Machine Learning Methods for Diagnosing Autism Spectrum Disorder and Attention- Deficit/Hyperactivity Disorder Using Functional and Structural MRI: A Survey.
Ontology highlight
ABSTRACT:
SUBMITTER: Eslami T
PROVIDER: S-EPMC7855595 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Machine Learning Methods for Diagnosing Autism Spectrum Disorder and Attention- Deficit/Hyperactivity Disorder Using Functional and Structural MRI: A Survey.
Eslami Taban T Almuqhim Fahad F Raiker Joseph S JS Saeed Fahad F
Frontiers in neuroinformatics 20210120
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 quanti ...[more]
Similar Datasets
Project description:Attention Deficit Hyperactivity Disorder (ADHD) and Autism Spectrum Disorders (ASD) are two of the most represented neurodevelopmental conditions in childhood. The diagnostic shift introduced by the DSM-5, allowing a combined diagnosis of ADHD and ASD, poses different clinical challenges related to diagnostic overshadowing, accuracy of clinical judgment and potential delay in an ASD diagnosis in children presenting with ADHD. Here we tried to disentangle the clinical phenotype and specificity of the two co-occurring conditions in relation to autism traits and empathy, by comparing children with ASD with and without comorbid ADHD with children presenting ADHD only and children with typical development. The child versions of the Autism Quotient (C-AQ) and Empathy Quotient (C-EQ) were administered to a total sample of 198 male children between 6 and 14 years old with age appropriate language skills and normal intelligence. Univariate analysis demonstrated no significant differences in the C-AQ total and subscale scores as well as the C-EQ between children with ASD and children with ASD + ADHD, while children with ADHD alone presented an intermediate phenotype between ASD and TD. Furthermore, a receiver operating characteristic (ROC) analysis was applied to discriminate among the different phenotypes. We found that the C-AQ and C-EQ were accurate at distinguishing with satisfactory reliability between: (a) ASD vs. non- ASD (N-ASD) groups comprising both ADHD and TD children (Area Under the Curve AUC 88% for C-AQ and 81% for C-EQ); (b) ASD and TD (AUC 92% for C-AQ and 95% for C-EQ); (c) ASD and ADHD (AUC 80% for C-AQ and 68% for C-EQ). Our data confirm the reliability of the C-AQ and C-EQ as behavioral markers to differentiate ASD (regardless of comorbid ADHD) from an ADHD condition and TD. Interestingly, in our sample an ADHD condition does not increase the severity of the clinical phenotype in terms of autism traits distribution and empathy, suggesting that the psychological measures detected by the two quantitative instruments are independent of ADHD traits. This evidence will contribute to the translational efforts in developing better tailored treatments and preventive strategies.
| S-EPMC8649805 | biostudies-literature
Project description:Attention-deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) are both highly heritable neurodevelopmental disorders. Evidence indicates both disorders co-occur with a high frequency, in 20-50% of children with ADHD meeting criteria for ASD and in 30-80% of ASD children meeting criteria for ADHD. This review will provide an overview on all available studies [family based, twin, candidate gene, linkage, and genome wide association (GWA) studies] shedding light on the role of shared genetic underpinnings of ADHD and ASD. It is concluded that family and twin studies do provide support for the hypothesis that ADHD and ASD originate from partly similar familial/genetic factors. Only a few candidate gene studies, linkage studies and GWA studies have specifically addressed this co-occurrence, pinpointing to some promising pleiotropic genes, loci and single nucleotide polymorphisms (SNPs), but the research field is in urgent need for better designed and powered studies to tackle this complex issue. We propose that future studies examining shared familial etiological factors for ADHD and ASD use a family-based design in which the same phenotypic (ADHD and ASD), candidate endophenotypic, and environmental measurements are obtained from all family members. Multivariate multi-level models are probably best suited for the statistical analysis.
