Regional Neuroanatomic Effects on Brain Age Inferred Using Magnetic Resonance Imaging and Ridge Regression

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

The biological age of the brain differs from its chronological age (CA) and can be used as biomarker of neural/cognitive disease processes and as predictor of mortality. Brain age (BA) is often estimated from magnetic resonance images (MRIs) using machine learning (ML) that rarely indicates how regional brain features contribute to BA. Leveraging an aggregate training sample of 3 418 healthy controls (HCs), we describe a ridge regression model that quantifies each region’s contribution to BA. After model testing on an independent sample of 651 HCs, we compute the coefficient of partial determination R̄2 p for each regional brain volume to quantify its contribution to BA. Model performance is also evaluated using the correlation r between chronological and biological ages, the mean absolute error (MAE ) and mean squared error (MSE) of BA estimates. On training data, r = 0.92, MSE = 70.94 years, MAE = 6.57 years, and R̄2 = 0.81; on test data, r = 0.90, MSE = 81.96 years, MAE = 7.00 years, and R̄2 = 0.79. The regions whose volumes contribute most to BA are the nucleus accumbens (R̄2 p = 7.27%), inferior temporal gyrus (R̄2 p = 4.03%), thalamus (R̄2 p = 3.61%), brainstem (R̄2 p = 3.29%), posterior lateral sulcus (R̄2 p = 3.22%), caudate nucleus (R̄2 p = 3.05%), orbital gyrus (R̄2 p = 2.96%), and precentral gyrus (R̄2 p = 2.80%). Our ridge regression, although outperformed by the most sophisticated ML approaches, identifies the importance and relative contribution of each brain structure to overall BA. Aside from its interpretability and quasi-mechanistic insights, our model can be used to validate future ML approaches for BA estimation.

Original languageEnglish
Pages (from-to)872-881
Number of pages10
JournalJournals of Gerontology - Series A Biological Sciences and Medical Sciences
Volume78
Issue number6
DOIs
StatePublished - Jun 1 2023

Bibliographical note

Publisher Copyright:
© The Author(s) 2022. Published by Oxford University Press on behalf of The Gerontological Society of America.

Keywords

  • Brain aging
  • Cognitive decline
  • Human aging
  • Imaging

ASJC Scopus subject areas

  • General Medicine

Fingerprint

Dive into the research topics of 'Regional Neuroanatomic Effects on Brain Age Inferred Using Magnetic Resonance Imaging and Ridge Regression'. Together they form a unique fingerprint.

Cite this