Abstract:

Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental clinical entity associated with a reduction in brain maturation mainly at the frontotemporal level, generating neurocognitive deficits. This disorder usually presents in a comorbid manner. This research presents a predictive study that aimed to identify the neurocognitive characteristics of ADHD (combined, hyperactive/impulsive, and inattentive) of pure presentation and with comorbidity with the oppositional defiant disorder, specific learning disorder, and an autism spectrum disorder. Probabilistic rules were constructed with different types of variables (total IQ, working memory index, perceptual reasoning index, processing speed index, phonological/semantic fluency, attention, visuoverbal memory, verbal memory, working memory, visual memory, visual perception, constructional praxias), using the Machine Learning Decision Tree (DTM) technique in Rcran 4.2.1 software, which allowed establishing a clinical hierarchy. It is concluded that children with pure ADHD present low performance in tasks assessing the index of working memory and perceptual reasoning that are not explained by deficits in IQ. Deficits in working memory are generalizable to all ADHD presentations and comorbidities. One of the main advantages of DTM compared to other Machine Learning predictive techniques is the possibility of differentiating the hierarchy of importance of the dependent variables, in this case, allowing the identification of the most important variables in four different populations of children diagnosed with ADHD.

Keywords: