A multi-stage feature selection method to improve classification of potential super-agers and cognitive decliners using structural brain MRI data-a UK biobank study

Parvin Mohammadiarvejeh; Mohammad Fili; Alice Dawson; Brandon S Klinedinst; Qian Wang; Shannin Moody; Neil Barnett; Amy Pollpeter; Brittany Larsen; Tianqi Li; Sara A Willette; Jonathan P Mochel; Karin Allenspach; Guiping Hu; Auriel A Willette

doi:10.1007/s11357-024-01458-9

Back

A multi-stage feature selection method to improve classification of potential super-agers and cognitive decliners using structural brain MRI data-a UK biobank study

Journal article

Open access

Peer reviewed

A multi-stage feature selection method to improve classification of potential super-agers and cognitive decliners using structural brain MRI data-a UK biobank study

Parvin Mohammadiarvejeh, Mohammad Fili, Alice Dawson, Brandon S Klinedinst, Qian Wang, Shannin Moody, Neil Barnett, Amy Pollpeter, Brittany Larsen, Tianqi Li, …

GeroScience, Vol.47(3), pp.3807-3819

06/2025

DOI: 10.1007/s11357-024-01458-9

PMCID: PMC12181481

PMID: 39656405

Files and links (1)

url

https://doi.org/10.1007/s11357-024-01458-9View

Published (Version of record) Open Access

Abstract

Cognitive aging is described as the age-related decline in areas such as memory, executive function, reasoning, and processing speed. Super-Agers, adults over 80 years old, have cognitive function performance comparable to middle-aged adults. To improve cognitive reserve and potentially decrease Alzheimer's disease (AD) risk, it is essential to contrast changes in regional brain volumes between "Positive-Agers" who have superior cognitive performance compared to their age peers but are not 80 years old yet and aging adults who show cognitive decline (i.e., "Cognitive Decliners"). Using longitudinal cognitive tests over 7-9 years in UK Biobank, principal component analysis (PCA) was first applied to four cognitive domains to create a general cognition (GC) composite score. The GC score was then used to identify latent cognitive groups. Given cognitive groups as the target variable and structural magnetic resonance imaging (sMRI) data and demographics as predictors, we developed a multi-stage feature selection algorithm to identify the most important features. We then trained a Random Forest (RF) classifier on the final set of 54 selected sMRI and covariate predictors to distinguish between Positive-Agers and Cognitive Decliners. The RF model achieved an AUC of 73%. The top 6 features were age, education, brain total surface area, the area of pars orbitalis, mean intensity of the thalamus, and superior frontal gyrus surface area. Prediction of cognitive trajectory types using sMRI may improve our understanding of successful cognitive aging.

Machine Learning

Aging

Cognitive decline

Structural MRI

FreeSurfer

Details

Title: Subtitle: A multi-stage feature selection method to improve classification of potential super-agers and cognitive decliners using structural brain MRI data-a UK biobank study
Creators: Parvin Mohammadiarvejeh
Mohammad Fili
Alice Dawson
Brandon S Klinedinst
Qian Wang
Shannin Moody
Neil Barnett
Amy Pollpeter
Brittany Larsen
Tianqi Li
Sara A Willette
Jonathan P Mochel
Karin Allenspach
Guiping Hu
Auriel A Willette
Resource Type: Journal article
Publication Details: GeroScience, Vol.47(3), pp.3807-3819
DOI: 10.1007/s11357-024-01458-9
PMID: 39656405
PMCID: PMC12181481
NLM abbreviation: Geroscience
ISSN: 2509-2715
eISSN: 2509-2723
Publisher: SPRINGER
Grant note: 1R01MH126979-01 / NIH HHS AARGD-22-974591 / Alzheimer's Association 5R21EB034184-02 / NIH HHS
Language: English
Electronic publication date: 12/10/2024
Date published: 06/2025
Academic Unit: Neurology
Record Identifier: 9984757067402771

Metrics

17 Record Views

1 Times Cited - Web of Science