Dataset Information

Machine Learning for Differential Diagnosis Between Clinical Conditions With Social Difficulty: Autism Spectrum Disorder, Early Psychosis, and Social Anxiety Disorder.

ABSTRACT: Differential diagnosis in adult cohorts with social difficulty is confounded by comorbid mental health conditions, common etiologies, and shared phenotypes. Identifying shared and discriminating profiles can facilitate intervention and remediation strategies. The objective of the study was to identify salient features of a composite test battery of cognitive and mood measures using a machine learning paradigm in clinical cohorts with social interaction difficulties. We recruited clinical participants who met standardized diagnostic criteria for autism spectrum disorder (ASD: n = 62), early psychosis (EP: n = 48), or social anxiety disorder (SAD: N = 83) and compared them with a neurotypical comparison group (TYP: N = 43). Using five machine-learning algorithms and repeated cross-validation, we trained and tested classification models using measures of cognitive and executive function, lower- and higher-order social cognition and mood severity. Performance metrics were the area under the curve (AUC) and Brier Scores. Sixteen features successfully differentiated between the groups. The control versus social impairment cohorts (ASD, EP, SAD) were differentiated by social cognition, visuospatial memory and mood measures. Importantly, a distinct profile cluster drawn from social cognition, visual learning, executive function and mood, distinguished the neurodevelopmental cohort (EP and ASD) from the SAD group. The mean AUC range was between 0.891 and 0.916 for social impairment versus control cohorts and, 0.729 to 0.781 for SAD vs neurodevelopmental cohorts. This is the first study that compares an extensive battery of neuropsychological and self-report measures using a machine learning protocol in clinical and neurodevelopmental cohorts characterized by social impairment. Findings are relevant for diagnostic, intervention and remediation strategies for these groups.

SUBMITTER: Demetriou EA

PROVIDER: S-EPMC7319094 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning for Differential Diagnosis Between Clinical Conditions With Social Difficulty: Autism Spectrum Disorder, Early Psychosis, and Social Anxiety Disorder.

Demetriou Eleni A EA Park Shin H SH Ho Nicholas N Pepper Karen L KL Song Yun J C YJC Naismith Sharon L SL Thomas Emma E EE Hickie Ian B IB Guastella Adam J AJ

Frontiers in psychiatry 20200619

Differential diagnosis in adult cohorts with social difficulty is confounded by comorbid mental health conditions, common etiologies, and shared phenotypes. Identifying shared and discriminating profiles can facilitate intervention and remediation strategies. The objective of the study was to identify salient features of a composite test battery of cognitive and mood measures using a machine learning paradigm in clinical cohorts with social interaction difficulties. We recruited clinical partici ...[more]

PMID: 32636768

Similar Datasets

Project description:Current literature is divided over whether and how processes such as perspective taking and reward sensitivity differ between individuals with autism spectrum disorder (ASD) versus neurotypical individuals. Discounting tasks may provide novel insight into how these processes operate. In delay discounting tasks, participants choose between smaller immediate rewards and larger delayed rewards, and in social discounting tasks, participants choose between a smaller monetary rewards for themselves versus a larger reward for partners of varied social distance (e.g., a close friend vs. an acquaintance). Delay and social discounting tasks thus implicitly measure the subjective value of rewards given to one's future self and to others, capturing constructs such as perspective taking, reward processing, and social closeness, all of which have been discussed as core cognitive mechanisms underlying ASD. Despite extensive research on discounting in other clinical populations, few studies have examined delay discounting in ASD and no research has examined social discounting in ASD. The goal of the current study was to assess delay and social discounting for monetary rewards in a single sample of adolescents and adults with ASD compared to a matched neurotypical sample. Overall, adults and adolescents with ASD valued both future rewards and rewards given to others less than their typical counterparts did, but rates of discounting were not significantly correlated across temporal and social domains. These results extend an important behavioral paradigm for understanding both perspective taking and reward processing to autism. Autism Res 2019, 12: 870-877. © 2019 International Society for Autism Research, Wiley Periodicals, Inc. LAY SUMMARY: Discounting tasks-which experimentally measure the subjective value of different rewards-have been used with a variety of clinical populations, but are underexplored in ASD. We found that compared to neurotypical individuals, individuals with ASD showed diminished subjective value for future rewards (compared to immediate rewards) and rewards for others (compared to rewards for self). This finding has implications for understanding perspective taking, reward processing, and social closeness in ASD.

Dataset Information

Machine Learning for Differential Diagnosis Between Clinical Conditions With Social Difficulty: Autism Spectrum Disorder, Early Psychosis, and Social Anxiety Disorder.

Publications

Machine Learning for Differential Diagnosis Between Clinical Conditions With Social Difficulty: Autism Spectrum Disorder, Early Psychosis, and Social Anxiety Disorder.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets