Accelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders

Brain structure in later life reflects both influences of intrinsic aging and those of lifestyle, environment and disease. We developed a deep neural network model trained on brain MRI scans of healthy people to predict “healthy” brain age. Brain regions most informative for the prediction included...

Full description

Saved in:
Bibliographic Details
Published in:Scientific reports Vol. 10; no. 1; p. 19940
Main Authors: Kolbeinsson, Arinbjörn, Filippi, Sarah, Panagakis, Yannis, Matthews, Paul M., Elliott, Paul, Dehghan, Abbas, Tzoulaki, Ioanna
Format: Journal Article
Language:English
Published: London Nature Publishing Group UK 17.11.2020
Nature Publishing Group
Subjects:
631/114/1305
631/378/2612
692/499
Age differences
Aging
Aging - genetics
Aging - pathology
Amygdala
Association analysis
Bias
Biobanks
Blood pressure
Body mass index
Brain
Brain - pathology
Brain Diseases - genetics
Brain Diseases - pathology
Brain research
Cardiovascular Diseases - genetics
Cardiovascular Diseases - pathology
Cerebellum
Cognitive ability
Cortex (insular)
Dementia
Dementia disorders
Diabetes
Diabetes mellitus
Disease
Epidemiology
Health care
Health risks
Humanities and Social Sciences
Humans
Lifestyles
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Mendelian Randomization Analysis
Metabolic Diseases - genetics
Metabolic Diseases - pathology
Metabolism
multidisciplinary
Neural networks
Neural Networks, Computer
Neuroimaging - methods
Public health
Quantitative Trait Loci
Risk factors
Science
Science (multidisciplinary)
ISSN:2045-2322, 2045-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Brain structure in later life reflects both influences of intrinsic aging and those of lifestyle, environment and disease. We developed a deep neural network model trained on brain MRI scans of healthy people to predict “healthy” brain age. Brain regions most informative for the prediction included the cerebellum, hippocampus, amygdala and insular cortex. We then applied this model to data from an independent group of people not stratified for health. A phenome-wide association analysis of over 1,410 traits in the UK Biobank with differences between the predicted and chronological ages for the second group identified significant associations with over 40 traits including diseases (e.g., type I and type II diabetes), disease risk factors (e.g., increased diastolic blood pressure and body mass index), and poorer cognitive function. These observations highlight relationships between brain and systemic health and have implications for understanding contributions of the latter to late life dementia risk.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-020-76518-z