Abstract ID: 26-483

Artificial Intelligence-Driven Virtual Reality Eye-Tracking for the Objective Assessment of Margin Reflex Distance

Author: Swati Parida
Base Hospital / Institution: Leicester Royal Infirmary

Presentation Type: Rapid Fire Presentation
Session: Eyelid Functional
Date: 12th September
Time: 09.03AM

Purpose

To evaluate an artificial intelligence-enabled virtual reality (VR) eye-tracking system (BulbiCAM) for automated measurement of eyelid position in blepharoptosis assessment.


Methods

101 patients with suspected blepharoptosis underwent clinician (standard of care) and VR (BulbiCAM) measurements of MRD1 and MRD2.The BulbiCAM device employs high-speed infrared video-oculography with convolutional neural network algorithms to automatically detect the pupil centre, corneal glint reflex, and eyelid margins. Agreement between the two methods was analysed using Pearson correlation and Bland–Altman plots. A predefined subset of participants were invited for a second visit >2 weeks after first assessment, to assess test–retest repeatability of the automated VR measurements. Feasibility was evaluated using both operator-recorded metrics and participant-reported experience measures.


Results

Automated measurements showed high agreement with standard clinical assessment, with mean differences of +0.29 mm for upper eyelid position and +0.01 mm for lower eyelid position. Strong correlations were observed between methods. Test-retest repeatability in 36 patients demonstrated mean differences of -0.03 mm and +0.27 mm between visits. Successful acquisition was achieved in all participants with a median of one attempt, and 98% reported the device as comfortable and easy to use.


Conclusion

This study demonstrates that AI-enabled VR eye-tracking provides automated eyelid measurements with excellent agreement to clinical standards, good repeatability, and high feasibility, supporting its potential role in enhancing objectivity and efficiency of ptosis assessment in both clinical practice and research settings.


Additional Authors

First name Last name Base Hospital / Institution
Reenette Savant University of Leicester
Agni Mokka Leicester Royal Infirmary
Mario Frank Farrugia Leicester Royal Infirmary
Mary Awad Leicester Royal Infirmary
Joyce Burns Leicester Royal Infirmary
Antonella Berry-Brincat Leicester Royal Infirmary
Raghavan Sampath Leicester Royal Infirmary
Mervyn Thomas Leicester Royal Infirmary

↑ Back to top