Related Experiment Video
Updated: May 27, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
A novel technology to screen for cognitive impairment in the elderly
David W Wright1, Harriet Nevárez, Patrick Kilgo
1Emory University School of Medicine, Department of Emergency Medicine, Atlanta, GA 30303, USA. david.wright@emory.edu
Background:
Traditional evaluation of mild cognitive impairment (MCI) can be costly, time consuming, and impractical for widespread screening. DETECT is a portable device developed to rapidly perform cognitive testing in diverse settings. This study compares DETECT with formal clinical assessment.
Methods:
A prospective cross-sectional comparison of the DETECT device versus an expert neuropsychologist's assessment (NPA). A total of 405 participants ≥65 years old, recruited from geriatric clinics and retirement facilities, completed both DETECT and NPA. Multivariable logistic regression methods were used to evaluate the degree of correlation between DETECT testing and the NPA diagnosis.
Results:
Predictive modeling demonstrated very good ability to discriminate between normal, MCI, and dementia per the NPA reference standard using DETECT subtests (c = 0.85 for any impairment; c = 0.99 for dementia).
Conclusion:
DETECT scores closely correlate with NPA. DETECT can identify and discriminate between normal, MCI, and dementia and could be incorporated as a screener for MCI.
More Related Videos
Related Concept Videos
Cognitive Development During Adulthood
Alzheimer Disease l: Introduction
Alzheimer's Disease: Treatment

