scholarly journals Prediction of autism spectrum disorder diagnosis using nonlinear measures of language-related EEG at 6 and 12 months

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Fleming C. Peck ◽  
Laurel J. Gabard-Durnam ◽  
Carol L. Wilkinson ◽  
William Bosl ◽  
Helen Tager-Flusberg ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Feature Selection ◽  
Language Learning ◽  
Predictive Accuracy ◽  
Pearson Correlation ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Phoneme Discrimination ◽  
Co Morbidity

Abstract Background Early identification of autism spectrum disorder (ASD) provides an opportunity for early intervention and improved developmental outcomes. The use of electroencephalography (EEG) in infancy has shown promise in predicting later ASD diagnoses and in identifying neural mechanisms underlying the disorder. Given the high co-morbidity with language impairment, we and others have speculated that infants who are later diagnosed with ASD have altered language learning, including phoneme discrimination. Phoneme learning occurs rapidly in infancy, so altered neural substrates during the first year of life may serve as early, accurate indicators of later autism diagnosis. Methods Using EEG data collected at two different ages during a passive phoneme task in infants with high familial risk for ASD, we compared the predictive accuracy of a combination of feature selection and machine learning models at 6 months (during native phoneme learning) and 12 months (after native phoneme learning), and we identified a single model with strong predictive accuracy (100%) for both ages. Samples at both ages were matched in size and diagnoses (n = 14 with later ASD; n = 40 without ASD). Features included a combination of power and nonlinear measures across the 10‑20 montage electrodes and 6 frequency bands. Predictive features at each age were compared both by feature characteristics and EEG scalp location. Additional prediction analyses were performed on all EEGs collected at 12 months; this larger sample included 67 HR infants (27 HR-ASD, 40 HR-noASD). Results Using a combination of Pearson correlation feature selection and support vector machine classifier, 100% predictive diagnostic accuracy was observed at both 6 and 12 months. Predictive features differed between the models trained on 6- versus 12-month data. At 6 months, predictive features were biased to measures from central electrodes, power measures, and frequencies in the alpha range. At 12 months, predictive features were more distributed between power and nonlinear measures, and biased toward frequencies in the beta range. However, diagnosis prediction accuracy substantially decreased in the larger, more behaviorally heterogeneous 12-month sample. Conclusions These results demonstrate that speech processing EEG measures can facilitate earlier identification of ASD but emphasize the need for age-specific predictive models with large sample sizes to develop clinically relevant classification algorithms.

scholarly journals Prediction of autism spectrum disorder diagnosis using nonlinear measures of language-related EEG at 6 and 12 months

2021 ◽  
Author(s):  
Fleming C. Peck ◽  
Laurel J. Gabard-Durnam ◽  
Carol L Wilkinson ◽  
William Bosl ◽  
Helen Tager-Flusberg ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Feature Selection ◽  
Language Learning ◽  
Predictive Accuracy ◽  
Pearson Correlation ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Phoneme Discrimination ◽  
Co Morbidity

Abstract Background: Early identification of autism spectrum disorder (ASD) provides opportunity for early intervention and improved outcomes. Electroencephalography (EEG) use in infants has shown promise in predicting later ASD diagnoses and in identifying neural mechanisms underlying the disorder. Given the high co-morbidity with language impairment, we and others have speculated that infants who are later diagnosed with ASD have altered language learning, including phoneme discrimination. Phoneme learning occurs rapidly in infancy, so altered neural substrates either during or after the first year may serve as early, accurate indicators of later autism diagnosis. Methods: Using longitudinal EEG data collected during a passive phoneme task in infants with high familial risk for ASD, we compared the predictive accuracy of a combination of feature selection and machine learning models at 6 months (during phoneme learning) versus 12 months (after phoneme learning), and identified a single model with strong predictive accuracy (100%) for both ages. Samples at both ages were matched in size and diagnoses (n=14 with later ASD; n= 40 without ASD). Features included a combination of power and nonlinear measures across 10-20 electrodes and 6 frequency bands. Predictive features at each age were compared both by feature characteristics and EEG scalp location. Results: Using a combination Pearson correlation feature selection and support vector machine classifier 100% predictive diagnostic accuracy was observed at both 6 and 12 months. Predictive features differed between the models trained on 6- versus 12- month data. At 6-months, predictive features were biased to measures from central electrodes, power measures, and measures in the alpha range. At 12-months, predictive features were more distributed between power and nonlinear measures, and biased toward measures in the beta range. Conclusions: These results demonstrate that speech processing EEG measures can facilitate earlier identification of ASD but emphasize the need for age-specific predictive models with large sample sizes to develop clinically relevant classification algorithms.

scholarly journals Prediction of autism spectrum disorder diagnosis using nonlinear measures of language-related EEG at 6 and 12 months

2020 ◽  
Author(s):  
Fleming C. Peck ◽  
Laurel J. Gabard-Durnam ◽  
Carol L. Wilkinson ◽  
William Bosl ◽  
Helen Tager-Flusberg ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Language Learning ◽  
Predictive Accuracy ◽  
Pearson Correlation ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Phoneme Discrimination ◽  
Co Morbidity

AbstractEarly identification of autism spectrum disorder (ASD) provides an opportunity for early intervention and improved outcomes. Use of electroencephalography (EEG) in infants has shown promise in predicting later ASD diagnoses and in identifying neural mechanisms underlying the disorder. Given the high co-morbidity with language impairment in ASD, we and others have speculated that infants who are later diagnosed with ASD have altered language learning, including phoneme discrimination. Phoneme learning occurs rapidly within the first postnatal year, so altered neural substrates either during or after the first year may serve as early, accurate indicators of later autism diagnosis. Using longitudinal EEG data collected during a passive phoneme task in infants with high familial risk for ASD, we compared predictive accuracy at 6-months (during phoneme learning) versus 12-months (after phoneme learning). Samples at both ages were matched in size and diagnoses (n=14 with later ASD; n= 40 without ASD). Using Pearson correlation feature selection and support vector machine with radial basis function classifier, 100% predictive diagnostic accuracy was observed at both ages. However, predictive features selected at the two ages differed and came from different scalp locations. We also report that performance across multiple machine learning algorithms was highly variable and declined when the 12-month sample size and behavioral heterogeneity was increased. These results demonstrate that speech processing EEG measures can facilitate earlier identification of ASD but emphasize the need for age-specific predictive models with large sample sizes in order to develop clinically relevant classification algorithms.

