Related Experiment Video
Updated: Mar 25, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
First Analysis of Mild Behavioral Impairment in a Sample of Mexican Older Adults
Ángela Acosta-Amaya1,2, Salvador Sánchez-Badajos3, David J Dávila-Ortiz de Montellano4
1Laboratorio de Neuropsicología Clínica, Instituto Nacional de Neurología y Neurocirugía, Manuel Velasco Suárez (INNNMVS), Mexico City 14269, Mexico.
Abstract:
Mild behavioral impairment (MBI) constitutes a late-life transition state that is associated with an increased risk of cognitive impairment and dementia. Herein, we cross-sectionally describe the MBI construct and its relationship with cognitive status in Mexican-Mestizos (MM) older adults. Participants were classified according to their cognitive and behavioral statuses using tests administered to older adults and their informants. APOE_rs429358/rs7412 variants were genotyped by real-time PCR. Multivariate correlation and Principal Components Analysis (PCA) were used in statistical analysis. A total of 246 participants were included, 56.1% were classified as individuals with NC, 13.0% had subjective cognitive decline, and 30.9% had mild cognitive impairment. A total of 37% (91/246) of participants from all over the cognitive spectrum met the MBI criteria; among this group, APOEε4 homozygosity was associated with two subdomains of the MBI. Subjective cognitive complaint, symptoms of depression, and cognitive decline reported by the informant were associated with an increased risk for MBI (ORs in the range of 4.7-15.89). The first three components of PCA explained 68.0% of the variance of the dataset, including the MBI-checklist total score as a main contributor. Well-known risk factors for dementia also correlated with this PCA. MBI could be a potential marker for cognitive decline in non-demented MM elderly people; however, observed associations should be confirmed in future longitudinal studies.

