Automatic classification of autism spectrum disorder in children using cortical thickness and support vector machine

Event-related potentials (ERPs) activated by faces and gaze processing are found in individuals with autism spectrum disorder (ASD) in the early stages of their development and may serve as a putative biomarker to supplement behavioral diagnosis. We present a novel approach to the classification of visual ERPs collected from 6-month-old infants using intrinsic mode functions (IMFs) derived from empirical mode decomposition (EMD). Selected features were used as inputs to two machine learning methods (support vector machines and k-nearest neighbors (k-NN)) using nested cross validation. Different runs were executed for the modelling and classification of the participants in the control and high-risk (HR) groups and the classification of diagnosis outcome within the high-risk group: HR-ASD and HR-noASD. The highest accuracy in the classification of familial risk was 88.44%, achieved using a support vector machine (SVM). A maximum accuracy of 74.00% for classifying infants at risk who go on to develop ASD vs. those who do not was achieved through k-NN. IMF-based extracted features were highly effective in classifying infants by risk status, but less effective by diagnostic outcome. Advanced signal analysis of ERPs integrated with machine learning may be considered a first step toward the development of an early biomarker for ASD.

Download Full-text

A Speech Emotion Recognition Solution-based on Support Vector Machine for Children with Autism Spectrum Disorder to Help Identify Human Emotions

2020 Intermountain Engineering, Technology and Computing (IETC) ◽

10.1109/ietc47856.2020.9249147 ◽

2020 ◽

Author(s):

Rezwan Matin ◽

Damian Valles

Keyword(s):

Autism Spectrum Disorder ◽

Support Vector Machine ◽

Emotion Recognition ◽

Children With Autism ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Speech Emotion Recognition ◽

Support Vector ◽

Human Emotions

Download Full-text

Prediksi Gejala Autism Spectrum Disorders pada Remaja Menggunakan Optimasi Particle Swarm Optimization dan Algoritma Support Vector Machine

INFORMATICS FOR EDUCATORS AND PROFESSIONAL : Journal of Informatics ◽

10.51211/itbi.v4i2.1306 ◽

2020 ◽

Vol 4 (2) ◽

pp. 113

Author(s):

Ilham Kurniawan

Keyword(s):

Autism Spectrum Disorder ◽

Support Vector Machine ◽

Feature Selection ◽

Particle Swarm ◽

Autism Spectrum ◽

Classification Algorithm ◽

Spectrum Disorder ◽

Support Vector ◽

Svm Classification ◽

Proposed Model

Abstrak: Telah ada peningkatan prevalensi diagnosis Autism Spectrum Disorder (ASD) secara global selama dekade terakhir. Perkiraan prevalensi ASD yang diperbarui dan keseluruhan di Asia akan membantu para profesional kesehatan untuk mengembangkan strategi kesehatan masyarakat yang relevan. Dalam penelitian ini, mengusulkan metode untuk prediksi gejala ASD menggunakan teknik integrasi seleksi fitur PSO dan algoritma Support Vector Machine. Penelitian ini menggunakan dataset dari UCI repository. Model yang diusulkan meliputi penerapan seleksi fitur menggunakan particle swarm optimization (PSO), dengan algoritma pengklasifikasi. Hasil akhir akan dilakukan perbandingan pengujian dan analisa terhadap model prediksi yang memiliki tingkat akurasi tertinggi atau terbaik dalam prediksi gejala ASD. Dalam penelitian ini menggunakan dataset UCI repository yaitu data ASD pada remaja, data tersebut memiliki jumlah data sebanyak 104 instance dan 21 atribut, 41 orang tidak menderita ASD dan 63 orang menderita ASD, tools yang digunakan untuk menerapkan model usulan menggunakan aplikasi Weka versi 3.8.4. Untuk mengetahui model usulan yang diajukan pada penelitian ini, pertama menguji dengan klasifikasi tunggal SVM, dan kedua, menguji dengan seleksi fitur PSO dan algoritma klasifikasi SVM. Untuk mengetahui apakah seleksi fitur PSO berpengaruh terhadap performa algoritma klasifikasi SVM. Pengujian pertama, nilai akurasi yang dihasilkan oleh algoritma klasifikasi SVM adalah sebesar 89.42%, dan nilai AUC sebesar 0.891. Berdasarkan pengujian yang kedua yaitu menggunakan seleksi fitur PSO, seleksi fitur PSO dapat meningkatkan performa algoritma klasifikasi SVM sebesar 2,88% dan nilai AUC sebesar 0,024. Kata kunci: Autism Spectrum Disorder, Particle Swarm Optimizatio, Support Vector Machine Abstract: There has been an increase in the prevalence of diagnoses of Autism Spectrum Disorder (ASD) globally over the past decade. Updated and overall ASD prevalence estimates in Asia will help health professionals to develop relevant public health strategies. In this study, proposing a method for ASD symptom prediction using PSO feature selection integration techniques and the Support Vector Machine algorithm. This study uses a dataset from the UCI repository. The proposed model includes the application of feature selection using particle swarm optimization (PSO), with the classification algorithm. The final result will be a comparison test and analysis of prediction models that have the highest or best accuracy in predicting ASD symptoms. In this study using the UCI repository dataset, ASD data on adolescents, the data has 104 data and 21 attributes, 41 people do not suffer from ASD and 63 people suffer from ASD, tools used to implement the proposed model using the Weka application version 3.8.4 . To find out the proposed model proposed in this study, firstly testing with SVM single classification, and secondly, testing with PSO feature selection and SVM classification algorithm. To find out whether the PSO feature selection affects the performance of the SVM classification algorithm. The first test, the accuracy value generated by the SVM classification algorithm is 89.42%, and the AUC value is 0.891. Based on the second test using PSO feature selection, PSO feature selection can improve the performance of the SVM classification algorithm by 2.88% and the AUC value of 0.024. Keywords: Autism Spectrum Disorder, Particle Swarm Optimizatio, Support Vector Machine.

Download Full-text

Predicting symptom severity in autism spectrum disorder based on cortical thickness measures in agglomerative data

10.1101/039180 ◽

2016 ◽

Cited By ~ 1

Author(s):

Elaheh Moradi ◽

Budhachandra Khundrakpam ◽

John D. Lewis ◽

Alan C. Evans ◽

Jussi Tohka

Keyword(s):

Machine Learning ◽

Autism Spectrum Disorder ◽

Cortical Thickness ◽

Symptom Severity ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Support Vector ◽

Imaging Data ◽

Learning Stage ◽

Severity Prediction

AbstractMachine learning approaches have been widely used for the identification of neuropathology from neuroimaging data. However, these approaches require large samples and suffer from the challenges associated with multi-site, multi-protocol data. We propose a novel approach to address these challenges, and demonstrate its usefulness with the Autism Brain Imaging Data Exchange (ABIDE) database. We predict symptom severity based on cortical thickness measurements from 156 individuals with autism spectrum disorder (ASD) from four different sites. The proposed approach consists of two main stages: a domain adaptation stage using partial least squares regression to maximize the consistency of imaging data across sites; and a learning stage combining support vector regression for regional prediction of severity with elastic-net penalized linear regression for integrating regional predictions into a whole-brain severity prediction. The proposed method performed markedly better than simpler alternatives, better with multi-site than single-site data, and resulted in a considerably higher cross-validated correlation score than has previously been reported in the literature for multi-site data. This demonstration of the utility of the proposed approach for detecting structural brain abnormalities in ASD from the multi-site, multi-protocol ABIDE dataset indicates the potential of designing machine learning methods to meet the challenges of agglomerative data.

Download Full-text