Artificial intelligence can significantly improve the accuracy of neural models using MRI brain scans to detect attention deficit hyperactivity disorder (ADHD), according to a study recently published in Radiology: Artificial Intelligence.1 The study, conducted by researchers from Ohio's University of Cincinnati and the Cincinnati Children's Hospital Medical Center, centers on the emerging idea of using brain imaging to detect signs of ADHD in patients. Currently, there is no single, definitive test for ADHD -- diagnosis comes after a series of symptom and behavioral tests. Research, however, suggests that ADHD can potentially be detected by studying the connectome -- a map of the brain's neural connections built by layering MRI scans of the brain, known as parcellations. Some studies suggest that a disrupted or interrupted connectome is linked to ADHD.

To develop a multichannel deep neural network (mcDNN) classification model based on multiscale brain functional connectome data and demonstrate the value of this model by using attention deficit hyperactivity disorder (ADHD) detection as an example. In this retrospective case-control study, existing data from the Neuro Bureau ADHD-200 dataset consisting of 973 participants were used. Multiscale functional brain connectomes based on both anatomic and functional criteria were constructed. The mcDNN model used the multiscale brain connectome data and personal characteristic data (PCD) as joint features to detect ADHD and identify the most predictive brain connectome features for ADHD diagnosis. The mcDNN model was compared with single-channel deep neural network (scDNN) models and the classification performance was evaluated through cross-validation and hold-out validation with the metrics of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).