Computational Analysis of Movement Patterns of Dogs with ADHD-Like Behavior

SIMPLE SUMMARY: ADHD-like (attention deficit hyperactivity disorder) behavior in dogs may be expressed as impulsivity, inattentiveness, or aggression, compromising both dog and owner quality of life. Its treatment in a clinical setting requires behavioral modification and sometimes a medical treatment is added. There is a lack of objective tools for assessment and diagnosis of the problem, and behavioral experts mostly rely on owner reports. To address this gap, in this paper we use a self-developed computational tool which automatically analyzes movement of a dog from video footage collected during behavioral consultation. Based on a computational analysis of behavioral consultations of 12 dogs medically treated due to ADHD-like behavior and of a control group of 12 dogs with no reported behavioral problems, we identify three dimensions of characteristic movement patterns of dogs with ADHD-like behaviors, which are detectable during consultation. These include (i) high speed of movement, (ii) large coverage of room space, and (iii) frequent re-orientation in room space. These patterns can form the basis for computational methods for objective assessment of dogs with ADHD-like behavior that could help for diagnosis and clinical treatment of the disorder. ABSTRACT: Computational approaches were called for to address the challenges of more objective behavior assessment which would be less reliant on owner reports. This study aims to use computational analysis for investigating a hypothesis that dogs with ADHD-like (attention deficit hyperactivity disorder) behavior exhibit characteristic movement patterns directly observable during veterinary consultation. Behavioral consultations of 12 dogs medically treated due to ADHD-like behavior were recorded, as well as of a control group of 12 dogs with no reported behavioral problems. Computational analysis with a self-developed tool based on computer vision and machine learning was performed, analyzing 12 movement parameters that can be extracted from automatic dog tracking data. Significant differences in seven movement parameters were found, which led to the identification of three dimensions of movement patterns which may be instrumental for more objective assessment of ADHD-like behavior by clinicians, while being directly observable during consultation. These include (i) high speed, (ii) large coverage of space, and (iii) constant re-orientation in space. Computational tools used on video data collected during consultation have the potential to support quantifiable assessment of ADHD-like behavior informed by the identified dimensions.