Dataset Information

Multimodal Ensemble Deep Learning to Predict Disruptive Behavior Disorders in Children.

ABSTRACT: Oppositional defiant disorder and conduct disorder, collectively referred to as disruptive behavior disorders (DBDs), are prevalent psychiatric disorders in children. Early diagnosis of DBDs is crucial because they can increase the risks of other mental health and substance use disorders without appropriate psychosocial interventions and treatment. However, diagnosing DBDs is challenging as they are often comorbid with other disorders, such as attention-deficit/hyperactivity disorder, anxiety, and depression. In this study, a multimodal ensemble three-dimensional convolutional neural network (3D CNN) deep learning model was used to classify children with DBDs and typically developing children. The study participants included 419 females and 681 males, aged 108-131 months who were enrolled in the Adolescent Brain Cognitive Development Study. Children were grouped based on the presence of DBDs (n = 550) and typically developing (n = 550); assessments were based on the scores from the Child Behavior Checklist and on the Schedule for Affective Disorders and Schizophrenia for School-age Children-Present and Lifetime version for DSM-5. The diffusion, structural, and resting-state functional magnetic resonance imaging (rs-fMRI) data were used as input data to the 3D CNN. The model achieved 72% accuracy in classifying children with DBDs with 70% sensitivity, 72% specificity, and an F1-score of 70. In addition, the discriminative power of the classifier was investigated by identifying the cortical and subcortical regions primarily involved in the prediction of DBDs using a gradient-weighted class activation mapping method. The classification results were compared with those obtained using the three neuroimaging modalities individually, and a connectome-based graph CNN and a multi-scale recurrent neural network using only the rs-fMRI data.

SUBMITTER: Menon SS

PROVIDER: S-EPMC8652047 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCross-sectional studies have demonstrated associations between screen time and disruptive behavior disorders (conduct disorder and oppositional defiant disorder); however, prospective associations remain unknown. This study's objective was to determine the prospective associations of contemporary screen time modalities with conduct and oppositional defiant disorder in a national cohort of 9-11-year-old children.MethodsWe analyzed data from the Adolescent Brain Cognitive Development (ABCD) Study (N = 11,875). Modified Poisson regression analyses were conducted to estimate the associations between baseline child-reported screen time (total and by modality) and parent-reported conduct or oppositional defiant disorder based on the Kiddie Schedule for Affective Disorders and Schizophrenia (KSADS-5) at 1-year follow-up, adjusting for potential confounders.ResultsParticipants reported an average of 4 hr of total screen time per day at baseline. Each hour of total screen time per day was prospectively associated with a 7% higher prevalence of conduct disorder (95% CI 1.03-1.11) and a 5% higher prevalence of oppositional defiant disorder (95% CI 1.03-1.08) at 1-year follow-up. Each hour of social media per day was associated with a 62% higher prevalence of conduct disorder (95% CI 1.39-1.87). Each hour of video chat (prevalence ratio [PR] 1.21, 95% CI 1.06-1.37), texting (PR 1.19, 95% CI 1.07-1.33), television/movies (PR 1.17, 95% CI 1.10-1.25), and video games (PR 1.14, 95% CI 1.07-1.21) per day was associated with a higher prevalence of the oppositional defiant disorder. When examining thresholds, exposure to >4 hr of total screen time per day was associated with a higher prevalence of conduct disorder (69%) and oppositional defiant disorder (46%).ConclusionsHigher screen time was prospectively associated with a higher prevalence of new-onset disruptive behavior disorders. The strongest association was between social media and conduct disorder, indicating that future research and interventions may focus on social media platforms to prevent conduct disorder.

