Autism Spectrum Disorder Detection with Machine Learning Methods

2020 ◽  
Vol 15 (4) ◽  
pp. 297-308 ◽  
Author(s):  
Uğur Erkan ◽  
Dang N.H. Thanh
Keyword(s):  
Machine Learning ◽  
Early Diagnosis ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Classification Methods ◽  
Brain Images ◽  
Machine Method ◽  
Nearest Neighbours ◽  
Number Of Patients

Background: Autistic Spectrum Disorder (ASD) is a disorder associated with genetic and neurological components leading to difficulties in social interaction and communication. According to statistics of WHO, the number of patients diagnosed with ASD is gradually increasing. Most of the current studies focus on clinical diagnosis, data collection and brain images analysis, but do not focus on the diagnosis of ASD based on machine learning. Objective: This study aims to classify ASD data to provide a quick, accessible and easy way to support early diagnosis of ASD. Methods: Three ASD datasets are used for children, adolescences and adults. To classify the ASD data, we used the k-Nearest Neighbours method (kNN), the Support Vector Machine method (SVM) and the Random Forests method (RF). In our experiments, the data was randomly split into training and test sets. The parts of the data were randomly selected 100 times to test the classification methods. Results: The final results were assessed by the average values. It is shown that SVM and RF are effective methods for ASD classification. In particular, the RF method classified the data with an accuracy of 100% for all above datasets. Conclusion: The early diagnosis of ASD is critical. If the number of data samples is large enough, we can achieve a high accuracy for machine learning-based ASD diagnosis. Among three classification methods, RF achieves the best performance for ASD data classification.

scholarly journals Child Behavioral Analysis: Machine Learning based Investigation for Autism Screening and Early Diagnosis

2021 ◽  
Vol 13 (2) ◽  
pp. 1199-1208
Author(s):  
N. Ajaypradeep ◽  
Dr.R. Sasikala
Keyword(s):  
Machine Learning ◽  
Early Diagnosis ◽  
Cross Validation ◽  
Parameter Tuning ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Therapeutic Practice ◽  
Nearest Neighbours ◽  
Wide Range

Autism is a developmental disorder which affects cognition, social and behavioural functionalities of a person. When a person is affected by autism spectrum disorder, he/she will exhibit peculiar behaviours and those symptoms initiate from that patient’s childhood. Early diagnosis of autism is an important and challenging task. Behavioural analysis a well known therapeutic practice can be adopted for earlier diagnosis of autism. Machine learning is a computational methodology, which can be applied to a wide range of applications in-order to obtain efficient outputs. At present machine learning is especially applied in medical applications such as disease prediction. In our study we evaluated various machine learning algorithms [(Naive bayes (NB), Support Vector Machines (SVM) and k-Nearest Neighbours (KNN)] with “k-fold” based cross validation for 3 datasets retrieved from the UCI repository. Additionally we validated the effective accuracy of the estimated results using a clustered cross validation strategy. The process of employing the clustered cross validation scrutinises the parameters which contributes more importance in the dataset. The strategy induces hyper parameter tuning which yields trusted results as it involves double validation. On application of the clustered cross validation for a SVM based model, we obtained an accuracy of 99.6% accuracy for autism child dataset.

scholarly journals Use of Empirical Mode Decomposition in ERP Analysis to Classify Familial Risk and Diagnostic Outcomes for Autism Spectrum Disorder

2021 ◽  
Vol 11 (4) ◽  
pp. 409
Author(s):  
Lina Abou-Abbas ◽  
Stefon van Noordt ◽  
James A. Desjardins ◽  
Mike Cichonski ◽  
Mayada Elsabbagh
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
High Risk ◽  
Empirical Mode Decomposition ◽  
Familial Risk ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Mode Decomposition

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.

scholarly journals Classification of adult autistic spectrum disorder using machine learning approach

2021 ◽  
Vol 10 (3) ◽  
pp. 743
Author(s):  
Nurul Amirah Mashudi ◽  
Norulhusna Ahmad ◽  
Norliza Mohd Noor
Keyword(s):  
Machine Learning ◽  
Naive Bayes ◽  
Autism Spectrum ◽  
Naïve Bayes ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Learning Approaches ◽  
Related Disorder ◽  
Machine Learning Approach ◽  
Linear Svm

Autism spectrum disorder (ASD) is a neurological-related disorder. Patients with ASD have poor social interaction and lack of communication that lead to restricted activities. Thus, early diagnosis with a reliable system is crucial as the symptoms may affect the patient’s entire lifetime. Machine learning approaches are an effective and efficient method for the prediction of ASD disease. The study mainly aims to achieve the accuracy of ASD classification using a variety of machine learning approaches. The dataset comprises 16 selected attributes that are inclusive of 703 patients and non-patients. The experiments are performed within the simulation environment and analyzed using the Waikato environment for knowledge analysis (WEKA) platform. Linear support vector machine (SVM), k-nearest neighbours (k-NN), J48, Bagging, Stacking, AdaBoost, and naïve bayes are the methods used to compute the prediction of ASD status on the subject using 3, 5, and 10-folds cross validation. The analysis is then computed to evaluate the accuracy, sensitivity, and specificity of the proposed methods. The comparative result between the machine learning approaches has shown that linear SVM, J48, Bagging, Stacking, and naïve bayes produce the highest accuracy at 100% with the lowest error rate.

scholarly journals A Machine Learning Way to Classify Autism Spectrum Disorder

2021 ◽  
Vol 16 (06) ◽  
pp. 182
Author(s):  
Sujatha R ◽  
Aarthy SL ◽  
Jyotir Moy Chatterjee ◽  
A. Alaboudi ◽  
NZ Jhanjhi
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Stochastic Gradient Descent ◽  
Screening Tests ◽  
Support Vector ◽  
Attention Switching ◽  
Adaptive Boosting ◽  
Over The Top

In recent times Autism Spectrum Disorder (ASD) is picking up its force quicker than at any other time. Distinguishing autism characteristics through screening tests is over the top expensive and tedious. Screening of the same is a challenging task, and classification must be conducted with great care. Machine Learning (ML) can perform great in the classification of this problem. Most researchers have utilized the ML strategy to characterize patients and typical controls, among which support vector machines (SVM) are broadly utilized. Even though several studies have been done utilizing various methods, these investigations didn't give any complete decision about anticipating autism qualities regarding distinctive age groups. Accordingly, this paper plans to locate the best technique for ASD classi-fication out of SVM, K-nearest neighbor (KNN), Random Forest (RF), Naïve Bayes (NB), Stochastic gradient descent (SGD), Adaptive boosting (AdaBoost), and CN2 Rule Induction using 4 ASD datasets taken from UCI ML repository. The classification accuracy (CA) we acquired after experimentation is as follows: in the case of the adult dataset SGD gives 99.7%, in the adolescent dataset RF gives 97.2%, in the child dataset SGD gives 99.6%, in the toddler dataset Ada-Boost gives 99.8%. Autism spectrum quotients (AQs) varied among several sce-narios for toddlers, adults, adolescents, and children that include positive predic-tive value for the scaling purpose. AQ questions referred to topics about attention to detail, attention switching, communication, imagination, and social skills.

scholarly journals Exploiting of Classification Paradigms for Early diagnosis of Alzheimer’s disease

2021 ◽  
Vol 9 (2) ◽  
pp. 281-288
Author(s):  
G Stalin Babu, Et. al.
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Feature Extraction ◽  
Early Diagnosis ◽  
Disease Diagnosis ◽  
Classification Methods ◽  
Brain Images ◽  
Deep Convolution Neural Network

Alzheimer’s disorder is an incurable neurodegenerative disease that ordinarily affects the aged population. Coherent automated assessment methods are essential for Alzheimer's disease diagnosis in early from distinct images modalities using Machine Learning. This article focuses on exploring various feature extraction and classification methods for early detection of AD proposed by researchers and proposes a modern predictive model that includes Voxel based Texture analysis of brain images for extract features and Optimized Classifier Deep Convolution Neural Network (DCNN) employed for enhance accuracy.

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

2016 ◽  
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.