| S-EPMC2839489 | biostudies-literature
Project description:Interest in the co-occurrence of attention deficit/hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) has grown in the last decade. Research on clinical populations supports the frequent co-occurrence of ADHD traits (e.g., hyperactivity) in individuals with ASD and ASD traits (e.g., social communication deficits) in individuals with ADHD. Similar trends in co-occurring traits have been observed in population-based samples, as well as family and genetic studies of affected individuals. Despite increased interest in co-occurring ADHD and ASD, relatively little research has been devoted to treatment considerations. The vast majority of intervention research has examined pharmacological treatment using traditional ADHD medications. Relatively few psychosocial interventions have directly addressed co-occurring symptoms. Treatment development will benefit from enhanced understanding of the phenomenon of co-occurring ADHD and ASD. Key topics for future research include examining developmental trajectories of co-occurring disorders, comorbid psychiatric conditions, deficits in social skills, and the nature of executive functioning impairment in individuals with co-occurring ADHD and ASD. In the current review, research in these areas is reviewed along with recommendation for future study. Given that clinicians are routinely observing and treating individuals with co-occurring symptoms, further research will yield needed information to inform intervention development and maximize benefits for affected individuals.
| S-EPMC3441928 | biostudies-literature
Project description:Autism spectrum disorder (ASD) symptoms frequently occur in subjects with attention deficit/hyperactivity disorder (ADHD). While there is evidence that both ADHD and ASD have differential structural correlates, no study to date has investigated these structural correlates within a framework that robustly accounts for the phenotypic overlap between the two disorders. The presence of ASD symptoms was measured by the parent-reported Children's Social and Behavioural Questionnaire (CSBQ) in ADHD subjects (n?=?180), their unaffected siblings (n?=?118) and healthy controls (n?=?146). ADHD symptoms were assessed by a structured interview (K-SADS-PL) and the Conners' ADHD questionnaires. Whole brain T1-weighted MPRAGE images were acquired and the structural MRI correlates of ASD symptom scores were analysed by modelling ASD symptom scores against white matter (WM) and grey matter (GM) volumes using mixed effects models which controlled for ADHD symptom levels. ASD symptoms were significantly elevated in ADHD subjects relative to both controls and unaffected siblings. ASD scores were predicted by the interaction between WM and GM volumes. Increasing ASD score was associated with greater GM volume. Equivocal results from previous structural studies in ADHD and ASD may be due to the fact that comorbidity has not been taken into account in studies to date. The current findings stress the need to account for issues of ASD comorbidity in ADHD.
| S-EPMC4076257 | biostudies-literature
Project description:Recent research has shown high rates of comorbidity between attention deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) and difficulties regarding differential diagnosis. Unlike those in Western countries, the Japanese ADHD prevalence rate is lower relative to that of ASD. This inconsistency could have occurred because of cultural diversities among professionals such as physicians. However, little is known about attitudes toward ADHD and ASD in non-Western cultural contexts. We conducted two experiments to identify biases in ASD and ADHD assessment. In Study 1, we examined attitudes toward these disorders in medical doctors and mental health professionals, using a web-based questionnaire. In Study 2, medical doctors and clinical psychologists assessed four fictional cases based on criteria for ADHD, ASD, oppositional defiant disorder, and disinhibited social engagement disorder (DSED). Diagnosis of ASD was considered more difficult relative to that of ADHD. Most participants assessed the fictional DSED case as ASD, rather than DSED or ADHD. The results provide evidence that Japanese professionals are more likely to attribute children's behavioral problems to ASD, relative to other disorders. Therefore, Japanese therapists could be more sensitive to and likely to diagnose ASD, relative to therapists in other countries. These findings suggest that cultural biases could influence clinicians' diagnosis of ADHD and ASD.
