Related Experiment Video
Updated: Jul 10, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Identifying populations with faster cognitive decline using blood-based biomarkers
James Russell Pike1, Yongmei Liu2, Theresa Chisolm3
1Optimal Aging Institute New York University Grossman School of Medicine New York New York USA.
Introduction:
Identifying individuals who undergo cognitive decline is vital to the success of prevention trials that aim to slow cognitive decline. Yet, the benefits of using blood-based biomarkers of neurodegeneration, as well as amyloid and tau, to enrich population-based prevention trials have not been quantified.
Methods:
The association of thresholds of Quanterix single molecule array (SiMoA) assays with subsequent change in cognition was estimated in the Atherosclerosis Risk in Communities cohort (N = 1826) using linear mixed effects models, validated in the Multi-Ethnic Study of Atherosclerosis cohort (N = 383), and extended to Alamar Nucleic acid Linked Immuno-Sandwich Assay (NULISA) assays in the Aging and Cognitive Health Evaluation in Elders cohort (N = 552).
Results:
Elevated plasma biomarker levels identified dementia-free older adults with faster cognitive decline. By selecting participants with Quanterix SiMoA measurements of neurofilament light > 30.65 pg/mL, the sample size needed to detect a 33% reduction in cognitive decline in a clinical trial decreased by 57%.
Discussion:
Clinical trials can use plasma biomarkers as a screening tool to increase statistical power.
Related Concept Videos
Dementia l: Introduction
Alzheimer Disease l: Introduction
Cognitive Development During Adulthood
Dementia
The progression of dementia is generally gradual.
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 and tau...

