Predicting age from cortical structure across the lifespan

Despite inter-individual differences in cortical structure, cross-sectional and longitudinal studies have demonstrated a large degree of population-level consistency in age-related differences in brain morphology. The present study assessed how accurately an individual’s age could be predicted by es...

Full description

Bibliographic Details
Main Authors: Madan, Christopher R., Kensinger, Elizabeth A.
Format: Article
Language:English
Published: Wiley 2018
Online Access:https://eprints.nottingham.ac.uk/49119/
_version_ 1848797926021660672
author Madan, Christopher R.
Kensinger, Elizabeth A.
author_facet Madan, Christopher R.
Kensinger, Elizabeth A.
author_sort Madan, Christopher R.
building Nottingham Research Data Repository
collection Online Access
description Despite inter-individual differences in cortical structure, cross-sectional and longitudinal studies have demonstrated a large degree of population-level consistency in age-related differences in brain morphology. The present study assessed how accurately an individual’s age could be predicted by estimates of cortical morphology, comparing a variety of structural measures, including thickness, gyrification, and fractal dimensionality. Structural measures were calculated across up to seven different parcellation approaches, ranging from 1 region to 1000 regions. The age-prediction framework was trained using morphological measures obtained from T1-weighted MRI volumes collected from multiple sites, yielding a training dataset of 1056 healthy adults, aged 18-97. Age predictions were calculated using a machine-learning approach that incorporated non-linear differences over the lifespan. In two independent, held-out test samples, age predictions had a median error of 6-7 years. Age predictions were best when using a combination of cortical metrics, both thickness and fractal dimensionality. Overall, the results reveal that age-related differences in brain structure are systematic enough to enable reliable age prediction based on metrics of cortical morphology.
first_indexed 2025-11-14T20:11:38Z
format Article
id nottingham-49119
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T20:11:38Z
publishDate 2018
publisher Wiley
recordtype eprints
repository_type Digital Repository
spelling nottingham-491192019-02-12T04:30:11Z https://eprints.nottingham.ac.uk/49119/ Predicting age from cortical structure across the lifespan Madan, Christopher R. Kensinger, Elizabeth A. Despite inter-individual differences in cortical structure, cross-sectional and longitudinal studies have demonstrated a large degree of population-level consistency in age-related differences in brain morphology. The present study assessed how accurately an individual’s age could be predicted by estimates of cortical morphology, comparing a variety of structural measures, including thickness, gyrification, and fractal dimensionality. Structural measures were calculated across up to seven different parcellation approaches, ranging from 1 region to 1000 regions. The age-prediction framework was trained using morphological measures obtained from T1-weighted MRI volumes collected from multiple sites, yielding a training dataset of 1056 healthy adults, aged 18-97. Age predictions were calculated using a machine-learning approach that incorporated non-linear differences over the lifespan. In two independent, held-out test samples, age predictions had a median error of 6-7 years. Age predictions were best when using a combination of cortical metrics, both thickness and fractal dimensionality. Overall, the results reveal that age-related differences in brain structure are systematic enough to enable reliable age prediction based on metrics of cortical morphology. Wiley 2018-03-03 Article PeerReviewed application/pdf en https://eprints.nottingham.ac.uk/49119/1/jurojin_final_sm.pdf Madan, Christopher R. and Kensinger, Elizabeth A. (2018) Predicting age from cortical structure across the lifespan. European Journal of Neuroscience, 47 (5). pp. 399-416. ISSN 1460-9568 http://onlinelibrary.wiley.com/doi/10.1111/ejn.13835/abstract? doi:10.1111/ejn.13835 doi:10.1111/ejn.13835
spellingShingle Madan, Christopher R.
Kensinger, Elizabeth A.
Predicting age from cortical structure across the lifespan
title Predicting age from cortical structure across the lifespan
title_full Predicting age from cortical structure across the lifespan
title_fullStr Predicting age from cortical structure across the lifespan
title_full_unstemmed Predicting age from cortical structure across the lifespan
title_short Predicting age from cortical structure across the lifespan
title_sort predicting age from cortical structure across the lifespan
url https://eprints.nottingham.ac.uk/49119/
https://eprints.nottingham.ac.uk/49119/
https://eprints.nottingham.ac.uk/49119/