A systematic review of structural MRI biomarkers in autism spectrum disorder: A machine learning perspective

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.

Download Full-text

Brain-based sex differences in autism spectrum disorder across the lifespan: A systematic review of structural MRI, fMRI, and DTI findings

NeuroImage Clinical ◽

10.1016/j.nicl.2021.102719 ◽

2021 ◽

pp. 102719

Author(s):

Melissa J.M. Walsh ◽

Gregory L. Wallace ◽

Stephen M. Gallegos ◽

B. Blair Braden

Keyword(s):

Systematic Review ◽

Autism Spectrum Disorder ◽

Sex Differences ◽

Structural Mri ◽

Autism Spectrum ◽

Spectrum Disorder

Download Full-text

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

Frontiers in Neuroinformatics ◽

10.3389/fninf.2020.575999 ◽

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.

Download Full-text

Machine learning with neuroimaging data to identify autism spectrum disorder: a systematic review and meta-analysis

Neuroradiology ◽

10.1007/s00234-021-02774-z ◽

2021 ◽

Author(s):

Da-Yea Song ◽

Constantin-Cristian Topriceanu ◽

Denis C. Ilie-Ablachim ◽

Maria Kinali ◽

Sotirios Bisdas

Keyword(s):

Machine Learning ◽

Systematic Review ◽

Autism Spectrum Disorder ◽

Meta Analysis ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Neuroimaging Data

Download Full-text

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

10.21203/rs.3.rs-1024223/v1 ◽

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.

Download Full-text

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

10.1101/2021.10.21.21265162 ◽

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.

Download Full-text

The Contribution of Machine Learning and Eye-Tracking Technology in Autism Spectrum Disorder Research: A Systematic Review

Electronics ◽

10.3390/electronics10232982 ◽

2021 ◽

Vol 10 (23) ◽

pp. 2982

Author(s):

Konstantinos-Filippos Kollias ◽

Christine K. Syriopoulou-Delli ◽

Panagiotis Sarigiannidis ◽

George F. Fragulis

Keyword(s):

Machine Learning ◽

Systematic Review ◽

Autism Spectrum Disorder ◽

Eye Tracking ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Assessment Tools ◽

Future Research ◽

Promising Tool ◽

Tracking Technology

Early and objective autism spectrum disorder (ASD) assessment, as well as early intervention are particularly important and may have long term benefits in the lives of ASD people. ASD assessment relies on subjective rather on objective criteria, whereas advances in research point to up-to-date procedures for early ASD assessment comprising eye-tracking technology, machine learning, as well as other assessment tools. This systematic review, the first to our knowledge of its kind, provides a comprehensive discussion of 30 studies irrespective of the stimuli/tasks and dataset used, the algorithms applied, the eye-tracking tools utilised and their goals. Evidence indicates that the combination of machine learning and eye-tracking technology could be considered a promising tool in autism research regarding early and objective diagnosis. Limitations and suggestions for future research are also presented.

Download Full-text

Assessment of the Autism Spectrum Disorder Based on Machine Learning and Social Visual Attention: A Systematic Review

Journal of Autism and Developmental Disorders ◽

10.1007/s10803-021-05106-5 ◽

2021 ◽

Author(s):

Maria Eleonora Minissi ◽

Irene Alice Chicchi Giglioli ◽

Fabrizia Mantovani ◽

Mariano Alcañiz Raya

Keyword(s):

Machine Learning ◽

Systematic Review ◽

Autism Spectrum Disorder ◽

Visual Attention ◽

Objective Evaluation ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Early Assessment ◽

Social Stimuli ◽

Future Directions

AbstractThe assessment of autism spectrum disorder (ASD) is based on semi-structured procedures addressed to children and caregivers. Such methods rely on the evaluation of behavioural symptoms rather than on the objective evaluation of psychophysiological underpinnings. Advances in research provided evidence of modern procedures for the early assessment of ASD, involving both machine learning (ML) techniques and biomarkers, as eye movements (EM) towards social stimuli. This systematic review provides a comprehensive discussion of 11 papers regarding the early assessment of ASD based on ML techniques and children’s social visual attention (SVA). Evidences suggest ML as a relevant technique for the early assessment of ASD, which might represent a valid biomarker-based procedure to objectively make diagnosis. Limitations and future directions are discussed.

Download Full-text

Parent Education in Studies With Nonverbal and Minimally Verbal Participants With Autism Spectrum Disorder: A Systematic Review

American Journal of Speech-Language Pathology ◽

10.1044/2019_ajslp-19-00007 ◽

2020 ◽

Vol 29 (2) ◽

pp. 890-902

Author(s):

Lynn Kern Koegel ◽

Katherine M. Bryan ◽

Pumpki Lei Su ◽

Mohini Vaidya ◽

Stephen Camarata

Keyword(s):

Systematic Review ◽

Autism Spectrum Disorder ◽

Parent Education ◽

Autism Spectrum ◽

Verbal Communication ◽

Fidelity Of Implementation ◽

Spectrum Disorder ◽

Education Programs ◽

Minimally Verbal ◽

Parent Education Programs

Purpose The purpose of this systematic review was to identify parent education procedures implemented in intervention studies focused on expressive verbal communication for nonverbal (NV) or minimally verbal (MV) children with autism spectrum disorder (ASD). Parent education has been shown to be an essential component in the habilitation of individuals with ASD. Parents of individuals with ASD who are NV or MV may particularly benefit from parent education in order to provide opportunities for communication and to support their children across the life span. Method ProQuest databases were searched between the years of 1960 and 2018 to identify articles that targeted verbal communication in MV and NV individuals with ASD. A total of 1,231 were evaluated to assess whether parent education was implemented. We found 36 studies that included a parent education component. These were reviewed with regard to (a) the number of participants and participants' ages, (b) the parent education program provided, (c) the format of the parent education, (d) the duration of the parent education, (e) the measurement of parent education, and (f) the parent fidelity of implementation scores. Results The results of this analysis showed that very few studies have included a parent education component, descriptions of the parent education programs are unclear in most studies, and few studies have scored the parents' implementation of the intervention. Conclusions Currently, there is great variability in parent education programs in regard to participant age, hours provided, fidelity of implementation, format of parent education, and type of treatment used. Suggestions are made to provide both a more comprehensive description and consistent measurement of parent education programs.

Download Full-text