A novel eye-tracking digital marker outperforms plasma biomarkers in detecting cognitive impairment

Detecting and monitoring cognitive performance in older adults is critical. In this study, we evaluated the validity of an eye-tracking tool in diagnosing cognitive impairment.

We recruited 119 cognitively unimpaired (CU) individuals and 157 cognitively impaired (CI) patients who completed digital eye-tracking tests and cognitive scales. Of them, 154, 120, 53, and 146 underwent plasma biomarker tests, amyloid-β positron emission tomography (Aβ-PET) scans, tau-PET scans, and magnetic resonance imaging (MRI) scans. The diagnostic performance of eye-tracking markers and their relationships to Alzheimer's disease biomarkers and cognition were examined.

The eye-tracking panel exhibited better performance (area under the curve [AUC] = 0.865) in classifying CI from CU compared to plasma Aβ_42/40 (AUC = 0.699), p-Tau₂₁₇ (AUC = 0.769), p-Tau₂₁₇/Aβ₄₂ (AUC = 0.801), glial fibrillary acidic protein (GFAP; AUC = 0.804), and neurofilament light chain (NfL) (AUC = 0.826).

These findings demonstrate the validity of digital eye-tracking markers for screening patients with cognitive impairment, providing a novel digital marker for detecting cognitive decline in older adults.