Related Experiment Video
Updated: Oct 9, 2025
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.7K
Cognitive screening with functional assessment improves diagnostic accuracy and attenuates bias
David Andrés González1,2, Mitzi M Gonzales1,2, Kyle J Jennette3
1Department of Neurology University of Texas Health Science Center at San Antonio San Antonio Texas USA.
Alzheimer'S & Dementia (Amsterdam, Netherlands)
|December 22, 2021
Summary
A new multitrait multimethod (MTMM) approach improves cognitive diagnosis accuracy and reduces racial disparities. This method combines cognitive screening and functional assessments for more equitable early intervention in dementia.
Area of Science:
- Neurology
- Gerontology
- Psychometrics
Background:
- Cognitive screening tools often lack sensitivity and exhibit ethnoracial inequities.
- Existing measures may not accurately identify cognitive impairment across diverse populations.
- A novel multitrait multimethod (MTMM) classification offers a potential solution to these limitations.
Purpose of the Study:
- To evaluate the diagnostic accuracy of an MTMM approach in cognitive impairment.
- To assess the MTMM approach's ability to reduce ethnoracial disparities in diagnosis.
- To compare the performance of different MTMM configurations.
Main Methods:
- Utilized data from 7227 participants in the National Alzheimer's Coordinating Center cohort.
- Employed random forest methods to predict diagnoses using demographically corrected Montreal Cognitive Assessment (MoCA) and Functional Assessment Questionnaire (FAQ).
- Compared three MTMM configurations: MoCA alone, MoCA + FAQ, and MoCA + FAQ with demographic correction.
Main Results:
- The MTMM approach with demographic correction achieved the highest diagnostic accuracy for cognitively unimpaired (AUC: 0.906) and mild cognitive impairment (AUC: 0.835) groups.
- This refined MTMM strategy significantly reduced racial disparities in diagnostic accuracy.
- All tested MTMM configurations outperformed single-measure assessments.
Conclusions:
- The MTMM approach integrating cognitive and functional assessments shows promise for enhancing diagnostic accuracy.
- This method has the potential to improve early detection of cognitive decline and facilitate equitable interventions.
- Further validation is recommended for widespread clinical application.
