Automatic diagnosis of ADHD based on multichannel nonlinear analysis of actimetry registries

Attention-Deficit Hyperactivity Disorder (ADHD) is the most common mental health problem in childhood and adolescence. It is commonly diagnosed by means of subjective methods which tend to overestimate the severity of the pathology. A number of objective methods also exist, but they are either expensive or time-consuming. Some recent proposals based on nonlinear processing of activity registries have deserved special attention. Since they rely on actigraphy measurements, they are both inexpensive and non-invasive. Among these methods, those shown to have higher reliability are based on single-channel complexity assessment of the activity patterns. This way, potentially useful information related to the interaction between the different channels is discarded. In this paper we propose a new methodology for ADHD diagnosis based on joint complexity assessment of multichannel activity registries. Results on real data show that the proposed method constitute a useful diagnostic aid tool reaching 87.10% sensitivity and 84.38% specificity. The combination of ADHD indicators extracted with the proposed method with single-channel complexity-based indices previously proposed lead to sensitivity and specifity values above 90%.