Predicting brain-age from multimodal imaging data captures cognitive impairment

Abstract

The disparity between the chronological age of an individual and their brain-age measured based on biological information has the potential to offer clinically relevant biomarkers of neurological syndromes that emerge late in the lifespan. While prior brain-age prediction studies have relied exclusively on either structural or functional brain data, here we investigate how multimodal brain-imaging data improves age prediction. Using cortical anatomy and whole-brain functional connectivity on a large adult lifespan sample (N=2354, age 19-82), we found that multimodal data improves brain-based age prediction, resulting in a mean absolute prediction error of 4.29 years. Furthermore, we found that the discrepancy between predicted age and chronological age captures cognitive impairment. Importantly, the brain-age measure was robust to confounding effects: head motion did not drive brain-based age prediction and our models generalized reasonably to an independent dataset acquired at a different site (N=475). Generalization performance was increased by training models on a larger and more heterogeneous dataset. The robustness of multimodal brain-age prediction to confounds, generalizability across sites, and sensitivity to clinically-relevant impairments, suggests promising future application to the early prediction of neurocognitive disorders.

Using and understanding cross-validation strategies. Perspectives on Saeb et al.

“…In a different application, Liem et al. [10] showed prediction of brain age from magnetic resonance images. However, it is known that elderly people tend to move more in the scanners, and that this movement has a systematic effect on the images.…”

“…However, the example of creating a balanced test set in age prediction [10] outlines the importance of having many observations in the test set. It is impossible to accumulate rich statistics on errors in small test sets.…”

How to Measure Population Aging? The Answer Is Less than Obvious: A Review

“…Studies use either or sometimes both [29]. Applying machine learning analysis to neuroimaging data from a healthy lifespan sample ( n = 2,001, 18–90 years) yielded coefficients that were successfully validated in a second sample of older adults using indicators of functional aging, such as walking speed, grip strength, or cognitive mechanics [30].…”

What the structural-functional connectome reveals about brain aging: The key role of the fronto-striatal-thalamic circuit and the rejuvenating impact of physical activity

“…By combining morphological descriptors together with functional connectivity ones, Liem et al (2017) were able to improve age estimation up to 4.29 years 53 . In relation to connectivity metrics, it was shown in a seminal study that resting FC descriptors estimated brain age 51 , but rather than addressing physiological ageing, the authors focused on neural development in the age range between 7 and 30 years.…”

“…To test these hypotheses, following previous work [39][40][41][51][52][53][54][55][56][57][58][59] , we built an ageing data-driven model to estimate the ChA of participants based on SC and FC biomarkers and investigated the extent to which the level of PA mediates the participant's brain biological age. Lastly, we discuss the general implications and applications of the described methodology.…”