Dataset Information

Multi-modular AI Approach to Streamline Autism Diagnosis in Young Children.

ABSTRACT: Autism has become a pressing healthcare challenge. The instruments used to aid diagnosis are time and labor expensive and require trained clinicians to administer, leading to long wait times for at-risk children. We present a multi-modular, machine learning-based assessment of autism comprising three complementary modules for a unified outcome of diagnostic-grade reliability: A 4-minute, parent-report questionnaire delivered via a mobile app, a list of key behaviors identified from 2-minute, semi-structured home videos of children, and a 2-minute questionnaire presented to the clinician at the time of clinical assessment. We demonstrate the assessment reliability in a blinded, multi-site clinical study on children 18-72 months of age (n = 375) in the United States. It outperforms baseline screeners administered to children by 0.35 (90% CI: 0.26 to 0.43) in AUC and 0.69 (90% CI: 0.58 to 0.81) in specificity when operating at 90% sensitivity. Compared to the baseline screeners evaluated on children less than 48 months of age, our assessment outperforms the most accurate by 0.18 (90% CI: 0.08 to 0.29 at 90%) in AUC and 0.30 (90% CI: 0.11 to 0.50) in specificity when operating at 90% sensitivity.

SUBMITTER: Abbas H

PROVIDER: S-EPMC7081341 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multi-modular AI Approach to Streamline Autism Diagnosis in Young Children.

Abbas Halim H Garberson Ford F Liu-Mayo Stuart S Glover Eric E Wall Dennis P DP

Scientific reports 20200319 1

Autism has become a pressing healthcare challenge. The instruments used to aid diagnosis are time and labor expensive and require trained clinicians to administer, leading to long wait times for at-risk children. We present a multi-modular, machine learning-based assessment of autism comprising three complementary modules for a unified outcome of diagnostic-grade reliability: A 4-minute, parent-report questionnaire delivered via a mobile app, a list of key behaviors identified from 2-minute, sem ...[more]

PMID: 32193406

Similar Datasets

Project description:Introduction: Clinicians working with children with autism spectrum disorder (ASD) occupy an important position between parents and the wide-ranging research findings. However, it is not widely known how clinicians view and experience ASD in children, even though their perspective has been shown to significantly influence their work. Material and methods: Sixteen physicians working with preschool children without a diagnosis of (intellectual or other) disability with a (presumed) diagnosis of ASD participated in a semistructured interview. They described their professional views on ASD, and how they experienced its use in their clinical practice. The data were analyzed by applying the qualitative research method of interpretative phenomenological analysis of the data through Nvivo 11. Results: The main topic of the interviewed physicians' views and experiences of ASD in a young child comprised three inductively established themes: 1) physicians' views on ASD are multifaceted but fit within their personal clinical styles; 2) the ASD diagnosis is a "descriptive" part of a clinical trajectory; and 3) ASD treatment is a mix of "standard" approaches and a personalized search. These physicians' perspectives on ASD are composed of multiple and sometimes ambiguous facets. However, their views are embedded in their personal clinical styles in general (i.e., beyond ASD) and are experienced as clinically "workable." With the aim of finding an adequate approach to the problems parents bring to their office, many interviewed physicians say that-complementary to or rather than a classificatory diagnosis-they prefer using a personalized "profile" of a child in a therapeutic "process." Conclusions: The interviewed physicians consider doubts and concerns to be an inherent part of their clinical work with ASD in young children, but do not experience this ambiguity as an obstacle to clinical care. These physicians deal with the multiplicity of their views on ASD by basing their eclectic views on their generally adopted clinical styles, and by selecting what works for them, and for the parents and child, from what they regard as the 'textbook knowledge' on ASD. We discuss the implications of these findings for translating research results to the clinic.

Project description:ImportanceAutism spectrum disorder (ASD) affects 1 in 44 children. The Autism Diagnostic Observation Schedule (ADOS) is a semi-structured observation developed for use in research but is considered a component of gold standard clinical diagnosis. The ADOS adds time and cost to diagnostic assessments.ObjectiveTo evaluate consistency between clinical diagnosis (index ASD diagnosis) and diagnosis incorporating the ADOS (reference standard ASD diagnosis) and to examine clinician and child factors that predict consistency between index diagnoses and reference standard diagnoses.Design, setting, and participantsThis prospective diagnostic study was conducted between May 2019 and February 2020. Developmental-behavioral pediatricians (DBPs) made a diagnosis based on clinical assessment (index ASD diagnosis). The ADOS was then administered, after which the DBP made a second diagnosis (reference standard ASD diagnosis). DBPs self-reported diagnostic certainty at the time of the index diagnoses and reference standard diagnoses. The study took place at 8 sites (7 US and 1 European) that provided subspecialty assessments for children with concerns for ASD. Participants included children aged 18 months to 5 years, 11 months, without a prior ASD diagnosis, consecutively referred for possible ASD. Among 648 eligible children, 23 refused, 376 enrolled, and 349 completed the study. All 40 eligible DBPs participated.ExposuresADOS administered to all child participants.Main outcomes and measuresIndex diagnoses and reference standard diagnoses of ASD (yes/no).ResultsAmong the 349 children (279 [79.7%] male; mean [SD] age, 39.9 [13.4] months), index diagnoses and reference standard diagnoses were consistent for 314 (90%) (ASD = 250; not ASD = 64) and changed for 35. Clinician diagnostic certainty was the most sensitive and specific predictor of diagnostic consistency (area under curve = 0.860; P < .001). In a multilevel logistic regression, no child or clinician factors improved prediction of diagnostic consistency based solely on clinician diagnostic certainty at time of index diagnosis.Conclusions and relevanceIn this prospective diagnostic study, clinical diagnoses of ASD by DBPs with vs without the ADOS were consistent in 90.0% of cases. Clinician diagnostic certainty predicted consistency of index diagnoses and reference standard diagnoses. This study suggests that the ADOS is generally not required for diagnosis of ASD in young children by DBPs and that DBPs can identify children for whom the ADOS may be needed.

