scholarly journals Reproducible neuroimaging features in Autism spectrum disorder that enable accurate diagnosis with machine learning models

2021 ◽  
Author(s):  
Cooper J Mellema ◽  
Kevin P Nguyen ◽  
Alex Treacher ◽  
Albert Montillo
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
State Of The Art ◽  
Neurodevelopmental Disorder ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Accurate Diagnosis ◽  
Spectrum Disorder ◽  
Learning Models ◽  
Model Search

Autism spectrum disorder (ASD) is the fourth most common neurodevelopmental disorder, with a prevalence of 1 in 160 children. Accurate diagnosis relies on experts, but such individuals are scarce. This has led to increasing interest in the development of machine learning (ML) models that can integrate neuroimaging features from functional and structural MRI (fMRI and sMRI) to measure alterations manifest in ASD. We optimized and compared the performance of 12 of the most popular and powerful ML models. Each was separately trained using 15 different combinations of fMRI and sMRI features and optimized with an unbiased model search. Deep learning models predicted ASD with the highest diagnostic accuracy and generalized well to other MRI datasets. Our model achieves state-of-the-art 80% area under the ROC curve (AUROC) in diagnosis on test data from the IMPAC dataset; and 86% and 79% AUROC on the external ABIDE I and ABIDE II datasets. The highest performing models identified reproducible putative biomarkers for accurate ASD diagnosis in accord with known ASD markers as well as novel cerebellum biomarkers. Such reproducibility lends credence to their tremendous potential for defining and using a set of truly generalizable ASD biomarkers that will advance scientific understanding of neuronal changes in ASD.

scholarly journals Reproducible Neuroimaging Features for Diagnosis of Autism Spectrum Disorder with Machine Learning

2021 ◽  
Author(s):  
Cooper J. Mellema ◽  
Kevin P. Nguyen ◽  
Alex Treacher ◽  
Albert Montillo
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
State Of The Art ◽  
Neurodevelopmental Disorder ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Accurate Diagnosis ◽  
Spectrum Disorder ◽  
Learning Models ◽  
Model Search

Abstract Autism spectrum disorder (ASD) is the fourth most common neurodevelopmental disorder, with a prevalence of 1 in 160 children. Accurate diagnosis relies on experts, but such individuals are scarce. This has led to increasing interest in the development of machine learning (ML) models that can integrate neuroimaging features from functional and structural MRI (fMRI and sMRI) to measure alterations manifest in ASD. We optimized and compared the performance of 12 of the most popular and powerful ML models. Each was separately trained using 15 different combinations of fMRI and sMRI features and optimized with an unbiased model search. Deep learning models predicted ASD with the highest diagnostic accuracy and generalized well to other MRI datasets. Our model achieves state-of-the-art 80% area under the ROC curve (AUROC) in diagnosis on test data from the IMPAC dataset; and 86% and 79% AUROC on the external ABIDE I and ABIDE II datasets. The highest performing models identified reproducible putative biomarkers for accurate ASD diagnosis in accord with known ASD markers as well as novel cerebellar biomarkers. Such reproducibility lends credence to their tremendous potential for defining and using a set of truly generalizable ASD biomarkers that will advance scientific understanding of neuronal changes in ASD.

Diagnostic test accuracy for use of machine learning in diagnosis of autism spectrum disorder: A Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Sun Jae Moon ◽  
Jin Seub Hwang ◽  
Rajesh Kana ◽  
John Torous ◽  
Jung Won Kim
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Autism Spectrum Disorder ◽  
Meta Analysis ◽  
Learning Algorithms ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Machine Learning Algorithms ◽  
Spectrum Disorder ◽  
Test Accuracy

BACKGROUND Over the recent years, machine learning algorithms have been more widely and increasingly applied in biomedical fields. In particular, its application has been drawing more attention in the field of psychiatry, for instance, as diagnostic tests/tools for autism spectrum disorder. However, given its complexity and potential clinical implications, there is ongoing need for further research on its accuracy. OBJECTIVE The current study aims to summarize the evidence for the accuracy of use of machine learning algorithms in diagnosing autism spectrum disorder (ASD) through systematic review and meta-analysis. METHODS MEDLINE, Embase, CINAHL Complete (with OpenDissertations), PsyINFO and IEEE Xplore Digital Library databases were searched on November 28th, 2018. Studies, which used a machine learning algorithm partially or fully in classifying ASD from controls and provided accuracy measures, were included in our analysis. Bivariate random effects model was applied to the pooled data in meta-analysis. Subgroup analysis was used to investigate and resolve the source of heterogeneity between studies. True-positive, false-positive, false negative and true-negative values from individual studies were used to calculate the pooled sensitivity and specificity values, draw SROC curves, and obtain area under the curve (AUC) and partial AUC. RESULTS A total of 43 studies were included for the final analysis, of which meta-analysis was performed on 40 studies (53 samples with 12,128 participants). A structural MRI subgroup meta-analysis (12 samples with 1,776 participants) showed the sensitivity at 0.83 (95% CI-0.76 to 0.89), specificity at 0.84 (95% CI -0.74 to 0.91), and AUC/pAUC at 0.90/0.83. An fMRI/deep neural network (DNN) subgroup meta-analysis (five samples with 1,345 participants) showed the sensitivity at 0.69 (95% CI- 0.62 to 0.75), the specificity at 0.66 (95% CI -0.61 to 0.70), and AUC/pAUC at 0.71/0.67. CONCLUSIONS Machine learning algorithms that used structural MRI features in diagnosis of ASD were shown to have accuracy that is similar to currently used diagnostic tools.

scholarly journals Machine Learning Methods for Diagnosing Autism Spectrum Disorder and Attention- Deficit/Hyperactivity Disorder Using Functional and Structural MRI: A Survey

2021 ◽  
Vol 14 ◽  
Author(s):  
Taban Eslami ◽  
Fahad Almuqhim ◽  
Joseph S. Raiker ◽  
Fahad Saeed
Keyword(s):  
Machine Learning ◽  
Autism Spectrum Disorder ◽  
Attention Deficit Hyperactivity Disorder ◽  
Attention Deficit ◽  
Imaging Techniques ◽  
Structural Mri ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Hyperactivity Disorder ◽  
Machine Learning Model

Here we summarize recent progress in machine learning model for diagnosis of Autism Spectrum Disorder (ASD) and Attention-deficit/Hyperactivity Disorder (ADHD). We outline and describe the machine-learning, especially deep-learning, techniques that are suitable for addressing research questions in this domain, pitfalls of the available methods, as well as future directions for the field. We envision a future where the diagnosis of ASD, ADHD, and other mental disorders is accomplished, and quantified using imaging techniques, such as MRI, and machine-learning models.

A Novel Automated Approach for Deep Learning on Stereotypical Autistic Motor Movements

2021 ◽  
pp. 54-68
Author(s):  
Mohammad Shabaz ◽  
Parveen Singla ◽  
Malik Mustafa Mohammad Jawarneh ◽  
Himayun Mukhtar Qureshi
Keyword(s):  
Neural Networks ◽  
Autism Spectrum Disorder ◽  
Deep Learning ◽  
State Of The Art ◽  
Neurodevelopmental Disorder ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Motor Disorders ◽  
Convolution Neural Networks ◽  
Motor Movements

Autism spectrum disorder (ASD) is an ongoing neurodevelopmental disorder, with repeated behavior called stereotypical movement autism (SMM). Some recent experiments with accelerometer features as feedback to computer classifiers demonstrate positive findings in persons with autistic motor disorders for the automobile detection of stereotypical motor motions (SMM). To date, several methods for detecting and recognizing SMMs have been introduced. In this context, the authors suggest an approach of deep learning for recognition of SMM, namely deep convolution neural networks (DCNN). They also implemented a robust DCNN model for the identification of SMM in order to solve stereotypical motor movements (SMM), which thus outperform state-of-the-art SMM classification work.

Specialized Diet Therapies: Exploration for Improving Behavior in Autism Spectrum Disorder (ASD)

2020 ◽  
Vol 27 (40) ◽  
pp. 6771-6786
Author(s):  
Geir Bjørklund ◽  
Nagwa Abdel Meguid ◽  
Maryam Dadar ◽  
Lyudmila Pivina ◽  
Joanna Kałużna-Czaplińska ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Neurodevelopmental Disorder ◽  
Caloric Intake ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Nutritional Deficiencies ◽  
Childhood And Adolescence ◽  
Restricted Interests ◽  
Balanced Diet ◽  
The Individual

As a major neurodevelopmental disorder, Autism Spectrum Disorder (ASD) encompasses deficits in communication and repetitive and restricted interests or behaviors in childhood and adolescence. Its etiology may come from either a genetic, epigenetic, neurological, hormonal, or an environmental cause, generating pathways that often altogether play a synergistic role in the development of ASD pathogenesis. Furthermore, the metabolic origin of ASD should be important as well. A balanced diet consisting of the essential and special nutrients, alongside the recommended caloric intake, is highly recommended to promote growth and development that withstand the physiologic and behavioral challenges experienced by ASD children. In this review paper, we evaluated many studies that show a relationship between ASD and diet to develop a better understanding of the specific effects of the overall diet and the individual nutrients required for this population. This review will add a comprehensive update of knowledge in the field and shed light on the possible nutritional deficiencies, metabolic impairments (particularly in the gut microbiome), and malnutrition in individuals with ASD, which should be recognized in order to maintain the improved socio-behavioral habit and physical health.

scholarly journals Intranasal oxytocin administration ameliorates social behavioral deficits in a POGZWT/Q1038R mouse model of autism spectrum disorder

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Kohei Kitagawa ◽  
Kensuke Matsumura ◽  
Masayuki Baba ◽  
Momoka Kondo ◽  
Tomoya Takemoto ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Social Behavior ◽  
Mouse Model ◽  
Mouse Models ◽  
De Novo ◽  
Neurodevelopmental Disorder ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
De Novo Mutation ◽  
Behavioral Deficits

AbstractAutism spectrum disorder (ASD) is a highly prevalent neurodevelopmental disorder characterized by core symptoms of impaired social behavior and communication. Recent studies have suggested that the oxytocin system, which regulates social behavior in mammals, is potentially involved in ASD. Mouse models of ASD provide a useful system for understanding the associations between an impaired oxytocin system and social behavior deficits. However, limited studies have shown the involvement of the oxytocin system in the behavioral phenotypes in mouse models of ASD. We have previously demonstrated that a mouse model that carries the ASD patient-derived de novo mutation in the pogo transposable element derived with zinc finger domain (POGZWT/Q1038R mice), showed ASD-like social behavioral deficits. Here, we have explored whether oxytocin (OXT) administration improves impaired social behavior in POGZWT/Q1038R mice and found that intranasal oxytocin administration effectively restored the impaired social behavior in POGZWT/Q1038R mice. We also found that the expression level of the oxytocin receptor gene (OXTR) was low in POGZWT/Q1038R mice. However, we did not detect significant changes in the number of OXT-expressing neurons between the paraventricular nucleus of POGZWT/Q1038R mice and that of WT mice. A chromatin immunoprecipitation assay revealed that POGZ binds to the promoter region of OXTR and is involved in the transcriptional regulation of OXTR. In summary, our study demonstrate that the pathogenic mutation in the POGZ, a high-confidence ASD gene, impairs the oxytocin system and social behavior in mice, providing insights into the development of oxytocin-based therapeutics for ASD.

scholarly journals A Deep Learning Approach to Predict Autism Spectrum Disorder Using Multisite Resting-State fMRI

2021 ◽  
Vol 11 (8) ◽  
pp. 3636
Author(s):  
Faria Zarin Subah ◽  
Kaushik Deb ◽  
Pranab Kumar Dhar ◽  
Takeshi Koshiba
Keyword(s):  
Autism Spectrum Disorder ◽  
Resting State ◽  
State Of The Art ◽  
Resting State Fmri ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Bootstrap Analysis ◽  
Proposed Model ◽  
Art Methods ◽  
The Mean

Autism spectrum disorder (ASD) is a complex and degenerative neuro-developmental disorder. Most of the existing methods utilize functional magnetic resonance imaging (fMRI) to detect ASD with a very limited dataset which provides high accuracy but results in poor generalization. To overcome this limitation and to enhance the performance of the automated autism diagnosis model, in this paper, we propose an ASD detection model using functional connectivity features of resting-state fMRI data. Our proposed model utilizes two commonly used brain atlases, Craddock 200 (CC200) and Automated Anatomical Labelling (AAL), and two rarely used atlases Bootstrap Analysis of Stable Clusters (BASC) and Power. A deep neural network (DNN) classifier is used to perform the classification task. Simulation results indicate that the proposed model outperforms state-of-the-art methods in terms of accuracy. The mean accuracy of the proposed model was 88%, whereas the mean accuracy of the state-of-the-art methods ranged from 67% to 85%. The sensitivity, F1-score, and area under receiver operating characteristic curve (AUC) score of the proposed model were 90%, 87%, and 96%, respectively. Comparative analysis on various scoring strategies show the superiority of BASC atlas over other aforementioned atlases in classifying ASD and control.

Sign in / Sign up

Export Citation Format

Share Document