Predicting ADHD Trajectories Of Children With Machine Learning Methods Using The Adolescent Brain Cognitive Development (ABCD) Study Dataset - Info and Reading Options

The Internet Archive:

This study aims to investigate the patterns of change in Attention Deficit and Hyperactivity Disorder (ADHD) symptoms and diagnoses over time. The goal is to identify types of change patterns in ADHD symptomology through a Latent Growth Curve Mixture Model (LGCM). To explain developmental trajectories, the identified typology classes will then be related to a selection of individual difference variables, or as called in machine learning terms, predictors (e.g. demographics, genetics, life events etc.) using a random forest model. In this study, we are using a large and longitudinal dataset consisting of American children from the Adolescent Brain Cognitive Development (ABCD) study. ADHD is a common neurodevelopmental disorder with a usually early childhood onset. Individuals with ADHD may suffer from impairments in paying and sustaining attention, impulsive behaviors, restlessness and hyperactivity. Hyperactivity symptoms are more salient during childhood. After puberty, hyperactivity tends to lessen, and inattentiveness is more present. Of the children with ADHD, 1 in 6 will continue to have ADHD as adults (Sibley et al., 2022). However, the current literature indicates that individual ADHD experiences tend to differ between individuals through development. ADHD is diagnosed by using the Diagnostic and Statistical Manual of Mental Disorders 5, the DSM-5 (American Psychiatric Association, 2013). The diagnostic criteria for ADHD consist of 9 inattention symptoms and 9 hyperactivity-impulsivity symptoms. When a child meets a minimum of 6 out of these 9 symptoms of hyperactivity-impulsivity, they may receive a predominantly hyperactive/impulsive ADHD diagnosis. The same applies to the inattention symptoms and the predominantly inattentive ADHD diagnosis. A third type is the combined ADHD diagnosis, where the child meets both the inattention and hyperactive-impulsive criteria. In addition, children must show some of the symptoms in more than one setting (e.g., classroom and at home) and before the age of 12 and there must be evident proof that the symptoms disrupt or diminish the level of social or academic performance. DSM-5 provides insight into the different types of ADHD and the severity of ADHD, but fails to capture the longitudinal changes that tend to occur in diagnostic status and subthreshold ADHD. In a longitudinal study, Sibley and colleagues (2022) tracked the ADHD trajectories of over 500 children from ages 2 to 16. They demonstrated that 63.8% of children had fluctuating ADHD, indicating that symptom patterns changed over time. Around 30% of children had periods where they were ADHD-free, but then 60% of those children had periods of recurrence. This study shed a very much needed light on the reality that ADHD is not a static disorder, on the contrary, it fluctuates over time. These important findings led us to our research question: Which individual differences variables contribute to different types of ADHD trajectories? To answer this question, we plan to use the largest longitudinal dataset that tracks the development of children, called the ABCD study. The ABCD study tracks over 11,000 children over a course of 10 years starting from ages 9-10 on, across 21 different data collection sites in the US. There are many measures from biospecimens, behavioral measures, to diagnostics. The current study is using the whole sample in order to be able to also detect possible subthreshold symptomology of ADHD.

Search for “Predicting ADHD Trajectories Of Children With Machine Learning Methods Using The Adolescent Brain Cognitive Development (ABCD) Study Dataset” downloads:

Visit our Downloads Search page to see if downloads are available.

Find “Predicting ADHD Trajectories Of Children With Machine Learning Methods Using The Adolescent Brain Cognitive Development (ABCD) Study Dataset” in Libraries Near You:

Read or borrow “Predicting ADHD Trajectories Of Children With Machine Learning Methods Using The Adolescent Brain Cognitive Development (ABCD) Study Dataset” from your local library.

• The WorldCat Libraries Catalog: Find a copy of “Predicting ADHD Trajectories Of Children With Machine Learning Methods Using The Adolescent Brain Cognitive Development (ABCD) Study Dataset” at a library near you.