Related Experiment Video
Updated: Oct 30, 2025

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Classification, Prediction, and Concordance of Cognitive and Functional Progression in Patients with Mild Cognitive
Julie Mouchet1, Keith A Betts2, Mihaela V Georgieva3
1F. Hoffmann-La Roche Ltd, Basel, Switzerland.
Background:
Progression trajectories of patients with mild cognitive impairment (MCI) are currently not well understood.
Objective:
To classify patients with incident MCI into different latent classes of progression and identify predictors of progression class.
Methods:
Participants with incident MCI were identified from the US National Alzheimer's Coordinating Center Uniform Data Set (09/2005-02/2019). Clinical Dementia Rating (CDR®) Dementia Staging Instrument-Sum of Boxes (CDR-SB), Functional Activities Questionnaire (FAQ), and Mini-Mental State Examination (MMSE) score longitudinal trajectories from MCI diagnosis were fitted using growth mixture models. Predictors of progression class were identified using multivariate multinomial logistic regression models; odds ratios (ORs) and 95% confidence intervals (CIs) were reported.
Results:
In total, 21%, 22%, and 57% of participants (N = 830) experienced fast, slow, and no progression on CDR-SB, respectively; for FAQ, these figures were 14%, 23%, and 64%, respectively. CDR-SB and FAQ class membership was concordant for most participants (77%). Older age (≥86 versus≤70 years, OR [95% CI] = 5.26 [1.78-15.54]), one copy of APOE ɛ4 (1.94 [1.08-3.47]), higher baseline CDR-SB (2.46 [1.56-3.88]), lower baseline MMSE (0.85 [0.75-0.97]), and higher baseline FAQ (1.13 [1.02-1.26]) scores were significant predictors of fast progression versus no progression based on CDR-SB (all p < 0.05). Predictors of FAQ class membership were largely similar.
Conclusion:
Approximately a third of participants experienced progression based on CDR-SB or FAQ during the 4-year follow-up period. CDR-SB and FAQ class assignment were concordant for the vast majority of participants. Identified predictors may help the selection of patients at higher risk of progression in future trials.
More Related Videos
08:43Application of Granger Causality Analysis of the Directed Functional Connection in Alzheimer's Disease and Mild Cognitive Impairment
Published on: August 7, 2017
07:31A Computerized Functional Skills Assessment and Training Program Targeting Technology Based Everyday Functional Skills
Published on: February 13, 2020
Related Concept Videos
Cognitive Development During Adulthood
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
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...