Deep learning-assisted ADHD diagnosis.

Attention deficit hyperactivity disorder (ADHD) can have a negative impact on children's development, even into adulthood, so the early diagnosis and screening for ADHD can be an important prerequisite for later intervention. However, the traditional diagnostic methods have limitations in terms of objectivity, convenience and efficiency. With the development of artificial intelligence, deep learning, as an emerging computer technology that can deal with massive data and variables, has gradually been applied to early prediction of ADHD in children and aiding diagnosis. From the traditional diagnostic methods to one based on conventional feature analysis, such as the diagnosis of ADHD in children based on EEG data analysis. With the continuous development of computer technology, the analysis and diagnosis of EEG data based on deep learning, and the combination of deep learning model and computer vision technology have been emerged. Due to the incompleteness of the analysis and diagnosis of unimodal data, the deep learning models of multimodal data can have a strong integrity, which has become a hot spot at present. However, deep learning still has limitations in hardware cost and algorithm selection. In the future, further research is needed in deep learning-assisted diagnosis to continuously optimize the algorithm and accelerate the improvement of ADHD intelligent identification and diagnosis ability.