Neural Mechanism Underlying Successful Classification of Amnestic Mild Cognitive Impairment Using Multi-Sensory-Evoked Potentials

Abstract

Introduction: The diagnosis, prognosis, and management of amnestic mild cognitive impairment (aMCI) remains challenging. Early detection of aMCI is crucial for timely interventions. Method: This study combines scalp recordings of auditory, visual, and somatosensory stimuli with a flexible and interpretable support vector machine classification pipeline to differentiate individuals diagnosed with aMCI from healthy controls. Results: Event-related potentials (ERPs) and functional connectivity (FC) matrices from each modality successfully predicted aMCI. We got optimal classification accuracy (96.1%), sensitivity (97.7%) and specificity (94.3%) when combining information from all sensory conditions than when using information from a single modality. Reduced ERP amplitude, higher FC in frontal region which predicted worse cognitive performance, and lower FC in posterior regions from delta to alpha frequency in aMCI contributed to classification. Conclusions: The results highlight the clinical potential of sensory-evoked potentials in detecting aMCI, with optimal classification using both amplitude and oscillatory-based FC measures from multiple modalities.