Predicting cognitive change using functional, structural, and neuropsychological predictors.

Area of Science:

• Neuroscience
• Neurology
• Medical Imaging

Background:

• Alzheimer's disease (AD) requires understanding early signs and progression markers.
• Very early brain activation anomalies show promise for early AD characterization and predicting cognitive decline.

Purpose of the Study:

• To assess the predictive value of brain activation for cognitive change.
• To evaluate brain activation, alone and combined with structural and neuropsychological measures, for predicting cognitive decline.

Main Methods:

• 105 individuals with subjective cognitive decline or mild cognitive impairment from the CEmiDAD-Q cohort were studied.
• Cognitive decline was measured using Montreal Cognitive Assessment (MoCA) scores and regression models.
• Unimodal and multimodal models were used to predict cognitive decline based on functional, structural, and neuropsychological data.

Main Results:

• Functional brain activation alone predicted cognitive change with 52.5% R² and 98.7% specificity.
• The functional model showed high specificity but low sensitivity (60%) for predicting decline.
• Multimodal models demonstrated superior explanatory power and sensitivity compared to unimodal models.

Conclusions:

• Early brain activation anomalies are valuable for detecting future cognitive changes in individuals at risk for AD.
• Multimodal approaches enhance the prediction of cognitive decline, offering insights for risk assessment and clinical trials.
• These findings support the use of functional activation anomalies in early AD detection and research.