number = "12",

}

A machine learning autism classification based on logistic regression analysis. / Thabtah, Fadi; Abdelhamid, Neda; Peebles, David.

In: Health Information Science and Systems, Vol. 7, No. 12, 01.12.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A machine learning autism classification based on logistic regression analysis

AU - Thabtah, Fadi

AU - Abdelhamid, Neda

AU - Peebles, David

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Autistic Spectrum Disorder (ASD) is a neurodevelopmental condition associated with significant healthcare costs; early diagnosis could substantially reduce these. The economic impact of autism reveals an urgent need for the development of easily implemented and effective screening methods. Therefore, time-efficient ASD screening is imperative to help health professionals and to inform individuals whether they should pursue formal clinical diagnosis. Presently, very limited autism datasets associated with screening are available and most of them are genetic in nature. We propose new machine learning framework related to autism screening of adults and adolescents that contain vital features and perform predictive analysis using Logistic Regression to reveal important information related to autism screening. We also perform an in-depth feature analysis on the two datasets using information gain (IG) and chi square testing (CHI) to determine the influential features that can be utilized in screening for autism. Results obtained reveal that machine learning technology was able to generate classification systems that have acceptable performance in terms of sensitivity, specificity and accuracy among others.

AB - Autistic Spectrum Disorder (ASD) is a neurodevelopmental condition associated with significant healthcare costs; early diagnosis could substantially reduce these. The economic impact of autism reveals an urgent need for the development of easily implemented and effective screening methods. Therefore, time-efficient ASD screening is imperative to help health professionals and to inform individuals whether they should pursue formal clinical diagnosis. Presently, very limited autism datasets associated with screening are available and most of them are genetic in nature. We propose new machine learning framework related to autism screening of adults and adolescents that contain vital features and perform predictive analysis using Logistic Regression to reveal important information related to autism screening. We also perform an in-depth feature analysis on the two datasets using information gain (IG) and chi square testing (CHI) to determine the influential features that can be utilized in screening for autism. Results obtained reveal that machine learning technology was able to generate classification systems that have acceptable performance in terms of sensitivity, specificity and accuracy among others.

KW - Autism Spectrum Disorder

KW - Classification

KW - Clinical decision making

KW - Data mining

KW - Feature analysis

KW - Machine learning

KW - Sensitivity

KW - Specificity

U2 - 10.1007/s13755-019-0073-5

DO - 10.1007/s13755-019-0073-5

M3 - Article

VL - 7

JO - Health Information Science and Systems

JF - Health Information Science and Systems

SN - 2047-2501

IS - 12

ER -