Abstract
Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzing the data obtained from two tri-axial accelerometers (one on the wrist of the dominant arm and the other on the ankle of the dominant leg) worn during school hours by a group of 22 children (11 children with ADHD and 11 paired controls). Five of the 11 ADHD diagnosed children were not on medication during the study. The children were not explicitly instructed to perform any particular activity but followed a normal session at school alternating classes of little or moderate physical activity with intermediate breaks of more prominent physical activity. The tri-axial acceleration signals were converted into 2D acceleration images and a Convolutional Neural Network (CNN) was trained to recognize the differences between non-medicated ADHD children and their paired controls. The results show that there were statistically significant differences in the way the two groups moved for the wrist accelerometer (t-test p-value <0.05). For the ankle accelerometer statistical significance was only achieved between data from the non-medicated children in the experimental group and the control group. Using a Convolutional Neural Network (CNN) to automatically extract embedded acceleration patterns and provide an objective measure to help in the diagnosis of ADHD, an accuracy of 0.875 for the wrist sensor and an accuracy of 0.9375 for the ankle sensor was achieved.
Highlights
Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which affects 3 to 5% of school-aged children [1,2]
In order to validate if there was a statistically significant difference between the acceleration images captured as described in Section 3 from typically developing non-ADHD controls and from participants with ADHD, a leave one out approach has been followed in order to train the Convolutional Neural Network (CNN) in ADHD classified acceleration images is greater or equal to that threshold
Each acceleration image in the validation set was fed into the CNN and the probability assigned after the softmax output layer for each group (ADHD, as learned from non-medicated data, or typically developing control) was recorded per image
Summary
Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which affects 3 to 5% of school-aged children [1,2]. There have been attempts to extract measures that correlate with ADHD symptoms from body worn physiological sensors Some of these objective tools are based on continuous performance tests (CPTs) [8] and electroencephalogram (EEG) [9]. Recently, new objective measures based on inertial sensors such as accelerometers and gyroscopes have been studied [10,11,12] These previous studies have focused on finding statistically significant differences in the data gathered from ADHD patients and typically developing non-ADHD controls when performing specific and predefined activities. ADHD diagnosed children were further divided into a non-medicated group and a medicated group so that the effect of medication on movement could be isolated
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
