How it Works

Home Work

Our Method

1. Experimental Setup

We administer a 20 minute visuospatial working memory task from a VR wearable, which is used to assess attentional performance.

2. Detailed Eye Biometrics

We record eye biometrics as a patient completes a task, looking at pupillometrics and eye gaze directions, which are then analyzed using our algorithms.

3. Machine/Deep Learning Backend

We analyze this biometric data using our proprietary algorithms to generate a detailed report of eye movements.

4. Exploratory Platform

A summary of eye biometrics is presented, along with detailed statistics and a probability of a patient having ADHD. We provide a platform for further examining these metrics.


Our method was recently published in Nature Scientific Reports.


Relevant Publications

  1. "A Robust Machine Learning Based Framework for the Automated Detection of ADHD Using Pupillometric Biomarkers and Time Series Analysis" - August 2021, Nature Scientific Reports
  2. "A Novel Pupillometric Based Application for the Automated Detection of ADHD Using Machine Learning" - 2020 11th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB)
  3. "A Machine Learning Approach for the Automated Diagnosis of ADHD: Implications and Significance for Sustainable Youth Development Policies" - Proceedings of the U.N. SDSN 4th International Conference on Sustainable Development
  4. "A Novel Application for the Efficient and Accessible Diagnosis of ADHD Using Machine Learning" - 2020 IEEE / ITU International Conference on AI for Good