Comparation of Machine Learning Algorithms for ADHD Detection with Eye Tracking

ADHD, or attention deficit hyperactivity disorder, is a persistent pattern of inattention that affects both young people and adults, causing interference with their functioning and overall development. The objective of this study is to develop an efficient diagnostic tool based on machine learning algorithms. The proposed tool utilizes eye-tracking technology to collect data on patients’ eye movements while engaging in a concentration game. The eye movement patterns are carefully analyzed and categorized into two groups: patients with ADHD and those without. Initially, a manual classification was performed, followed by the training of algorithms, resulting in F1 scores of 100%, 95.55%, and 60.86% for KNN, ANN, and SVM, respectively. The main goal of this project is to provide a comparation comparison between four machine learning techniques and get base for a diagnostic tool that surpasses the accuracy of current diagnostic methods. By achieving this, it aims to enhance the precision and efficiency of ADHD diagnosis, ultimately improving the quality of care and support provided to individuals with this condition.