Frontiers in child and adolescent psychiatry最新文献

Background: Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder with a complex etiology. The current diagnostic process for ADHD is often time-intensive and subjective. Recent advancements in machine learning offer new opportunities to improve ADHD diagnosis using diverse data sources. This study explores the potential of Fitbit-derived physical activity data to enhance ADHD diagnosis.

Method: We analyzed a sample of 450 participants from the Adolescent Brain Cognitive Development (ABCD) study (data release 5.0). Correlation analyses were conducted to examine associations between ADHD diagnosis and Fitbit-derived measurements, including sedentary time, resting heart rate, and energy expenditure. We then used multivariable logistic regression models to evaluate the predictive power of these measurements for ADHD diagnosis. Additionally, machine learning classifiers were trained to automatically classify individuals into ADHD+ and ADHD- groups.

Results: Our correlation analyses revealed statistically significant associations between ADHD diagnosis and Fitbit-derived physical activity data. The multivariable logistic regression models identified specific Fitbit measurements that significantly predicted ADHD diagnosis. Among the machine learning classifiers, the Random Forest outperformed others with cross-validation accuracy of 0.89, AUC of 0.95, precision of 0.88, recall of 0.90, F1-score of 0.89, and test accuracy of 0.88.

Conclusion: Fitbit-derived measurements show promise for predicting ADHD diagnosis, with machine learning classifiers, particularly Random Forest, demonstrating high predictive accuracy. These findings suggest that wearable data may contribute to more objective and efficient methods for ADHD identification, potentially enhancing clinical practices for diagnosis and management.

Introduction: Attention-Deficit/Hyperactivity Disorder (ADHD) significantly affects adolescents' everyday lives, particularly in emotion regulation and interpersonal relationships. Despite its high prevalence, ADHD remains underdiagnosed, highlighting the need for improved diagnostic tools. This study explores, for the first time, the potential of Natural Language Processing (NLP) and stylometry to identify linguistic markers within Self-Defining Memories (SDMs) of adolescents with ADHD and to evaluate their utility in detecting the disorder. A further novel aspect of this research is the use of SDMs as a linguistic dataset, which reveals meaningful patterns while engaging psychological processes related to identity and memory.

Method: Our objectives were to: (1) characterize linguistic features of SDMs in ADHD and control groups; (2) assess the predictive power of stylometry in classifying participants' narratives as belonging to either the ADHD or control group; and (3) conduct a qualitative analysis of key linguistic markers of each group. Sixty-six adolescents (25 diagnosed with ADHD and 41 typically developing peers) recounted SDMs in a semi-structured format; these narratives were transcribed for analysis. Stylometric features were extracted and used to train a Support Vector Machine (SVM) classifier to distinguish between narratives from the ADHD and control groups. Linguistic metrics such as wordcount, lexical diversity, lexical density, and cohesion were computed and analyzed. A qualitative analysis was also applied to examine stylistic patterns in the narratives.

Results: Adolescents with ADHD produced narratives that were shorter, less lexically diverse, and less cohesive. Stylometric analysis using an SVM classifier distinguished between ADHD and control groups with up to 100% precision. Distinct linguistic markers were identified, potentially reflecting difficulties in emotion regulation.

Discussion: These findings suggest that NLP and stylometry can enhance ADHD diagnostics by providing objective linguistic markers, thereby improving both its understanding and diagnostic procedures. Further research is needed to validate these methods in larger and more diverse populations.

Introduction: Childhood maltreatment (CM) has broad and severe adverse effects in later life, but there are not enough studies conducted during childhood close to the time of maltreatment. Most studies have focused only on a single symptom and have not attempted to capture the global picture of CM.

Methods: We used the Child Behavior Checklist (CBCL) to assess children's behavioral/emotional problems more comprehensively. This study leveraged 32 CM children and 29 typically developing (TD) children who have been assessed using the CBCL 4-18 from our dataset. Group comparisons of the eight subscales were conducted to characterize each behavioral/emotional problem. Receiver Operating Characteristic (ROC) curve analysis was conducted to assess the classification performance. Finally, sensitive period and type analyses were performed based on the children's maltreatment history.

Results: The CM group showed significantly higher behavioral/emotional problems in seven out of the eight subscales. Logistic regression analysis was performed using all combinations of CBCL subscale T-scores and age, sex, and IQ. We created 2047 models and performed ROC analysis for each. Three models were generated: the most accurate model (comprising CBCL T-score, age, sex, and IQ; sensitivity: 0.906, specificity: 0.966), a model excluding IQ (sensitivity: 0.875, specificity: 0.931), and a model consisting only of CBCL (sensitivity: 0.906, specificity: 0.862). The CBCL demonstrated robust predictive capacity for CM by utilizing information provided by caregivers, without directly inquiring about trauma. The sensitive period analysis revealed that the temporal predictor of severity for "withdrawn" and "thought problems" were exposure to CM at age five. Similarly, exposure to CM between the ages of five and seven predicted "somatic complaints". In the case of type, physical abuse was the predictor for "somatic complaints" and "delinquent behavior", and emotional abuse was the predictor for "anxious/depressed" and "thought problems".

Conclusion: Maltreated children present a wider range of behavioral/emotional problems, which must be considered when supporting them. Perspectives gained from sensitive analyses of maltreatment history will help clinicians provide more appropriate interventions.

