Investigative Ophthalmology & Visual Science Cover Image for Volume 65, Issue 7
June 2024
Volume 65, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2024
Machine Learning, Artificial Intelligence and Eye Movements: Utility in Detection of Amblyopia
Author Affiliations & Notes
  • Egan Sanchez
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Dipak Prasad Upadhyaya
    Case Western Reserve University, Cleveland, Ohio, United States
  • Gokce Busra Cakir
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Aasef Shaikh
    VA Northeast Ohio Healthcare System, Cleveland, Ohio, United States
  • Ramat Stefano
    Universita degli Studi di Pavia, Pavia, Lombardia, Italy
  • Satya Sahoo
    Case Western Reserve University, Cleveland, Ohio, United States
  • Fatema Ghasia
    Cole Eye Institute, Cleveland Clinic, Cleveland, Ohio, United States
  • Footnotes
    Commercial Relationships   Egan Sanchez None; Dipak Upadhyaya None; Gokce Cakir None; Aasef Shaikh None; Ramat Stefano None; Satya Sahoo None; Fatema Ghasia None
  • Footnotes
    Support  Case Western Reserve University Biomedical Research Fellowship- Hartwell Foundation, Blind Children’s Foundation grant , and Research to Prevent Blindness Disney Amblyopia Award, CWRT CTSC Pilot Grant Program (F.G.), Cleveland Clinic RPC Grant, Lerner Research Institute Artificial Intelligence in Medicine, Departmental Grants from Research to Prevent Blindness, Unrestricted Block Grant CCLCM, NIH-NEI P30 Core Grant Award and Cleveland Eye Bank.
Investigative Ophthalmology & Visual Science June 2024, Vol.65, 4301. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Egan Sanchez, Dipak Prasad Upadhyaya, Gokce Busra Cakir, Aasef Shaikh, Ramat Stefano, Satya Sahoo, Fatema Ghasia; Machine Learning, Artificial Intelligence and Eye Movements: Utility in Detection of Amblyopia. Invest. Ophthalmol. Vis. Sci. 2024;65(7):4301.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : Amblyopia damages both visual sensory and ocular motor functions. One manifestation of the damage is abnormal fixation eye movements (FM)(Figure 1). Advances in eye-tracking have enabled an accurate and objective assessment of fixation in pediatric patients. Our study aims to integrate eye tracking technology with high-accuracy AI algorithms for detection of amblyopia.

Methods : High-resolution video-oculography was used to record FMs from 46 controls and 160 amblyopia subjects under binocular viewing (BV) and under right vs left eye viewing (MV, one eye blocked) conditions. The fixation and vergence stability were quantified using Bivariate Contour Ellipse Area (BCEA). The fast and slow FMs were analyzed using Engbert algorithms. The data was split 70:30 for training and testing ML and AI algorithms. We used fixation and vergence instability, fast and slow FM metrics to train ML models namely Random Forest, Decision Tree, Gradient Boost, AdaBoost classifiers to detect amblyopia. We also used two deep learning algorithms, namely Long Short-Term Memory (LSTM) and transformer in which the inputs were calibrated eye positions.

Results : The ML models detected the presence of amblyopia with an accuracy ranging 81-88% and ROC ranging 0.85-0.96. The LSTM and Transformer models predicted the severity of amblyopia with a ROC-AUC ranging from 0.71-0.81 for mild/treated and 0.82-0.89 for moderate/severe amblyopia subjects.

Conclusions : We have developed ML/AI tools using FM biomarkers that can reliably detect the presence and severity of amblyopia. Future work would comprise of developing AI algorithms that combine unique selected FM features with sequences of actual eye position data to optimize model performances.

This abstract was presented at the 2024 ARVO Annual Meeting, held in Seattle, WA, May 5-9, 2024.

 

Horizontal and vertical eye positions of right and left eye of control (A), fellow eye and amblyopic eye of treated (B), mild (C), moderate (D) and severe (D) amblyopia subjects obtained during a 45-second visual fixation trial in primary position during Binocular Viewing (BV), Monocular Viewing (FE) and Monocular viewing (AE). The log 68% BCEA values of fixation stability for each eye are included as a quantitative measure of fixation scatter – the greater the BCEA values the more unstable is the fixation (blue= fellow eye or left eye in control, red= amblyopic eye or right eye in control). The black arrows indicate the location of the target.

Horizontal and vertical eye positions of right and left eye of control (A), fellow eye and amblyopic eye of treated (B), mild (C), moderate (D) and severe (D) amblyopia subjects obtained during a 45-second visual fixation trial in primary position during Binocular Viewing (BV), Monocular Viewing (FE) and Monocular viewing (AE). The log 68% BCEA values of fixation stability for each eye are included as a quantitative measure of fixation scatter – the greater the BCEA values the more unstable is the fixation (blue= fellow eye or left eye in control, red= amblyopic eye or right eye in control). The black arrows indicate the location of the target.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×