Project description:ObjectiveDisrupted reward processing is implicated in the etiology of disruptive behavior disorders (DBDs) and callous-unemotional traits. However, neuroimaging investigations of reward processing underlying these phenotypes remain sparse. The authors examined neural sensitivity in response to reward anticipation and receipt among youths with DBDs, with and without callous-unemotional traits.MethodsData were obtained from the Adolescent Brain and Cognitive Development Study (mean age=9.51 years [SD=0.50]; 49% female). Reward-related activation during the monetary incentive delay task was examined across 16 brain regions, including the amygdala, anterior cingulate cortex (ACC), nucleus accumbens (NAcc), and orbitofrontal cortex (OFC). Latent variable modeling was used to examine network-level coactivation. The following diagnostic groups were compared: typically developing youths (N=693) and youths with DBDs (N=995), subdivided into those with callous-unemotional traits (DBD+CU, N=198) and without callous-unemotional traits (DBD only, N=276).ResultsDuring reward anticipation, youths in the overall DBD group (with and without callous-unemotional traits) showed decreased dorsal ACC activation compared with typically developing youths. The DBD-only group exhibited reduced ventral and dorsal striatal activity compared with the DBD+CU and typically developing groups. During reward receipt, youths with DBDs showed increased cortical (e.g., OFC) and subcortical (e.g., NAcc) regional activation compared with typically developing youths. The DBD+CU group demonstrated greater activation in several regions compared with those in the typically developing (e.g., amygdala) and DBD-only (e.g., dorsal ACC) groups. At the network level, the DBD-only group showed reduced anticipatory reward activation compared with the typically developing and DBD+CU groups, whereas youths in the DBD+CU group showed increased activation during reward receipt compared with those in the typically developing group.ConclusionsThese findings advance our understanding of unique neuroetiologic pathways to DBDs and callous-unemotional traits.

Project description:Disruptive behaviour disorders (DBDs) in childhood include conduct disorder (CD) and oppositional defiant disorder (ODD). Though psychological therapies are considered to be the first-line treatment for DBDs, many patients require adjunctive pharmacotherapy for the control of specific symptoms, such as aggression. Three prior systematic reviews have examined the evidence for the use of antipsychotics in DBDs and have concluded that their efficacy is marginal and limited by adverse effects. This paper has two objectives: (i) to summarize the findings of existing systematic reviews of antipsychotics for the management of DBDs in children and adolescents (2012-2017), and (ii) to provide an update to these reviews by examining recent clinical trials of antipsychotics in this population, published in the period from 2 January 2017 to 10 October 2022. The PubMed, Scopus and ScienceDirect databases were searched for relevant citations using the search terms "disruptive behaviour disorder", "oppositional defiant disorder", "conduct disorder" and their variants, along with "antipsychotic", "atypical antipsychotic" and the generic names of all currently approved atypical antipsychotics. Six relevant trials were identified during this period, including five randomized controlled trials and one naturalistic open-label trial. These trials were critically evaluated in terms of outcome measures, efficacy and safety. Overall, the data from these trials suggests that of all available antipsychotics, risperidone appears to be effective in the short-term management of DBDs. All available antipsychotics are associated with significant metabolic adverse effects in this population. These results are discussed in the light of global trends towards increasing off-label prescription of antipsychotic medication in children and adolescents and of recent literature on the neuropharmacology of aggression in this patient population. The need for rational, short-term use of these drugs is highlighted, as well as the importance of post-marketing surveillance for long-term or severe adverse events.

Project description:ObjectiveYouths with disruptive behavior disorders (DBD) (conduct disorder and oppositional defiant disorder) have an elevated risk for maladaptive reactive aggression. Theory suggests that this is due to an elevated sensitivity of basic threat circuitry implicated in retaliation (amygdala/periaqueductal gray) in youths with DBD and low levels of callous-unemotional traits and dysfunctional regulatory activity in the ventromedial prefrontal cortex in youths with DBD irrespective of callous-unemotional traits.MethodA total of 56 youths 10-18 years of age (23 of them female) participated in the study: 30 youths with DBD, divided by median split into groups with high and low levels of callous-unemotional traits, and 26 healthy youths. All participants completed an ultimatum game task during functional MRI.ResultsRelative to the other groups, youths with DBD and low levels of callous-unemotional traits showed greater increases in activation of basic threat circuitry when punishing others and dysfunctional down-regulation of the ventromedial prefrontal cortex during retaliation. Relative to healthy youths, all youths with DBD showed reduced amygdala-ventromedial prefrontal cortex connectivity during high provocation. Ventromedial prefrontal cortex responsiveness and ventromedial prefrontal cortex-amygdala connectivity were related to patients' retaliatory propensity (behavioral responses during the task) and parent-reported reactive aggression.ConclusionsThese data suggest differences in the underlying neurobiology of maladaptive reactive aggression in youths with DBD who have relatively low levels of callous-unemotional traits. Youths with DBD and low callous-unemotional traits alone showed significantly greater threat responses during retaliation relative to comparison subjects. These data also suggest that ventromedial prefrontal cortex-amygdala connectivity is critical for regulating retaliation/reactive aggression and, when dysfunctional, contributes to reactive aggression, independent of level of callous-unemotional traits.

Dataset Information

Multimodal Ensemble Deep Learning to Predict Disruptive Behavior Disorders in Children.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets