A portable and efficient dementia screening tool using eye tracking machine learning and virtual reality

Authors: Ying Xu, Chi Zhang, Baobao Pan, Qing Yuan, Xu Zhang

Journal: npj Digital Medicine 7, 219 (2024)

DOI: 10.1038/s41746-024-01206-5

Published: 22 August 2024

Type: Original Article

Abstract

Dementia represents a significant global health challenge, with early screening during the preclinical stage being crucial for effective management. Traditional diagnostic biomarkers for Alzheimer’s Disease, the most common form of dementia, are limited by cost and invasiveness. Mild cognitive impairment (MCI), a precursor to dementia, is currently identified through neuropsychological tests like the Montreal Cognitive Assessment (MoCA), which are not suitable for large-scale screening. Eye-tracking technology, capturing and quantifying eye movements related to cognitive behavior, has emerged as a promising tool for cognitive assessment. Subtle changes in eye movements could serve as early indicators of MCI. However, the interpretation of eye-tracking data is challenging.

This study introduced a dementia screening tool, VR Eye-tracking Cognitive Assessment (VECA), using eye-tracking technology, machine learning, and virtual reality (VR) to offer a non-invasive, efficient alternative capable of large-scale deployment.

Methods and Results

• Participants: 201 participants from Shenzhen Baoan Chronic Hospital
• Technology: Eye-tracking data captured via VR headsets
• Model: Support vector regression (SVR) to predict MoCA scores and classify cognitive impairment across different educational backgrounds
• Performance:
  • High correlation (r = 0.9) with MoCA scores, significantly outperforming baseline models
  • Optimal cut-off scores for identifying cognitive impairment
  • Sensitivity: 88.5%
  • Specificity: 83%

Significance

• Demonstrates VECA’s potential as a portable, efficient tool for early dementia screening
• Highlights benefits of integrating eye-tracking technology, machine learning, and VR in cognitive health assessments
• Addresses limitations of traditional biomarkers (cost, invasiveness) and neuropsychological tests (unsuitability for large-scale screening)
• Enables non-invasive, large-scale deployable solution for preclinical screening

Key Points

• Dementia screening via VR-based eye tracking with ML analysis
• VECA predicts MoCA scores with r = 0.9 correlation
• 88.5% sensitivity, 83% specificity for cognitive impairment
• 201 participants across educational backgrounds
• Addresses cost and invasiveness limitations of traditional AD biomarkers