| Abstract |
The purpose of ‘NeuroGaze’ is to explore how eye-tracking technology and artificial intelligence can be used to help identify signs of Attention Deficit Hyperactivity Disorder (ADHD) earlier and more accurately. Currently diagnostic methods often rely on interviews, questionnaires, and observations, which can take time and has no defined answer. NeuroGaze aims to offer a faster, more objective tool that supports clinicians in making decisions.
This involves creating a web-based system where participants will do simple tasks, such as reading a paragraph, finding objects in a visual search, or reacting to changes on the screen. While performing these tasks, the system records eye data about their eye movements, how long they focus on certain points (fixations), how often their eyes move between points (saccades), and how consistently their eyes follow moving objects (smooth pursuit). Reaction times and attention shifts are also measured.
The data is stored in formats and analyzed with machine learning algorithms to identify patterns that may be linked with ADHD. As an example, people with ADHD often show shorter fixation durations, higher saccade frequency, and more irregular scanning behaviors. These differences can be used to distinguish between ADHD-like patterns and those seen in non-ADHD individuals.
In conclusion, NeuroGaze demonstrates how combining technology and AI can provide valuable, more objective insights into attention and focus. While not a replacement for professional diagnosis, it has the potential to support clinicians, reduce diagnosing times, and open a pathway for more accessible ADHD diagnosing into the future.
|