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

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.

scholarly journals Fostering Emotion Recognition in Children with Autism Spectrum Disorder

2021 ◽  
Vol 5 (10) ◽  
pp. 57
Author(s):  
Vinícius Silva ◽  
Filomena Soares ◽  
João Sena Esteves ◽  
Cristina P. Santos ◽  
Ana Paula Pereira
Keyword(s):  
Autism Spectrum Disorder ◽  
Social Interaction ◽  
Emotion Recognition ◽  
Facial Expressions ◽  
Social Communication ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Support Vector ◽  
Robotic Platform ◽  
Children With Asd

Facial expressions are of utmost importance in social interactions, allowing communicative prompts for a speaking turn and feedback. Nevertheless, not all have the ability to express themselves socially and emotionally in verbal and non-verbal communication. In particular, individuals with Autism Spectrum Disorder (ASD) are characterized by impairments in social communication, repetitive patterns of behaviour, and restricted activities or interests. In the literature, the use of robotic tools is reported to promote social interaction with children with ASD. The main goal of this work is to develop a system capable of automatic detecting emotions through facial expressions and interfacing them with a robotic platform (Zeno R50 Robokind® robotic platform, named ZECA) in order to allow social interaction with children with ASD. ZECA was used as a mediator in social communication activities. The experimental setup and methodology for a real-time facial expression (happiness, sadness, anger, surprise, fear, and neutral) recognition system was based on the Intel® RealSense™ 3D sensor and on facial features extraction and multiclass Support Vector Machine classifier. The results obtained allowed to infer that the proposed system is adequate in support sessions with children with ASD, giving a strong indication that it may be used in fostering emotion recognition and imitation skills.

scholarly journals A Three-Stage Teacher, Student Neural Networks and Sequential Feed Forward Selection-Based Feature Selection Approach for the Classification of Autism Spectrum Disorder

2020 ◽  
Vol 10 (10) ◽  
pp. 754
Author(s):  
Naseer Ahmed Khan ◽  
Samer Abdulateef Waheeb ◽  
Atif Riaz ◽  
Xuequn Shang
Keyword(s):  
Autism Spectrum Disorder ◽  
Feature Selection ◽  
Data Exchange ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Connectivity Matrix ◽  
Brain Disorder ◽  
Selection Approach ◽  
Feature Selection Approach

Autism disorder, generally known as Autism Spectrum Disorder (ASD) is a brain disorder characterized by lack of communication skills, social aloofness and repetitions in the actions in the patients, which is affecting millions of the people across the globe. Accurate identification of autistic patients is considered a challenging task in the domain of brain disorder science. To address this problem, we have proposed a three-stage feature selection approach for the classification of ASD on the preprocessed Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI Dataset. In the first stage, a large neural network which we call a “Teacher ” was trained on the correlation-based connectivity matrix to learn the latent representation of the input. In the second stage an autoencoder which we call a “Student” autoencoder was given the task to learn those trained “Teacher” embeddings using the connectivity matrix input. Lastly, an SFFS-based algorithm was employed to select the subset of most discriminating features between the autistic and healthy controls. On the combined site data across 17 sites, we achieved the maximum 10-fold accuracy of 82% and for the individual site-wise data, based on 5-fold accuracy, our results outperformed other state of the art methods in 13 out of the total 17 site-wise comparisons.

scholarly journals Interpretable Learning Approaches in Resting-State Functional Connectivity Analysis: The Case of Autism Spectrum Disorder

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jinlong Hu ◽  
Lijie Cao ◽  
Tenghui Li ◽  
Bin Liao ◽  
Shoubin Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Autism Spectrum Disorder ◽  
Functional Connectivity ◽  
Resting State ◽  
Piecewise Linear ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Fmri Data ◽  
Support Vector ◽  
Resting State Functional Connectivity

Deep neural networks have recently been applied to the study of brain disorders such as autism spectrum disorder (ASD) with great success. However, the internal logics of these networks are difficult to interpret, especially with regard to how specific network architecture decisions are made. In this paper, we study an interpretable neural network model as a method to identify ASD participants from functional magnetic resonance imaging (fMRI) data and interpret results of the model in a precise and consistent manner. First, we propose an interpretable fully connected neural network (FCNN) to classify two groups, ASD versus healthy controls (HC), based on input data from resting-state functional connectivity (rsFC) between regions of interests (ROIs). The proposed FCNN model is a piecewise linear neural network (PLNN) which uses piecewise linear function LeakyReLU as its activation function. We experimentally compared the FCNN model against widely used classification models including support vector machine (SVM), random forest, and two new classes of deep neural network models in a large dataset containing 871 subjects from ABIDE I database. The results show the proposed FCNN model achieves the highest classification accuracy. Second, we further propose an interpreting method which could explain the trained model precisely with a precise linear formula for each input sample and decision features which contributed most to the classification of ASD versus HC participants in the model. We also discuss the implications of our proposed approach for fMRI data classification and interpretation.

Sign in / Sign up

Export Citation Format

Share Document