Passive BCI Oddball Paradigm for Dementia Digital Neuro-biomarker Elucidation from Attended and Inhibited ERPs Utilizing Information Geometry Classification Approaches

Abstract

Brain-computer interface (BCI) and efficient machine learning (ML) algorithms belonging to the so-called ‘AI for social good’ domain contribute to the well-being improvement of patients with limited mobility or communication skills. We report preliminary results from a project focusing on developing a dementia digital neuro–biomarker for early-onset prognosis of a possible cognitive decline utilizing a passive BCI approach. We also report findings from two elderly volunteer pilot study groups in oddball paradigm EEG responses to attended (target) and inhibited (ignored) images in a classical short-term-memory evaluating oddball paradigm. We propose applying an information geometry approach employing Riemannian geometry tools for EEG covariance matrix-derived features used in subsequent shallow machine learning classification. The reported pilot study showcases the vital application of artificial intelligence (AI) for an early-onset mild cognitive impairment (MCI) prediction in the elderly.