Assessing distinct patterns of cognitive aging using tissue-specific brain age prediction based on diffusion tensor imaging and brain morphometry

Abstract

Multimodal imaging enables sensitive measures of the architecture and integrity of the human brain, but the high-dimensional nature of advanced brain imaging features poses inherent challenges for the analyses and interpretations. Multivariate age prediction reduces the dimensionality to one biologically informative summary measure with potential for assessing deviations from normal lifespan trajectories. A number of studies documented remarkably accurate age prediction, but the differential age trajectories and the cognitive sensitivity of distinct brain tissue classes have yet to be adequately characterized. Exploring differential brain age models driven by tissue-specific classifiers provides a hitherto unexplored opportunity to disentangle independent sources of heterogeneity in brain biology. We trained machine-learning models to estimate brain age using various combinations of FreeSurfer based morphometry and diffusion tensor imaging based indices of white matter microstructure in 612 healthy controls aged 18–87 years. To compare the tissue-specific brain ages and their cognitive sensitivity, we applied each of the 11 models in an independent and cognitively well-characterized sample (n = 265, 20–88 years). Correlations between true and estimated age and mean absolute error (MAE) in our test sample were highest for the most comprehensive brain morphometry (r = 0.83, CI:0.78–0.86, MAE = 6.76 years) and white matter microstructure (r = 0.79, CI:0.74–0.83, MAE = 7.28 years) models, confirming sensitivity and generalizability. The deviance from the chronological age were sensitive to performance on several cognitive tests for various models, including spatial Stroop and symbol coding, indicating poorer performance in individuals with an over-estimated age. Tissue-specific brain age models provide sensitive measures of brain integrity, with implications for the study of a range of brain disorders.

Brain age estimation is a sensitive marker of processing speed in the early course of multiple sclerosis

“…We show that brain age estimation In our study, increasing brain age gap were significantly associated with slower performance for the Color Naming condition of CWIT across all time points, corresponding to an estimated 0.13 seconds increase in completion time for every year increase in brain age gap. This finding is in line with a recent study reporting lower processing speed as measured using the Stroop test with higher brain age gap in healthy individuals covering large parts of the adult lifespan 22 . Supporting the sensitivity to individual differences in relevant clinical and cognitive traits, brain age gap has also been linked to negative symptoms in patients with schizophrenia, cognitive impairment in patients with dementia, and symptom burden in patients with MS 21 .…”

“…Having an older-appearing brain is associated with advanced physiological and cognitive ageing and mortality in several neurodegenerative and neurodevelopmental disorders 20,22,23 .…”

Multi-modality neuroimaging brain-age in UK Biobank: relationship to biomedical, lifestyle and cognitive factors

“…Fluid intelligence has previously been linked to brain-PAD (Cole, et al, 2018), as has performance on the trail-making task (Cole, et al, 2015, Cole, et al, 2017b, and other studies report moderate significant relationships between brain-ageing and cognitive performance (Liem, et al, 2017, Richard, et al, 2018. Here I was able to replicate that relationship, though more detailed analysis of how brain-ageing relates to cognitive ageing will require more comprehensive cognitive testing.…”

“…The majority of extant brain-age studies use T1-weighted MRI alone (Cole, et al, 2019b), though previous multi-modality studies have used two or three modalities (Cherubini, et al, 2016, Groves, et al, 2012, Liem, et al, 2017, Richard, et al, 2018. Thanks to UK Biobank, I was able to combine and compared six different modalities As anticipated, T1-weighted MRI proved important for brain-age prediction here, with normalised grey matter volume being the most informative neuroimaging phenotype.…”

“…Several previous brain-age studies have used two or three modalities (Cherubini, et al, 2016, Groves, et al, 2012, Liem, et al, 2017, Richard, et al, 2018. Liem and colleagues (2017) studied n=2354 people, finding improved accuracy when combining T1-weighted structural MRI with resting-state fMRI (MAE = 4.29 years).…”