Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data

Lea Baecker, Jessica Dafflon, Pedro F. Da Costa, Rafael Garcia Dias, Sandra Vieira, Cristina Scarpazza, Vince D Calhoun, Joao R. Sato, Andrea Mechelli, Walter H. L. Pinaya

Research output: Contribution to journalArticlepeer-review

60 Citations (Scopus)
390 Downloads (Pure)

Abstract

Brain morphology varies across the ageing trajectory and the prediction of a person’s age using brain features can aid the detection of abnormalities in the ageing process. Existing studies on such ‘brain age prediction’ vary widely in terms of their methods and type of data, so at present the most accurate and generalisable methodological approach is unclear. Therefore, we used the UK Biobank dataset (N = 10,824, age range 47-73) to compare the performance of the machine learning models support vector regression, relevance vector regression, and Gaussian process regression on whole-brain region-based or voxel-based structural magnetic resonance imaging data with or without dimensionality reduction through principal component analysis. Performance was assessed in the validation set through cross-validation as well as an independent test set. The models achieved mean absolute errors between 3.7 and 4.7 years, with those trained on voxel-level data with principal component analysis performing best. Overall, we observed little difference in performance between models trained on the same data type, indicating that the type of input data had greater impact on performance than model choice. All code is provided online in the hope that this will aid future research.
Original languageEnglish
Pages (from-to) 2332-2346
Number of pages15
JournalHuman Brain Mapping
Volume42
Issue number8
Early online date19 Mar 2021
DOIs
Publication statusPublished - 1 Jun 2021

Fingerprint

Dive into the research topics of 'Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data'. Together they form a unique fingerprint.

Cite this