Autistic individuals have an increased likelihood for negative adjustment relative to their peers, often as a result of adverse experiences. Consistent with the biosocial model of resilience and the growing neurodiversity movement, identifying factors that may contribute to positive outcomes among autistic individuals is an urgent research priority. The present review explores the existing literature on the role of self-advocacy and self-determination in promoting positive adjustment for autistic adolescents and young adults. Findings point to encouraging associations of self-advocacy and self-determination with various adjustment outcomes, including educational and employment outcomes, socialization, relationship development, identity development, self-concept, and quality of life. Implications are discussed, including limitations, directions for future research, and considerations for designing interventions that support autistic individuals to act with the agency and autonomy they desire.

Motor dysfunction is commonly associated with autism spectrum disorders (ASD). However, even if it may represent an intrinsic dimension of ASD it is not thought of as a relevant therapeutic target. Here we describe the postural, motor, and autistic characteristics of two children with ASD, a girl aged 3 years and 9 months and a boy aged 4 years and 7 months at enrollment, and their evolution over 20 or 23 months in response to interventions targeting these postural characteristics. Both met DSM-5 diagnosis critera for ASD. In both cases, asymmetric postures, twisting around the longitudinal axis, and underuse of the hands, particularly the thumbs, were observed. The children were repeatedly encouraged to engage in motor experiences involving their spatial cues and body axes and to correct their postures. We assessed more than fifty items describing motor particularities, communication, and social interactions. We observed a progressive and synchronous improvement in most of the items. In particular, communication and interaction skills improved in a similar way to motor skills. CARS scores also improved from 36 at initial assessment to 26 at the end of the follow-up for the boy and from 39.5 to 30 for the girl. These results suggest that motor dysfunction is an intrinsic dimension of autism and that interventions aimed at improving motor organization around a "body axis" could benefit children with ASD.

In the context of parent-child interaction, the Emotional Availability Scales have been developed to capture a dyad's emotional connection in an observational setting by four parental and two child-related scales. This study aims to test the psychometric foundation of the EAS, including basic descriptive preconditions on the item level and structural validity on the scale level, for a preschool-aged sample; as such, it complements analyses by Aran for a sample of infants. The sample of parents and their preschool-aged children is a mixed clinically referred and non-clinical sample from a midsize city in Germany. Interactions were observed in a free-play setting and rated with the EAS by two blind and certificated raters. Several model tests indicate violations for the structural model as well as all six measurement models. An additional post hoc exploratory factor analysis with parallel analysis suggests a non-interpretable two-factor structure. Psychometric analyses did not validate the EAS's postulated structure and measurement model. A post hoc literature review showed that ceiling effects on the item and scale levels are not unique to our study. However, traditionally important concepts or terms of parent-child relationships covered by the EAS are not rejected by our study and can be assessed with alternative measures, but these also need psychometric evaluation in the future.

The early onset, high prevalence, persistence and comorbidity of developmental disorders make affective dysregulation (AD) in childhood and adolescence one of the conditions with the greatest psychosocial burden and economic impact on society. Despite ongoing research, there remains a substantial need to optimize individualized treatment strategies to improve treatment outcomes and alleviate subjective distress and economic costs. The objective of this study is to investigate psychopathological markers of AD in children and adolescents with attention-deficit/hyperactivity disorder (ADHD) treated with the drug guanfacine as part of routine clinical care. These ADHD patients typically have not responded adequately to methylphenidate or other stimulant treatment. This study will employ a multicenter, single-arm design to evaluate the effects of guanfacine on AD symptoms in n = 40 patients of children and adolescents receiving regular ADHD treatment. The findings of this study are expected to address the hypothesis that guanfacine provides beneficial effects on symptoms of AD in addition to its effects on symptoms of ADHD.

Public clinical trial registry: Affective Dysregulation (AD) in Children With ADHD Treated by Guanfacin, ClinicalTrials.gov ID NCT04016207.

Background: Attention Deficit Hyperactivity Disorder (ADHD) among children younger than 6 years is quite impairing, nearly half these youth with ADHD experience school exclusion from mainstream preschool classes due to related emotional and behavioral outbursts. While a range of behavior rating scales and subjective measures are used to assess these youth, objective methods of assessment and prediction derived from technology have potential to improve therapeutic and academic interventions outcomes for these youths. We hypothesized that biometric sensors would provide objective, highly sensitive and specific information regarding the physiological status of children prior to an impulsive outburst and could be feasibly implemented using a wearable device in the special education classroom.

Methods: We recruited two whole classrooms (N = 5 youth in the pre-K class and N = 5 youth from the first grade) of a specialized therapeutic day-school for youth with ADHD and other psychiatric and developmental disorders to examine feasibility of obtaining continuous physiological data associated with behavioral and emotional outbursts through smartwatch use. Children wore a sensor watch during their daily classroom activities for two weeks and trained observers collected data using behavioral logs. Using Ecological Momentary Assessment methodology, to examine correlations between objective sensor data and observer observation. Data collected from parents regarding prior night's sleep was also examined.

Results: All participants completed the study. With a few tolerability or palatability issues. Associations were found between physiological and behavioral/questionnaire data. The methodology holds promise for reliably measuring behavioral and emotional outbursts in young children.

Conclusions: This is the first study to use a bio-marker device in vivo among severely dysregulated pre-school aged youth throughout a full school day. This study established the feasibility of utilizing sensor derived physiological data as an objective biomarker of ADHD within the special education therapeutic classroom. Further research with larger samples is required to build a more robust and personalized AI predictive model.