| S-EPMC5836146 | biostudies-literature
Project description:Attention-deficit/hyperactivity (ADHD) and autism spectrum (ASD) disorders are commonly co-occurring conditions characterized by neurocognitive impairments. Few studies have directly compared neurocognitive profiles in ADHD and ASD and fewer still have controlled for comorbidity of ADHD and ASD. All direct comparisons have been in clinic samples, leaving the question of generalizability of results unaddressed. We compared neurocognitive performance in clinically ascertained ASD (n = 261) and ADHD (n = 423) cases and controls (n = 162), 6.0-17.9 years of age. We also compared ASD (n = 190) and ADHD (n = 926) cases ascertained in the community with controls (n = 14,842) of similar age. Using the stop-signal task (SST), we measured response inhibition (stop-signal reaction time-SSRT), sustained attention (defined as reaction time variability-RTV), and reaction time (RT). We controlled for comorbidity using ADHD and ASD trait scores and categorically-defined ADHD. Compared with controls, both clinic ADHD and ASD had significantly longer SSRT and RTV than controls and did not differ from each other. ADHD traits accounted for neurocognitive impairment in ASD, but not vice versa. There were no group differences for RT. Similar patterns of neurocognitive impairment were observed in the community sample. In the largest direct comparison of ADHD and ASD to date, we found impaired response inhibition and sustained attention in both disorders. However, neurocognitive impairment in ASD was almost completely accounted for by comorbid ADHD. Results generalized in the community sample indicating that referral bias alone did not drive results. Response inhibition and sustained attention likely play a role in ADHD and ASD.
| S-EPMC9763138 | biostudies-literature
Project description:Attention deficit hyperactivity disorder (ADHD) and autism spectrum disorder (ASD) are neurodevelopmental conditions of overlapping etiologies and phenotypes. For ASD, we recently reported altered elemental metabolic patterns in the form of short and irregular zinc and copper cycles. Here, we extend the application of these biomarkers of prenatal and early postnatal elemental metabolism to distinguish between individuals diagnosed with ADHD and/or ASD and neurotypical controls. We recruited twins discordant for ADHD, ASD and other neurodevelopmental diagnoses from national twin studies in Sweden (N = 74) diagnosed according to DSM-5 clinical consensus and standardized psychiatric instruments. Detailed temporal profiles of exposure to 10 metals over the prenatal and early childhood periods were measured using tooth biomarkers. We used recurrence quantification analysis (RQA) to characterize properties of cyclical metabolic patterns of these metals. Regularity (determinism) and complexity (entropy) of elemental cycles was consistently reduced in ADHD for cobalt, lead, and vanadium (determinism: cobalt, β = -0.03, P = 0.017; lead, β = -0.03, P = 0.016; and vanadium, β = -0.03, P = 0.01. Entropy: cobalt, β = -0.13, P = 0.017; lead, β = -0.18, P = 0.016; and vanadium, β = -0.15, P = 0.008). Further, we found elemental pathways and dynamical features specific to ADHD vs ASD, and unique characteristics associated with ADHD/ASD combined presentation. Dysregulation of cyclical processes in elemental metabolism during prenatal and early postnatal development not only encompasses pathways shared by ADHD and ASD, but also comprise features specific to either condition.