Modified Cuckoo Search-Support Vector Machine (MCS-SVM) Gene Selection and Classification for Autism Spectrum Disorder (ASD) Gene Expression

2020 ◽  
Vol 18 (11) ◽  
pp. 01-13
Author(s):  
Dr.M. Kalaiarasu ◽  
Dr.J. Anitha
Keyword(s):  
Gene Expression ◽  
Autism Spectrum Disorder ◽  
Support Vector Machine ◽  
Gene Selection ◽  
Cuckoo Search ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Methods

Autism Spectrum Disorder (ASD) is a neuro developmental disorder characterized by weakened social skills, impaired verbal and non-verbal interaction, and repeated behavior. ASD has increased in the past few years and the root cause of the symptom cannot yet be determined. In ASD with gene expression is analyzed by classification methods. For the selection of genes in ASD, statistical philtres and a wrapper-based Geometric Binary Particle Swarm Optimization-Support Vector Machine (GBPSO-SVM) algorithm have recently been implemented. However GBPSO has provides lesser accuracy, if the dataset samples are large and it cannot directly apply to multiple output systems. To overcome this issue, Modified Cuckoo Search-Support Vector Machine (MCS-SVM) based wrapper feature selection algorithm is proposed which improves the accuracy of the classifier in ASD. This work consists of three major steps, (i) preprocessing, (ii) gene selection, and (iii) classification. Firstly, preprocessing is performed by mean or median ratios close to unity was removed from original gene dataset; based on this samples are reduced from 54,613 to 9454. Secondly, gene selection is performed by using statistical filters and wrapper algorithm. Statistical filters methods like Wilcox on Rank Sum test (WRS), Class Correlation (COR) function and Two-sample T-test (TT) were applied in parallel to a ten-fold cross validation range of the most discriminatory genes. In the wrapper algorithm, Modified Cuckoo Search (MCS) is also proposed to gene selection. This step decreases the number of genes of the dataset by removing genes. Finally, SVM classifier combined forms of gene subsets for grading. The autism microarray dataset used in the analysis was downloaded from the benchmark public repository Gene Expression Omnibus (GEO) (National Center for Biotechnology Information (NCBI)). The classification methods are measured in terms of the metrics like precision, recall, f-measure and accuracy. Proposed MCS-SVM classifier achieves highest accuracy when compared Linear Regression (LR), and GBPSO-SVM classifiers.

Possibility that the Onset of Autism Spectrum Disorder is Induced by Failure of the Glutamine-Glutamate Cycle

2020 ◽  
Vol 14 (2) ◽  
pp. 170-174
Author(s):  
Koichi Kawada ◽  
Nobuyuki Kuramoto ◽  
Seisuke Mimori
Keyword(s):  
Autism Spectrum Disorder ◽  
Endoplasmic Reticulum ◽  
Environmental Factors ◽  
Endoplasmic Reticulum Stress ◽  
Synapse Formation ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Neurodevelopmental Disease ◽  
Number Of Patients ◽  
The Brain

: Autism spectrum disorder (ASD) is a neurodevelopmental disease, and the number of patients has increased rapidly in recent years. The causes of ASD involve both genetic and environmental factors, but the details of causation have not yet been fully elucidated. Many reports have investigated genetic factors related to synapse formation, and alcohol and tobacco have been reported as environmental factors. This review focuses on endoplasmic reticulum stress and amino acid cycle abnormalities (particularly glutamine and glutamate) induced by many environmental factors. In the ASD model, since endoplasmic reticulum stress is high in the brain from before birth, it is clear that endoplasmic reticulum stress is involved in the development of ASD. On the other hand, one report states that excessive excitation of neurons is caused by the onset of ASD. The glutamine-glutamate cycle is performed between neurons and glial cells and controls the concentration of glutamate and GABA in the brain. These neurotransmitters are also known to control synapse formation and are important in constructing neural circuits. Theanine is a derivative of glutamine and a natural component of green tea. Theanine inhibits glutamine uptake in the glutamine-glutamate cycle via slc38a1 without affecting glutamate; therefore, we believe that theanine may prevent the onset of ASD by changing the balance of glutamine and glutamate in the brain.

Sign in / Sign up

Export Citation Format

Share Document