It has been remarked that conditions such as ADHD, Fetal Alcohol Spectrum Disorder and Parkinson's Disease all involve ocular control and attention dysfunctions and as such, according to studies, they can be identified by watching patients eye movements while the view TV.
Natural attention and eye movement behaviors are like a biological signature of an individual and their state of brain function or dysfunction. Each signature and especially potential biomarkers of some classified neurological conditions which they may contain, however, have not yet been decoded successfully.
The usual methods of detection are clinical evaluation, structured tasks in behaviour and neuroimaging but these are very are costly, labor-intensive and also limited by the patient's ability to understand and comply with given instructions.
Therefore a new screening method was devised.
The study subjects were merely asked to "watch and enjoy" television clips for 20 minutes meanwhile their eye movements were recorded. the data from the eye tracking was combined with normative eye-tracking data and a computer model of visual attention to extract 224 quantitative features. This allowed the investigating team to use new machine-learning techniques to identify critical features that differed from patient to patient as control subjects.
With the eye movement data the team identified older adults with Parkinson's Disease with 89.6 percent accuracy, and children with either ADHD or FASD with 77.3 percent accuracy. 108 subjects were used.
Providing new insights into which aspects of attention and gaze control are affected by specific disorders, the team's method provides considerable promise as an easily deployed, low-cost, high-throughput screening tool, especially for young children and elderly populations who may be less compliant to traditional tests.