| S-EPMC6760156 | biostudies-literature
Project description:ImportanceClinical overlap between autism spectrum disorder (ASD) and attention-deficit/hyperactivity disorder (ADHD) is increasingly appreciated, but the underlying brain mechanisms remain unknown to date.ObjectiveTo examine associations between white matter organization and 2 commonly co-occurring neurodevelopmental conditions, ASD and ADHD, through both categorical and dimensional approaches.Design, setting, and participantsThis investigation was a cross-sectional diffusion tensor imaging (DTI) study at an outpatient academic clinical and research center, the Department of Child and Adolescent Psychiatry at New York University Langone Medical Center. Participants were children with ASD, children with ADHD, or typically developing children. Data collection was ongoing from December 2008 to October 2015.Main outcomes and measuresThe primary measure was voxelwise fractional anisotropy (FA) analyzed via tract-based spatial statistics. Additional voxelwise DTI metrics included radial diffusivity (RD), mean diffusivity (MD), axial diffusivity (AD), and mode of anisotropy (MA).ResultsThis cross-sectional DTI study analyzed data from 174 children (age range, 6.0-12.9 years), selected from a larger sample after quality assurance to be group matched on age and sex. After quality control, the study analyzed data from 69 children with ASD (mean [SD] age, 8.9 [1.7] years; 62 male), 55 children with ADHD (mean [SD] age, 9.5 [1.5] years; 41 male), and 50 typically developing children (mean [SD] age, 9.4 [1.5] years; 38 male). Categorical analyses revealed a significant influence of ASD diagnosis on several DTI metrics (FA, MD, RD, and AD), primarily in the corpus callosum. For example, FA analyses identified a cluster of 4179 voxels (TFCE FEW corrected P < .05) in posterior portions of the corpus callosum. Dimensional analyses revealed associations between ASD severity and FA, RD, and MD in more extended portions of the corpus callosum and beyond (eg, corona radiata and inferior longitudinal fasciculus) across all individuals, regardless of diagnosis. For example, FA analyses revealed clusters overall encompassing 12121 voxels (TFCE FWE corrected P < .05) with a significant association with parent ratings in the social responsiveness scale. Similar results were evident using an independent measure of ASD traits (ie, children communication checklist, second edition). Total severity of ADHD-traits was not significantly related to DTI metrics but inattention scores were related to AD in corpus callosum in a cluster sized 716 voxels. All these findings were robust to algorithmic correction of motion artifacts with the DTIPrep software.Conclusions and relevanceDimensional analyses provided a more complete picture of associations between ASD traits and inattention and indexes of white matter organization, particularly in the corpus callosum. This transdiagnostic approach can reveal dimensional relationships linking white matter structure to neurodevelopmental symptoms.
| S-EPMC5710226 | biostudies-literature
Project description:The overlap/distinctiveness between Attention-Deficit/Hyperactivity Disorder (ADHD) and Autism Spectrum Disorder (ASD) has been increasingly investigated in recent years, particularly since the DSM-5 allows the dual diagnosis of ASD and ADHD, but the underlying brain mechanisms remain unclear. Although both disorders are associated with brain volumetric abnormalities, it is necessary to unfold the shared and specific volume abnormalities that could contribute to explain the similarities and differences in the clinical and neurocognitive profiles between ADHD and ASD. In this voxel-based morphometry (VBM) study, regional grey matter volumes (GMV) were compared between 22 children with ADHD, 18 children with ASD and 17 typically developing (TD) children aged 8 to 12 years old, controlling for age and total intracranial volume. When compared to TD children or children with ASD, children with ADHD had a larger left precuneus, and a smaller right thalamus, suggesting that these brain abnormalities are specific to ADHD relative to ASD. Overall, this study contributes to the delineation of disorder-specific structural abnormalities in ADHD and ASD.
| S-EPMC7652272 | biostudies-literature
Project description:Traditional diagnostic systems for neurodevelopmental disorders define diagnostic categories that are heterogeneous in behavior and underlying neurobiological alterations. The goal of this study was to parse heterogeneity in a core executive function (EF), cognitive flexibility, in children with a range of abilities (N = 132; children with autism spectrum disorder, attention-deficit/hyperactivity disorder [ADHD], and typically developing children) using directed functional connectivity profiles derived from resting-state functional magnetic resonance imaging data. Brain regions activated in response to a cognitive flexibility task in adults were used to guide region-of-interest selection to estimate individual connectivity profiles in this study. We expected to find subgroups of children who differed in their network connectivity metrics and symptom measures. Unexpectedly, we did not find a stable or valid subgrouping solution, which suggests that categorical models of the neural substrates of cognitive flexibility in children may be invalid. Exploratory analyses revealed dimensional associations between network connectivity metrics and ADHD symptomatology and EF ability across the entire sample. Results shed light on the validity of conceptualizing the neural substrates of cognitive flexibility categorically in children. Ultimately, this work may provide a foundation for the development of a revised nosology focused on neurobiological substrates as an alternative to traditional symptom-based classification systems.
| S-EPMC6862970 | biostudies-literature