Project description:BackgroundAutism spectrum disorder (ASD) is a heterogeneous neurodevelopmental disorder characterized by impaired social interaction and communication and the occurrence of stereotyped and repetitive behaviors. Several studies have reported altered cytokine profiles in ASD and hence may serve as potential diagnostic biomarkers of the disorder. This study aims to identify diagnostic biomarkers for ASD in a well-defined study cohort in Qatar.MethodsWe measured the protein levels of 45 cytokines in the plasma samples of age- and gender-matched children (2-4 years) with ASD (n = 100) and controls (n = 60) using a Luminex multiplex assay. We compared the differences in the levels of these cytokines between the two study groups and then fitted the significantly altered cytokines into a logistic regression model to examine their diagnostic potential for ASD.ResultsWe found elevated levels of IFN-γ, FGF-2, IL-1RA, and IL-13 and reduced levels of eotaxin, HGF, IL-1 alpha, IL-22, IL-9, MCP-1, SCF, SDF-1 alpha, VEGFA, and IP-10 in the plasma of children with ASD compared to controls. Furthermore, we observed that elevated levels of IFN-γ (odds ratio (OR) = 1.823; 95% (confidence interval) CI = 1.206, 2.755; p = 0.004) and FGF-2 (OR = 2.528; 95% CI = 1.457, 4.385; p < 0.001) were significantly associated with increased odds of ASD, whereas reduced levels of eotaxin (OR = 0.350; 95% CI = 0.160, 0.765; p = 0.008) and HGF (OR = 0.220; 95% CI = 0.070, 0.696; p = 0.010) were significantly associated with lower odds of ASD relative to controls. The combination of these four cytokines revealed an area under the curve (ROC-AUC) of 0.829 (95% CI = 0.767, 0.891; p < 0.001), which demonstrates the diagnostic accuracy of the four-cytokine signature.ConclusionsOur results identified a panel of cytokines that could discriminate between children with ASD and controls in Qatar. In addition, our findings support the predominance of a Th1 immune phenotype in ASD children and emphasize the need to validate these results in larger populations.

Project description:Autism spectrum disorder is associated with an altered early brain development. However, the specific cortical structure abnormalities underlying this disorder remain largely unknown. Nonetheless, atypical cortical folding provides lingering evidence of early disruptions in neurodevelopmental processes and identifying changes in the geometry of cortical sulci is of primary interest for characterizing these structural abnormalities in autism and their evolution over the first stages of brain development. Here, we applied state-of-the-art sulcus-based morphometry methods to a large highly-selective cohort of 73 young male children of age spanning from 18 to 108 months. Moreover, such large cohort was selected through extensive behavioral assessments and stringent inclusion criteria for the group of 59 children with autism. After manual labeling of 59 different sulci in each hemisphere, we computed multiple shape descriptors for each single sulcus element, hereby separating the folding measurement into distinct factors such as the length and depth of the sulcus. We demonstrated that the central, intraparietal and frontal medial sulci showed a significant and consistent pattern of abnormalities across our different geometrical indices. We also found that autistic and control children exhibited strikingly different relationships between age and structural changes in brain morphology. Lastly, the different measures of sulcus shapes were correlated with the CARS and ADOS scores that are specific to the autistic pathology and indices of symptom severity. Inherently, these structural abnormalities are confined to regions that are functionally relevant with respect to cognitive disorders in ASD. In contrast to those previously reported in adults, it is very unlikely that these abnormalities originate from general compensatory mechanisms unrelated to the primary pathology. Rather, they most probably reflect an early disruption on developmental trajectory that could be part of the primary pathology.

Dataset Information

Multi-modular AI Approach to Streamline Autism Diagnosis in Young Children.

Publications

Multi-modular AI Approach to Streamline Autism Diagnosis in Young Children.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets