Related Experiment Video
Updated: May 12, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Are empirically-derived subtypes of mild cognitive impairment consistent with conventional subtypes?
Lindsay R Clark1, Lisa Delano-Wood, David J Libon
1San Diego State University/University of California San Diego Joint Doctoral Program in Clinical Psychology, San Diego, CA, USA.
Diagnosing mild cognitive impairment (MCI) using different criteria yields varied subtypes. One method identified distinct Dysexecutive and Visuospatial subtypes, unlike conventional approaches.
Area of Science:
- Neuroscience
- Psychology
- Gerontology
Background:
- Identifying early signs of dementia, known as prodromes, is crucial for developing effective treatments.
- Mild cognitive impairment (MCI) is a transitional stage between normal aging and dementia.
- Standardized diagnostic criteria for MCI are essential for consistent research and clinical practice.
Purpose of the Study:
- To compare two distinct diagnostic methods for identifying mild cognitive impairment (MCI).
- To determine the consistency of empirically-derived MCI subtypes between these methods and conventional subtypes.
- To investigate whether different MCI diagnostic criteria yield comparable or distinct patient profiles.
Main Methods:
- Participants were diagnosed with MCI using either conventional Petersen/Winblad criteria or comprehensive neuropsychological criteria (Jak et al., 2009).
- Hierarchical cluster and discriminant function analyses were employed to examine the resulting MCI samples.
- Empirically-derived MCI subtypes were compared with conventional subtypes (amnestic, non-amnestic, single-domain, multi-domain).
Main Results:
- Neuropsychological profiles differed significantly based on the diagnostic criteria used for MCI.
- Both criteria identified an Amnestic MCI subtype, potentially indicating prodromal Alzheimer's disease (AD), and a Mixed subtype.
- Comprehensive criteria uniquely identified Dysexecutive and Visuospatial MCI subtypes; conventional criteria yielded a subtype with normal performance, suggesting potential false positives.
Conclusions:
- The choice of diagnostic criteria influences the identification of MCI subtypes.
- Comprehensive criteria may offer a more nuanced classification of MCI, revealing subtypes like Dysexecutive and Visuospatial.
- Further research is needed to validate these empirically-derived MCI subtypes and their association with neuropathology and dementia progression.
More Related Videos
Related Concept Videos
Dementia l: Introduction
Dementia
The progression of dementia is generally gradual.
Cognitive Enhancers: Cholinesterase Inhibitors and NMDA Receptor Antagonists
Cognitive Development During Adulthood
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...
Alzheimer Disease l: Introduction

