Related Experiment Video
Updated: Jan 6, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Predicting cognitive decline in Alzheimer's disease: A real-life proof-of-principle study on multimodal assessment
Francesco Motolese1,2, Davide Norata1,2, Gianmarco Iaccarino1
1Department of Medicine and Surgery, Unit of Neurology, Neurophysiology, Neurobiology and Psychiatry, Università Campus Bio-Medico di Roma, Roma, Italy.
Abstract:
BackgroundAlzheimer's disease (AD) is the most common neurodegenerative disorder. While AD diagnosis traditionally relies on clinical criteria, recent trends favor a precise biological definition. Existing biomarkers efficiently detect AD pathology but inadequately reflect the extent of cognitive impairment or disease heterogeneity. Alternative tools, such as neuroimaging and neurophysiological techniques, might better assess actual functional impairment.ObjectiveTo explore a multimodal approach-combining quantitative electroencephalography (EEG), cerebrospinal fluid (CSF), and cognitive assessment-to identify the most effective predictors of cognitive decline in AD patients.MethodsIn this observational study, 28 biologically confirmed AD patients underwent baseline evaluations including high-density EEG, CSF biomarker analysis, and cognitive assessment (Mini-Mental State Examination, MMSE). Cognitive assessment was repeated after one year. The rate of cognitive decline was calculated as monthly MMSE score change.ResultsMedian baseline age was 71.2 years. Median monthly MMSE decline was 0.25 points. Patients were classified into slow (≤0.25 MMSE/month) or fast (>0.25 MMSE/month) progressors. Fast progressors had significantly lower baseline individual alpha frequency (IAF) (6.8 Hz versus 9.1 Hz; p = 0.003), lower MMSE at one year (19 versus 24; p = 0.02), and more frequent diabetes and cardiovascular history. A multivariate regression analysis adjusted for age revealed that baseline IAF (p = 0.002), initial MMSE score (p = 0.028), and the p-tau/Aβ42 ratio (p < 0.01) significantly predicted monthly cognitive decline.ConclusionsCombining quantitative EEG-derived IAF, baseline cognitive status, and CSF biomarkers (p-tau/Aβ42 ratio) enhances prediction of AD progression. This integrated approach better captures disease heterogeneity, highlighting the need for multimodal strategies in the prognosis and management of AD.
More Related Videos
07:42Dual-Task Stroop Paradigm for Detecting Cognitive Deficits in High-Functioning Stroke Patients
Published on: December 16, 2022
06:46Automated, Long-term Behavioral Assay for Cognitive Functions in Multiple Genetic Models of Alzheimer's Disease, Using IntelliCage
Published on: August 4, 2018
Related Concept Videos
Alzheimer's Disease: Overview
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
Cognitive Development During Adulthood
Alzheimer's Disease: Treatment
Dementia
The progression of dementia is generally gradual....