% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{More:1005113,
author = {More, Shammi and Antonopoulos, Georgios and Hoffstaedter,
Felix and Caspers, Julian and Eickhoff, Simon B. and Patil,
Kaustubh R. and Initiative, Alzheimer's Disease
Neuroimaging},
title = {{B}rain-age prediction: {A} systematic comparison of
machine learning workflows},
journal = {NeuroImage},
volume = {270},
issn = {1053-8119},
address = {Orlando, Fla.},
publisher = {Academic Press},
reportid = {FZJ-2023-01312},
pages = {119947 -},
year = {2023},
abstract = {The difference between age predicted using anatomical brain
scans and chronological age, i.e., the brain-age delta,
provides a proxy for atypical aging. Various data
representations and machine learning (ML) algorithms have
been used for brain-age estimation. However, how these
choices compare on performance criteria important for
real-world applications, such as; (1) within-dataset
accuracy, (2) cross-dataset generalization, (3) test-retest
reliability, and (4) longitudinal consistency, remains
uncharacterized. We evaluated 128 workflows consisting of 16
feature representations derived from gray matter (GM) images
and eight ML algorithms with diverse inductive biases. Using
four large neuroimaging databases covering the adult
lifespan (total N = 2953, 18–88 years), we followed a
systematic model selection procedure by sequentially
applying stringent criteria. The 128 workflows showed a
within-dataset mean absolute error (MAE) between 4.73–8.38
years, from which 32 broadly sampled workflows showed a
cross-dataset MAE between 5.23–8.98 years. The test-retest
reliability and longitudinal consistency of the top 10
workflows were comparable. The choice of feature
representation and the ML algorithm both affected the
performance. Specifically, voxel-wise feature spaces
(smoothed and resampled), with and without principal
components analysis, with non-linear and kernel-based ML
algorithms performed well. Strikingly, the correlation of
brain-age delta with behavioral measures disagreed between
within-dataset and cross-dataset predictions. Application of
the best-performing workflow on the ADNI sample showed a
significantly higher brain-age delta in Alzheimer's and mild
cognitive impairment patients compared to healthy controls.
However, in the presence of age bias, the delta estimates in
the patients varied depending on the sample used for bias
correction. Taken together, brain-age shows promise, but
further evaluation and improvements are needed for its
real-world application.},
cin = {INM-7},
ddc = {610},
cid = {I:(DE-Juel1)INM-7-20090406},
pnm = {5251 - Multilevel Brain Organization and Variability
(POF4-525) / DFG project 432015680 - Automatisierte
Gehirnalterung-Vorhersage und deren Interpretation},
pid = {G:(DE-HGF)POF4-5251 / G:(GEPRIS)432015680},
typ = {PUB:(DE-HGF)16},
pubmed = {36801372},
UT = {WOS:000954924800001},
doi = {10.1016/j.neuroimage.2023.119947},
url = {https://juser.fz-juelich.de/record/1005113},
}